diff --git a/docs/assets/index-DchNQQNQ.js b/docs/assets/index-DchNQQNQ.js new file mode 100644 index 0000000..50e9c38 --- /dev/null +++ b/docs/assets/index-DchNQQNQ.js @@ -0,0 +1,11 @@ +var e=Object.create,t=Object.defineProperty,n=Object.getOwnPropertyDescriptor,r=Object.getOwnPropertyNames,i=Object.getPrototypeOf,a=Object.prototype.hasOwnProperty,o=(e,t)=>()=>(t||(e((t={exports:{}}).exports,t),e=null),t.exports),s=(e,i,o,s)=>{if(i&&typeof i==`object`||typeof i==`function`)for(var c=r(i),l=0,u=c.length,d;li[e]).bind(null,d),enumerable:!(s=n(i,d))||s.enumerable});return e},c=(n,r,o)=>(o=n==null?{}:e(i(n)),s(r||!n||!n.__esModule||!a.call(n,`default`)?t(o,`default`,{value:n,enumerable:!0}):o,n));(function(){let e=document.createElement(`link`).relList;if(e&&e.supports&&e.supports(`modulepreload`))return;for(let e of document.querySelectorAll(`link[rel="modulepreload"]`))n(e);new MutationObserver(e=>{for(let t of e)if(t.type===`childList`)for(let e of t.addedNodes)e.tagName===`LINK`&&e.rel===`modulepreload`&&n(e)}).observe(document,{childList:!0,subtree:!0});function t(e){let t={};return e.integrity&&(t.integrity=e.integrity),e.referrerPolicy&&(t.referrerPolicy=e.referrerPolicy),t.credentials=e.crossOrigin===`use-credentials`?`include`:e.crossOrigin===`anonymous`?`omit`:`same-origin`,t}function n(e){if(e.ep)return;e.ep=!0;let n=t(e);fetch(e.href,n)}})();var l=o((e=>{var t=Symbol.for(`react.transitional.element`),n=Symbol.for(`react.portal`),r=Symbol.for(`react.fragment`),i=Symbol.for(`react.strict_mode`),a=Symbol.for(`react.profiler`),o=Symbol.for(`react.consumer`),s=Symbol.for(`react.context`),c=Symbol.for(`react.forward_ref`),l=Symbol.for(`react.suspense`),u=Symbol.for(`react.memo`),d=Symbol.for(`react.lazy`),f=Symbol.for(`react.activity`),p=Symbol.for(`react.view_transition`),m=Symbol.iterator;function h(e){return typeof e!=`object`||!e?null:(e=m&&e[m]||e[`@@iterator`],typeof e==`function`?e:null)}var g={isMounted:function(){return!1},enqueueForceUpdate:function(){},enqueueReplaceState:function(){},enqueueSetState:function(){}},_=Object.assign,v={};function y(e,t,n){this.props=e,this.context=t,this.refs=v,this.updater=n||g}y.prototype.isReactComponent={},y.prototype.setState=function(e,t){if(typeof e!=`object`&&typeof e!=`function`&&e!=null)throw Error(`takes an object of state variables to update or a function which returns an object of state variables.`);this.updater.enqueueSetState(this,e,t,`setState`)},y.prototype.forceUpdate=function(e){this.updater.enqueueForceUpdate(this,e,`forceUpdate`)};function b(){}b.prototype=y.prototype;function ee(e,t,n){this.props=e,this.context=t,this.refs=v,this.updater=n||g}var x=ee.prototype=new b;x.constructor=ee,_(x,y.prototype),x.isPureReactComponent=!0;var te=Array.isArray;function ne(){}var S={H:null,A:null,T:null,S:null},re=Object.prototype.hasOwnProperty;function C(e,n,r){var i=r.ref;return{$$typeof:t,type:e,key:n,ref:i===void 0?null:i,props:r}}function ie(e,t){return C(e.type,t,e.props)}function w(e){return typeof e==`object`&&!!e&&e.$$typeof===t}function ae(e){var t={"=":`=0`,":":`=2`};return`$`+e.replace(/[=:]/g,function(e){return t[e]})}var T=/\/+/g;function oe(e,t){return typeof e==`object`&&e&&e.key!=null?ae(``+e.key):t.toString(36)}function se(e){switch(e.status){case`fulfilled`:return e.value;case`rejected`:throw e.reason;default:switch(typeof e.status==`string`?e.then(ne,ne):(e.status=`pending`,e.then(function(t){e.status===`pending`&&(e.status=`fulfilled`,e.value=t)},function(t){e.status===`pending`&&(e.status=`rejected`,e.reason=t)})),e.status){case`fulfilled`:return e.value;case`rejected`:throw e.reason}}throw e}function ce(e,r,i,a,o){var s=typeof e;(s===`undefined`||s===`boolean`)&&(e=null);var c=!1;if(e===null)c=!0;else switch(s){case`bigint`:case`string`:case`number`:c=!0;break;case`object`:switch(e.$$typeof){case t:case n:c=!0;break;case d:return c=e._init,ce(c(e._payload),r,i,a,o)}}if(c)return o=o(e),c=a===``?`.`+oe(e,0):a,te(o)?(i=``,c!=null&&(i=c.replace(T,`$&/`)+`/`),ce(o,r,i,``,function(e){return e})):o!=null&&(w(o)&&(o=ie(o,i+(o.key==null||e&&e.key===o.key?``:(``+o.key).replace(T,`$&/`)+`/`)+c)),r.push(o)),1;c=0;var l=a===``?`.`:a+`:`;if(te(e))for(var u=0;u{t.exports=l()})),d=o((e=>{function t(e,t){var n=e.length;e.push(t);a:for(;0>>1,a=e[r];if(0>>1;ri(c,n))li(u,c)?(e[r]=u,e[l]=n,r=l):(e[r]=c,e[s]=n,r=s);else if(li(u,n))e[r]=u,e[l]=n,r=l;else break a}}return t}function i(e,t){var n=e.sortIndex-t.sortIndex;return n===0?e.id-t.id:n}if(e.unstable_now=void 0,typeof performance==`object`&&typeof performance.now==`function`){var a=performance;e.unstable_now=function(){return a.now()}}else{var o=Date,s=o.now();e.unstable_now=function(){return o.now()-s}}var c=[],l=[],u=1,d=null,f=3,p=!1,m=!1,h=!1,g=!1,_=typeof setTimeout==`function`?setTimeout:null,v=typeof clearTimeout==`function`?clearTimeout:null,y=typeof setImmediate<`u`?setImmediate:null;function b(e){for(var i=n(l);i!==null;){if(i.callback===null)r(l);else if(i.startTime<=e)r(l),i.sortIndex=i.expirationTime,t(c,i);else break;i=n(l)}}function ee(e){if(h=!1,b(e),!m){if(n(c)!==null)m=!0,x||(x=!0,ie());else{var t=n(l);t!==null&&T(ee,t.startTime-e)}}}var x=!1,te=-1,ne=5,S=-1;function re(){return g?!0:!(e.unstable_now()-St&&re());){var o=d.callback;if(typeof o==`function`){d.callback=null,f=d.priorityLevel;var s=o(d.expirationTime<=t);if(t=e.unstable_now(),typeof s==`function`){d.callback=s,b(t),i=!0;break b}d===n(c)&&r(c),b(t)}else r(c);d=n(c)}if(d!==null)i=!0;else{var u=n(l);u!==null&&T(ee,u.startTime-t),i=!1}}break a}finally{d=null,f=a,p=!1}i=void 0}}finally{i?ie():x=!1}}}var ie;if(typeof y==`function`)ie=function(){y(C)};else if(typeof MessageChannel<`u`){var w=new MessageChannel,ae=w.port2;w.port1.onmessage=C,ie=function(){ae.postMessage(null)}}else ie=function(){_(C,0)};function T(t,n){te=_(function(){t(e.unstable_now())},n)}e.unstable_IdlePriority=5,e.unstable_ImmediatePriority=1,e.unstable_LowPriority=4,e.unstable_NormalPriority=3,e.unstable_Profiling=null,e.unstable_UserBlockingPriority=2,e.unstable_cancelCallback=function(e){e.callback=null},e.unstable_forceFrameRate=function(e){0>e||125o?(r.sortIndex=a,t(l,r),n(c)===null&&r===n(l)&&(h?(v(te),te=-1):h=!0,T(ee,a-o))):(r.sortIndex=s,t(c,r),m||p||(m=!0,x||(x=!0,ie()))),r},e.unstable_shouldYield=re,e.unstable_wrapCallback=function(e){var t=f;return function(){var n=f;f=t;try{return e.apply(this,arguments)}finally{f=n}}}})),f=o(((e,t)=>{t.exports=d()})),p=o((e=>{var t=u();function n(e){var t=`https://react.dev/errors/`+e;if(1{function n(){if(!(typeof __REACT_DEVTOOLS_GLOBAL_HOOK__>`u`||typeof __REACT_DEVTOOLS_GLOBAL_HOOK__.checkDCE!=`function`))try{__REACT_DEVTOOLS_GLOBAL_HOOK__.checkDCE(n)}catch(e){console.error(e)}}n(),t.exports=p()})),h=o((e=>{var t=f(),n=u(),r=m();function i(e){var t=`https://react.dev/errors/`+e;if(1De||(e.current=Ee[De],Ee[De]=null,De--)}function O(e,t){De++,Ee[De]=e.current,e.current=t}var Ae=Oe(null),je=Oe(null),Me=Oe(null),Ne=Oe(null);function Pe(e,t){switch(O(Me,t),O(je,e),O(Ae,null),t.nodeType){case 9:case 11:e=(e=t.documentElement)&&(e=e.namespaceURI)?up(e):0;break;default:if(e=t.tagName,t=t.namespaceURI)t=up(t),e=dp(t,e);else switch(e){case`svg`:e=1;break;case`math`:e=2;break;default:e=0}}ke(Ae),O(Ae,e)}function Fe(){ke(Ae),ke(je),ke(Me)}function Ie(e){var t=e.memoizedState;t!==null&&(sh._currentValue=t.memoizedState,O(Ne,e)),t=Ae.current;var n=dp(t,e.type);t!==n&&(O(je,e),O(Ae,n))}function Le(e){je.current===e&&(ke(Ae),ke(je)),Ne.current===e&&(ke(Ne),sh._currentValue=Te)}var Re,ze;function Be(e){if(Re===void 0)try{throw Error()}catch(e){var t=e.stack.trim().match(/\n( *(at )?)/);Re=t&&t[1]||``,ze=-1)`:-1i||c[r]!==l[i]){var u=` +`+c[r].replace(` at new `,` at `);return e.displayName&&u.includes(``)&&(u=u.replace(``,e.displayName)),u}while(1<=r&&0<=i);break}}}finally{Ve=!1,Error.prepareStackTrace=n}return(n=e?e.displayName||e.name:``)?Be(n):``}function Ue(e,t){switch(e.tag){case 26:case 27:case 5:return Be(e.type);case 16:return Be(`Lazy`);case 13:return e.child!==t&&t!==null?Be(`Suspense Fallback`):Be(`Suspense`);case 19:return Be(`SuspenseList`);case 0:case 15:return He(e.type,!1);case 11:return He(e.type.render,!1);case 1:return He(e.type,!0);case 31:return Be(`Activity`);case 30:return Be(`ViewTransition`);default:return``}}function We(e){try{var t=``,n=null;do t+=Ue(e,n),n=e,e=e.return;while(e);return t}catch(e){return` +Error generating stack: `+e.message+` +`+e.stack}}var Ge=Object.prototype.hasOwnProperty,Ke=t.unstable_scheduleCallback,qe=t.unstable_cancelCallback,Je=t.unstable_shouldYield,Ye=t.unstable_requestPaint,Xe=t.unstable_now,Ze=t.unstable_getCurrentPriorityLevel,Qe=t.unstable_ImmediatePriority,$e=t.unstable_UserBlockingPriority,et=t.unstable_NormalPriority,tt=t.unstable_LowPriority,nt=t.unstable_IdlePriority,rt=t.log,it=t.unstable_setDisableYieldValue,at=null,ot=null;function st(e){if(typeof rt==`function`&&it(e),ot&&typeof ot.setStrictMode==`function`)try{ot.setStrictMode(at,e)}catch{}}var ct=Math.clz32?Math.clz32:dt,lt=Math.log,ut=Math.LN2;function dt(e){return e>>>=0,e===0?32:31-(lt(e)/ut|0)|0}var ft=256,pt=262144,mt=4194304;function ht(e){var t=e&42;if(t!==0)return t;switch(e&-e){case 1:return 1;case 2:return 2;case 4:return 4;case 8:return 8;case 16:return 16;case 32:return 32;case 64:return 64;case 128:return 128;case 256:case 512:case 1024:case 2048:case 4096:case 8192:case 16384:case 32768:case 65536:case 131072:return e&-e;case 262144:case 524288:case 1048576:case 2097152:return e&3932160;case 4194304:case 8388608:case 16777216:case 33554432:return e&62914560;case 67108864:return 67108864;case 134217728:return 134217728;case 268435456:return 268435456;case 536870912:return 536870912;case 1073741824:return 0;default:return e}}function gt(e,t,n){var r=e.pendingLanes;if(r===0)return 0;var i=0,a=e.suspendedLanes,o=e.pingedLanes;e=e.warmLanes;var s=r&134217727;return s===0?(s=r&~a,s===0?o===0?n||(n=r&~e,n!==0&&(i=ht(n))):i=ht(o):i=ht(s)):(r=s&~a,r===0?(o&=s,o===0?n||(n=s&~e,n!==0&&(i=ht(n))):i=ht(o)):i=ht(r)),i===0?0:t!==0&&t!==i&&(t&a)===0&&(a=i&-i,n=t&-t,a>=n||a===32&&n&4194048)?t:i}function _t(e,t){return(e.pendingLanes&~(e.suspendedLanes&~e.pingedLanes)&t)===0}function vt(e,t){t&8&&(t|=t&32);var n=e.entangledLanes;if(n!==0)for(e=e.entanglements,n&=t;0n;n++)t.push(e);return t}function St(e,t){e.pendingLanes|=t,t!==268435456&&(e.suspendedLanes=0,e.pingedLanes=0,e.warmLanes=0)}function Ct(e,t,n,r,i,a){var o=e.pendingLanes;e.pendingLanes=n,e.suspendedLanes=0,e.pingedLanes=0,e.warmLanes=0,e.expiredLanes&=n,e.entangledLanes&=n,e.errorRecoveryDisabledLanes&=n,e.shellSuspendCounter=0;var s=e.entanglements,c=e.expirationTimes,l=e.hiddenUpdates;for(n=o&~n;0`u`||window.document===void 0||window.document.createElement===void 0),Rn=!1;if(Ln)try{var zn={};Object.defineProperty(zn,"passive",{get:function(){Rn=!0}}),window.addEventListener(`test`,zn,zn),window.removeEventListener(`test`,zn,zn)}catch{Rn=!1}var Bn=null,Vn=null,Hn=null;function Un(){if(Hn)return Hn;var e,t=Vn,n=t.length,r,i=`value`in Bn?Bn.value:Bn.textContent,a=i.length;for(e=0;e=Sr),Tr=` `,Er=!1;function Dr(e,t){switch(e){case`keyup`:return br.indexOf(t.keyCode)!==-1;case`keydown`:return t.keyCode!==229;case`keypress`:case`mousedown`:case`focusout`:return!0;default:return!1}}function Or(e){return e=e.detail,typeof e==`object`&&`data`in e?e.data:null}var kr=!1;function Ar(e,t){switch(e){case`compositionend`:return Or(t);case`keypress`:return t.which===32?(Er=!0,Tr):null;case`textInput`:return e=t.data,e===Tr&&Er?null:e;default:return null}}function jr(e,t){if(kr)return e===`compositionend`||!xr&&Dr(e,t)?(e=Un(),Hn=Vn=Bn=null,kr=!1,e):null;switch(e){case`paste`:return null;case`keypress`:if(!(t.ctrlKey||t.altKey||t.metaKey)||t.ctrlKey&&t.altKey){if(t.char&&1=t)return{node:n,offset:t-e};e=r}a:{for(;n;){if(n.nextSibling){n=n.nextSibling;break a}n=n.parentNode}n=void 0}n=ei(n)}}function ni(e,t){return e&&t?e===t?!0:e&&e.nodeType===3?!1:t&&t.nodeType===3?ni(e,t.parentNode):`contains`in e?e.contains(t):e.compareDocumentPosition?!!(e.compareDocumentPosition(t)&16):!1:!1}function ri(e){e=e!=null&&e.ownerDocument!=null&&e.ownerDocument.defaultView!=null?e.ownerDocument.defaultView:window;for(var t=$r(e.document);t instanceof e.HTMLIFrameElement;){try{var n=typeof t.contentWindow.location.href==`string`}catch{n=!1}if(n)e=t.contentWindow;else break;t=$r(e.document)}return t}function ii(e){var t=e&&e.nodeName&&e.nodeName.toLowerCase();return t&&(t===`input`&&(e.type===`text`||e.type===`search`||e.type===`tel`||e.type===`url`||e.type===`password`)||t===`textarea`||e.contentEditable===`true`)}var ai=Ln&&`documentMode`in document&&11>=document.documentMode,oi=null,si=null,ci=null,li=!1;function ui(e,t,n){var r=n.window===n?n.document:n.nodeType===9?n:n.ownerDocument;li||oi==null||oi!==$r(r)||(r=oi,`selectionStart`in r&&ii(r)?r={start:r.selectionStart,end:r.selectionEnd}:(r=(r.ownerDocument&&r.ownerDocument.defaultView||window).getSelection(),r={anchorNode:r.anchorNode,anchorOffset:r.anchorOffset,focusNode:r.focusNode,focusOffset:r.focusOffset}),ci&&Qr(ci,r)||(ci=r,r=Jf(si,`onSelect`),0>=o,i-=o,oa=1<<32-ct(t)+i|n<h?(g=d,d=null):g=d.sibling;var _=p(i,d,s[h],c);if(_===null){d===null&&(d=g);break}e&&d&&_.alternate===null&&t(i,d),a=o(_,a,h),u===null?l=_:u.sibling=_,u=_,d=g}if(h===s.length)return n(i,d),j&&ca(i,h),l;if(d===null){for(;hg?(_=h,h=null):_=h.sibling;var y=p(a,h,v.value,l);if(y===null){h===null&&(h=_);break}e&&h&&y.alternate===null&&t(a,h),s=o(y,s,g),d===null?u=y:d.sibling=y,d=y,h=_}if(v.done)return n(a,h),j&&ca(a,g),u;if(h===null){for(;!v.done;g++,v=c.next())v=f(a,v.value,l),v!==null&&(s=o(v,s,g),d===null?u=v:d.sibling=v,d=v);return j&&ca(a,g),u}for(h=r(h);!v.done;g++,v=c.next())v=m(h,a,g,v.value,l),v!==null&&(e&&(_=v.alternate,_!==null&&h.delete(_.key===null?g:_.key)),s=o(v,s,g),d===null?u=v:d.sibling=v,d=v);return e&&h.forEach(function(e){return t(a,e)}),j&&ca(a,g),u}function _(e,r,o,c){if(typeof o==`object`&&o&&o.type===T&&o.key===null&&o.props.ref===void 0&&(o=o.props.children),typeof o==`object`&&o){switch(o.$$typeof){case w:a:{for(var l=o.key;r!==null;){if(r.key===l){if(l=o.type,l===T){if(r.tag===7){n(e,r.sibling),c=a(r,o.props.children),_o(c,o),c.return=e,e=c;break a}}else if(r.elementType===l||typeof l==`object`&&l&&l.$$typeof===me&&lo(l)===r.type){n(e,r.sibling),c=a(r,o.props),_o(c,o),c.return=e,e=c;break a}n(e,r);break}t(e,r),r=r.sibling}o.type===T?(c=qi(o.props.children,e.mode,c,o.key),_o(c,o),c.return=e,e=c):(c=Ki(o.type,o.key,o.props,null,e.mode,c),_o(c,o),c.return=e,e=c)}return s(e);case ae:a:{for(l=o.key;r!==null;){if(r.key===l){if(r.tag===4&&r.stateNode.containerInfo===o.containerInfo&&r.stateNode.implementation===o.implementation){n(e,r.sibling),c=a(r,o.children||[]),c.return=e,e=c;break a}n(e,r);break}t(e,r),r=r.sibling}c=Xi(o,e.mode,c),c.return=e,e=c}return s(e);case me:return o=lo(o),_(e,r,o,c)}if(we(o))return h(e,r,o,c);if(xe(o)){if(l=xe(o),typeof l!=`function`)throw Error(i(150));return o=l.call(o),g(e,r,o,c)}if(typeof o.then==`function`)return _(e,r,go(o),c);if(o.$$typeof===le)return _(e,r,Fa(e,o),c);vo(e,o)}return typeof o==`string`&&o!==``||typeof o==`number`||typeof o==`bigint`?(o=``+o,r!==null&&r.tag===6?(n(e,r.sibling),c=a(r,o),c.return=e,e=c):(n(e,r),c=Ji(o,e.mode,c),c.return=e,e=c),s(e)):n(e,r)}return function(e,t,n,r){try{ho=0;var i=_(e,t,n,r);return mo=null,i}catch(t){if(t===ro||t===ao)throw t;var a=Hi(29,t,null,e.mode);return a.lanes=r,a.return=e,a}}}var bo=yo(!0),xo=yo(!1),So=!1;function Co(e){e.updateQueue={baseState:e.memoizedState,firstBaseUpdate:null,lastBaseUpdate:null,shared:{pending:null,lanes:0,hiddenCallbacks:null},callbacks:null}}function wo(e,t){e=e.updateQueue,t.updateQueue===e&&(t.updateQueue={baseState:e.baseState,firstBaseUpdate:e.firstBaseUpdate,lastBaseUpdate:e.lastBaseUpdate,shared:e.shared,callbacks:null})}function To(e){return{lane:e,tag:0,payload:null,callback:null,next:null}}function Eo(e,t,n){var r=e.updateQueue;if(r===null)return null;if(r=r.shared,W&2){var i=r.pending;return i===null?t.next=t:(t.next=i.next,i.next=t),r.pending=t,t=zi(e),Ri(e,null,n),t}return Fi(e,r,t,n),zi(e)}function Do(e,t,n){if(t=t.updateQueue,t!==null&&(t=t.shared,n&4194048)){var r=t.lanes;r&=e.pendingLanes,n|=r,t.lanes=n,Tt(e,n)}}function Oo(e,t){var n=e.updateQueue,r=e.alternate;if(r!==null&&(r=r.updateQueue,n===r)){var i=null,a=null;if(n=n.firstBaseUpdate,n!==null){do{var o={lane:n.lane,tag:n.tag,payload:n.payload,callback:null,next:null};a===null?i=a=o:a=a.next=o,n=n.next}while(n!==null);a===null?i=a=t:a=a.next=t}else i=a=t;n={baseState:r.baseState,firstBaseUpdate:i,lastBaseUpdate:a,shared:r.shared,callbacks:r.callbacks},e.updateQueue=n;return}e=n.lastBaseUpdate,e===null?n.firstBaseUpdate=t:e.next=t,n.lastBaseUpdate=t}var ko=!1;function Ao(){if(ko){var e=Ja;if(e!==null)throw e}}function jo(e,t,n,r){ko=!1;var i=e.updateQueue;So=!1;var a=i.firstBaseUpdate,o=i.lastBaseUpdate,s=i.shared.pending;if(s!==null){i.shared.pending=null;var c=s,l=c.next;c.next=null,o===null?a=l:o.next=l,o=c;var u=e.alternate;u!==null&&(u=u.updateQueue,s=u.lastBaseUpdate,s!==o&&(s===null?u.firstBaseUpdate=l:s.next=l,u.lastBaseUpdate=c))}if(a!==null){var d=i.baseState;o=0,u=l=c=null,s=a;do{var f=s.lane&-536870913,p=f!==s.lane;if(p?(q&f)===f:(r&f)===f){f!==0&&f===qa&&(ko=!0),u!==null&&(u=u.next={lane:0,tag:s.tag,payload:s.payload,callback:null,next:null});a:{var m=e,h=s;f=t;var g=n;switch(h.tag){case 1:if(m=h.payload,typeof m==`function`){d=m.call(g,d,f);break a}d=m;break a;case 3:m.flags=m.flags&-65537|128;case 0:if(m=h.payload,f=typeof m==`function`?m.call(g,d,f):m,f==null)break a;d=C({},d,f);break a;case 2:So=!0}}f=s.callback,f!==null&&(e.flags|=64,p&&(e.flags|=8192),p=i.callbacks,p===null?i.callbacks=[f]:p.push(f))}else p={lane:f,tag:s.tag,payload:s.payload,callback:s.callback,next:null},u===null?(l=u=p,c=d):u=u.next=p,o|=f;if(s=s.next,s===null){if(s=i.shared.pending,s===null)break;p=s,s=p.next,p.next=null,i.lastBaseUpdate=p,i.shared.pending=null}}while(1);u===null&&(c=d),i.baseState=c,i.firstBaseUpdate=l,i.lastBaseUpdate=u,a===null&&(i.shared.lanes=0),sd|=o,e.lanes=o,e.memoizedState=d}}function Mo(e,t){if(typeof e!=`function`)throw Error(i(191,e));e.call(t)}function No(e,t){var n=e.callbacks;if(n!==null)for(e.callbacks=null,e=0;ea?a:8;var o=E.T,s={};s.types=o===null?null:o.types,E.T=s,gc(e,!1,t,n);try{var c=i(),l=E.S;l!==null&&l(s,c),typeof c==`object`&&c&&typeof c.then==`function`?hc(e,t,Za(c,r),jd(e)):hc(e,t,r,jd(e))}catch(n){hc(e,t,{then:function(){},status:`rejected`,reason:n},jd())}finally{D.p=a,o!==null&&s.types!==null&&(o.types=s.types),E.T=o}}function ac(){}function oc(e,t,n,r){if(e.tag!==5)throw Error(i(476));var a=sc(e).queue;ic(e,a,t,Te,n===null?ac:function(){return cc(e),n(r)})}function sc(e){var t=e.memoizedState;if(t!==null)return t;t={memoizedState:Te,baseState:Te,baseQueue:null,queue:{pending:null,lanes:0,dispatch:null,lastRenderedReducer:_s,lastRenderedState:Te},next:null};var n={};return t.next={memoizedState:n,baseState:n,baseQueue:null,queue:{pending:null,lanes:0,dispatch:null,lastRenderedReducer:_s,lastRenderedState:n},next:null},e.memoizedState=t,e=e.alternate,e!==null&&(e.memoizedState=t),t}function cc(e){var t=sc(e);t.next===null&&(t=e.alternate.memoizedState),hc(e,t.next.queue,{},jd())}function lc(){return Pa(sh)}function uc(){return L().memoizedState}function dc(){return L().memoizedState}function fc(e){for(var t=e.return;t!==null;){switch(t.tag){case 24:case 3:var n=jd();e=To(n);var r=Eo(t,e,n);r!==null&&(Pd(r,t,n),Do(r,t,n)),t={cache:Ba()},e.payload=t;return}t=t.return}}function pc(e,t,n){var r=jd();n={lane:r,revertLane:0,gesture:null,action:n,hasEagerState:!1,eagerState:null,next:null},_c(e)?vc(t,n):(n=Ii(e,t,n,r),n!==null&&(Pd(n,e,r),yc(n,t,r)))}function mc(e,t,n){hc(e,t,n,jd())}function hc(e,t,n,r){var i={lane:r,revertLane:0,gesture:null,action:n,hasEagerState:!1,eagerState:null,next:null};if(_c(e))vc(t,i);else{var a=e.alternate;if(e.lanes===0&&(a===null||a.lanes===0)&&(a=t.lastRenderedReducer,a!==null))try{var o=t.lastRenderedState,s=a(o,n);if(i.hasEagerState=!0,i.eagerState=s,Zr(s,o))return Fi(e,t,i,0),G===null&&Pi(),!1}catch{}if(n=Ii(e,t,i,r),n!==null)return Pd(n,e,r),yc(n,t,r),!0}return!1}function gc(e,t,n,r){if(r={lane:2,revertLane:Pf(),gesture:null,action:r,hasEagerState:!1,eagerState:null,next:null},_c(e)){if(t)throw Error(i(479))}else t=Ii(e,n,r,2),t!==null&&Pd(t,e,2)}function _c(e){var t=e.alternate;return e===N||t!==null&&t===N}function vc(e,t){Qo=Zo=!0;var n=e.pending;n===null?t.next=t:(t.next=n.next,n.next=t),e.pending=t}function yc(e,t,n){if(n&4194048){var r=t.lanes;r&=e.pendingLanes,n|=r,t.lanes=n,Tt(e,n)}}var bc={readContext:Pa,use:hs,useCallback:I,useContext:I,useEffect:I,useImperativeHandle:I,useLayoutEffect:I,useInsertionEffect:I,useMemo:I,useReducer:I,useRef:I,useState:I,useDebugValue:I,useDeferredValue:I,useTransition:I,useSyncExternalStore:I,useId:I,useHostTransitionStatus:I,useFormState:I,useActionState:I,useOptimistic:I,useMemoCache:I,useCacheRefresh:I,useEffectEvent:I},xc={readContext:Pa,use:hs,useCallback:function(e,t){return fs().memoizedState=[e,t===void 0?null:t],e},useContext:Pa,useEffect:Gs,useImperativeHandle:function(e,t,n){n=n==null?null:n.concat([e]),Us(4194308,4,Zs.bind(null,t,e),n)},useLayoutEffect:function(e,t){return Us(4194308,4,e,t)},useInsertionEffect:function(e,t){Us(4,2,e,t)},useMemo:function(e,t){var n=fs();t=t===void 0?null:t;var r=e();if($o){st(!0);try{e()}finally{st(!1)}}return n.memoizedState=[r,t],r},useReducer:function(e,t,n){var r=fs();if(n!==void 0){var i=n(t);if($o){st(!0);try{n(t)}finally{st(!1)}}}else i=t;return r.memoizedState=r.baseState=i,e={pending:null,lanes:0,dispatch:null,lastRenderedReducer:e,lastRenderedState:i},r.queue=e,e=e.dispatch=pc.bind(null,N,e),[r.memoizedState,e]},useRef:function(e){var t=fs();return e={current:e},t.memoizedState=e},useState:function(e){e=Ds(e);var t=e.queue,n=mc.bind(null,N,t);return t.dispatch=n,[e.memoizedState,n]},useDebugValue:$s,useDeferredValue:function(e,t){return nc(fs(),e,t)},useTransition:function(){var e=Ds(!1);return e=ic.bind(null,N,e.queue,!0,!1),fs().memoizedState=e,[!1,e]},useSyncExternalStore:function(e,t,n){var r=N,a=fs();if(j){if(n===void 0)throw Error(i(407));n=n()}else{if(n=t(),G===null)throw Error(i(349));q&127||Ss(r,t,n)}a.memoizedState=n;var o={value:n,getSnapshot:t};return a.queue=o,Gs(ws.bind(null,r,o,e),[e]),r.flags|=2048,Vs(9,{destroy:void 0},Cs.bind(null,r,o,n,t),null),n},useId:function(){var e=fs(),t=G.identifierPrefix;if(j){var n=sa,r=oa;n=(r&~(1<<32-ct(r)-1)).toString(32)+n,t=`_`+t+`R_`+n,n=es++,0<\/script>`,o=o.removeChild(o.firstChild);break;case`select`:o=typeof r.is==`string`?s.createElement(`select`,{is:r.is}):s.createElement(`select`),r.multiple?o.multiple=!0:r.size&&(o.size=r.size);break;default:o=typeof r.is==`string`?s.createElement(a,{is:r.is}):s.createElement(a)}}o[Mt]=t,o[Nt]=r;a:for(s=t.child;s!==null;){if(s.tag===5||s.tag===6)o.appendChild(s.stateNode);else if(s.tag!==4&&s.tag!==27&&s.child!==null){s.child.return=s,s=s.child;continue}if(s===t)break a;for(;s.sibling===null;){if(s.return===null||s.return===t)break a;s=s.return}s.sibling.return=s.return,s=s.sibling}t.stateNode=o;a:switch(np(o,a,r),a){case`button`:case`input`:case`select`:case`textarea`:r=!!r.autoFocus;break a;case`img`:r=!0;break a;default:r=!1}r&&_l(t)}}return B(t),t.subtreeFlags&=-33554433,vl(t,t.type,e===null?null:e.memoizedProps,t.pendingProps,n),null;case 6:if(e&&t.stateNode!=null)e.memoizedProps!==r&&_l(t);else{if(typeof r!=`string`&&t.stateNode===null)throw Error(i(166));if(e=Me.current,ba(t)){if(e=t.stateNode,n=t.memoizedProps,r=null,a=pa,a!==null)switch(a.tag){case 27:case 5:r=a.memoizedProps}e[Mt]=t,e=!!(e.nodeValue===n||r!==null&&!0===r.suppressHydrationWarning||ep(e.nodeValue,n)),e||_a(t,!0)}else e=lp(e).createTextNode(r),e[Mt]=t,t.stateNode=e}return B(t),null;case 31:if(n=t.memoizedState,e===null||e.memoizedState!==null){if(r=ba(t),n!==null){if(e===null){if(!r)throw Error(i(318));if(e=t.memoizedState,e=e===null?null:e.dehydrated,!e)throw Error(i(557));e[Mt]=t}else xa(),!(t.flags&128)&&(t.memoizedState=null),t.flags|=4;B(t),e=!1}else n=Sa(),e!==null&&e.memoizedState!==null&&(e.memoizedState.hydrationErrors=n),e=!0;if(!e)return t.flags&256?(Go(t),t):(Go(t),null);if(t.flags&128)throw Error(i(558))}return B(t),null;case 13:if(r=t.memoizedState,e===null||e.memoizedState!==null&&e.memoizedState.dehydrated!==null){if(a=ba(t),r!==null&&r.dehydrated!==null){if(e===null){if(!a)throw Error(i(318));if(a=t.memoizedState,a=a===null?null:a.dehydrated,!a)throw Error(i(317));a[Mt]=t}else xa(),!(t.flags&128)&&(t.memoizedState=null),t.flags|=4;B(t),a=!1}else a=Sa(),e!==null&&e.memoizedState!==null&&(e.memoizedState.hydrationErrors=a),a=!0;if(!a)return t.flags&256?(Go(t),t):(Go(t),null)}return Go(t),t.flags&128?(t.lanes=n,t):(n=r!==null,e=e!==null&&e.memoizedState!==null,n&&(r=t.child,a=null,r.alternate!==null&&r.alternate.memoizedState!==null&&r.alternate.memoizedState.cachePool!==null&&(a=r.alternate.memoizedState.cachePool.pool),o=null,r.memoizedState!==null&&r.memoizedState.cachePool!==null&&(o=r.memoizedState.cachePool.pool),o!==a&&(r.flags|=2048)),n!==e&&n&&(t.child.flags|=8192),bl(t,t.updateQueue),B(t),null);case 4:return Fe(),e===null&&Wf(t.stateNode.containerInfo),t.flags|=67108864,B(t),null;case 10:return Oa(t.type),B(t),null;case 19:if(Jo(t),r=t.memoizedState,r===null)return B(t),null;if(a=!!(t.flags&128),o=r.rendering,o===null){if(a)xl(r,!1);else{if(Y!==0||e!==null&&e.flags&128)for(e=t.child;e!==null;){if(o=Yo(e),o!==null){for(t.flags|=128,xl(r,!1),e=o.updateQueue,t.updateQueue=e,bl(t,e),t.subtreeFlags=0,e=n,n=t.child;n!==null;)Gi(n,e),n=n.sibling;return qo(t,Ko.current&1|2),j&&ca(t,r.treeForkCount),t.child}e=e.sibling}r.tail!==null&&Xe()>_d&&(t.flags|=128,a=!0,xl(r,!1),t.lanes=4194304)}}else{if(!a){if(e=Yo(o),e!==null){if(t.flags|=128,a=!0,e=e.updateQueue,t.updateQueue=e,bl(t,e),xl(r,!0),r.tail===null&&r.tailMode!==`collapsed`&&r.tailMode!==`visible`&&!o.alternate&&!j)return B(t),null}else 2*Xe()-r.renderingStartTime>_d&&n!==536870912&&(t.flags|=128,a=!0,xl(r,!1),t.lanes=4194304)}r.isBackwards?(o.sibling=t.child,t.child=o):(e=r.last,e===null?t.child=o:e.sibling=o,r.last=o)}if(r.tail!==null){e=r.tail;a:{for(n=e;n!==null;){if(n.alternate!==null){n=!1;break a}n=n.sibling}n=!0}return r.rendering=e,r.tail=e.sibling,r.renderingStartTime=Xe(),e.sibling=null,o=Ko.current,o=a?o&1|2:o&1,r.tailMode===`visible`||r.tailMode===`collapsed`||!n||j?qo(t,o):(n=o,O(zo,t),O(Ko,n),Bo===null&&(Bo=t)),j&&ca(t,r.treeForkCount),e}return B(t),null;case 22:case 23:return Go(t),Ro(),r=t.memoizedState!==null,e===null?r&&(t.flags|=8192):e.memoizedState!==null!==r&&(t.flags|=8192),r?n&536870912&&!(t.flags&128)&&(B(t),t.subtreeFlags&6&&(t.flags|=8192)):B(t),n=t.updateQueue,n!==null&&bl(t,n.retryQueue),n=null,e!==null&&e.memoizedState!==null&&e.memoizedState.cachePool!==null&&(n=e.memoizedState.cachePool.pool),r=null,t.memoizedState!==null&&t.memoizedState.cachePool!==null&&(r=t.memoizedState.cachePool.pool),r!==n&&(t.flags|=2048),e!==null&&ke($a),null;case 24:return n=null,e!==null&&(n=e.memoizedState.cache),t.memoizedState.cache!==n&&(t.flags|=2048),Oa(M),B(t),null;case 25:return null;case 30:return t.flags|=33554432,B(t),null}throw Error(i(156,t.tag))}function Cl(e,t){switch(da(t),t.tag){case 1:return e=t.flags,e&65536?(t.flags=e&-65537|128,t):null;case 3:return Oa(M),Fe(),e=t.flags,e&65536&&!(e&128)?(t.flags=e&-65537|128,t):null;case 26:case 27:case 5:return Le(t),null;case 31:if(t.memoizedState!==null){if(Go(t),t.alternate===null)throw Error(i(340));xa()}return e=t.flags,e&65536?(t.flags=e&-65537|128,t):null;case 13:if(Go(t),e=t.memoizedState,e!==null&&e.dehydrated!==null){if(t.alternate===null)throw Error(i(340));xa()}return e=t.flags,e&65536?(t.flags=e&-65537|128,t):null;case 19:return Jo(t),e=t.flags,e&65536?(t.flags=e&-65537|128,e=t.memoizedState,e!==null&&(e.rendering=null,e.tail=null),t.flags|=4,t):null;case 4:return Fe(),null;case 10:return Oa(t.type),null;case 22:case 23:return Go(t),Ro(),e!==null&&ke($a),e=t.flags,e&65536?(t.flags=e&-65537|128,t):null;case 24:return Oa(M),null;case 25:return null;default:return null}}function wl(e,t){switch(da(t),t.tag){case 3:Oa(M),Fe();break;case 26:case 27:case 5:Le(t);break;case 4:Fe();break;case 31:t.memoizedState!==null&&Go(t);break;case 13:Go(t);break;case 19:Jo(t);break;case 10:Oa(t.type);break;case 22:case 23:Go(t),Ro(),e!==null&&ke($a);break;case 24:Oa(M)}}function Tl(e,t){try{var n=t.updateQueue,r=n===null?null:n.lastEffect;if(r!==null){var i=r.next;n=i;do{if((n.tag&e)===e){r=void 0;var a=n.create,o=n.inst;r=a(),o.destroy=r}n=n.next}while(n!==i)}}catch(e){Z(t,t.return,e)}}function El(e,t,n){try{var r=t.updateQueue,i=r===null?null:r.lastEffect;if(i!==null){var a=i.next;r=a;do{if((r.tag&e)===e){var o=r.inst,s=o.destroy;if(s!==void 0){o.destroy=void 0,i=t;var c=n,l=s;try{l()}catch(e){Z(i,c,e)}}}r=r.next}while(r!==a)}}catch(e){Z(t,t.return,e)}}function Dl(e){var t=e.updateQueue;if(t!==null){var n=e.stateNode;try{No(t,n)}catch(t){Z(e,e.return,t)}}}function Ol(e,t,n){n.props=Oc(e.type,e.memoizedProps),n.state=e.memoizedState;try{n.componentWillUnmount()}catch(n){Z(e,t,n)}}function kl(e,t){try{var n=e.ref;if(n!==null){switch(e.tag){case 26:case 27:case 5:var r=e.stateNode;break;case 30:var i=e.stateNode,a=Di(e.memoizedProps,i);(i.ref===null||i.ref.name!==a)&&(i.ref=Pp(a)),r=i.ref;break;case 7:if(e.stateNode===null){var o=new Fp(e);h(e.child,!1,Qp,o,void 0,void 0),e.stateNode=o}r=e.stateNode;break;default:r=e.stateNode}typeof n==`function`?e.refCleanup=n(r):n.current=r}}catch(n){Z(e,t,n)}}function Al(e,t){var n=e.ref,r=e.refCleanup;if(n!==null){if(typeof r==`function`)try{r()}catch(n){Z(e,t,n)}finally{e.refCleanup=null,e=e.alternate,e!=null&&(e.refCleanup=null)}else if(typeof n==`function`)try{n(null)}catch(n){Z(e,t,n)}else n.current=null}}function jl(e,t){if((e.tag===5||e.tag===27||e.tag===6)&&e.alternate===null&&t!==null)for(var n=0;n title`))),np(r,t,n),r[Mt]=e,Kt(r),t=r;break a;case`link`:if(o=Gm(`link`,`href`,a).get(t+(n.href||``))){for(s=0;sg&&(o=g,g=h,h=o);var _=ti(s,h),v=ti(s,g);if(_&&v&&(p.rangeCount!==1||p.anchorNode!==_.node||p.anchorOffset!==_.offset||p.focusNode!==v.node||p.focusOffset!==v.offset)){var y=d.createRange();y.setStart(_.node,_.offset),p.removeAllRanges(),h>g?(p.addRange(y),p.extend(v.node,v.offset)):(y.setEnd(v.node,v.offset),p.addRange(y))}}}}for(d=[],p=s;p=p.parentNode;)p.nodeType===1&&d.push({element:p,left:p.scrollLeft,top:p.scrollTop});for(typeof s.focus==`function`&&s.focus(),s=0;sn?32:n,E.T=null,n=wd,wd=null;var o=bd,s=Sd;if(X=0,xd=bd=null,Sd=0,W&6)throw Error(i(331));var c=W;if(W|=4,Zu(o.current),Uu(o,o.current,s,n),W=c,Df(0,!1),ot&&typeof ot.onPostCommitFiberRoot==`function`)try{ot.onPostCommitFiberRoot(at,o)}catch{}return!0}finally{D.p=a,E.T=r,uf(e,t)}}function pf(e,t,n){t=Qi(n,t),t=Pc(e.stateNode,t,2),e=Eo(e,t,2),e!==null&&(St(e,2),Ef(e))}function Z(e,t,n){if(e.tag===3)pf(e,e,n);else for(;t!==null;){if(t.tag===3){pf(t,e,n);break}if(t.tag===1){var r=t.stateNode;if(typeof t.type.getDerivedStateFromError==`function`||typeof r.componentDidCatch==`function`&&(yd===null||!yd.has(r))){e=Qi(n,e),n=Fc(2),r=Eo(t,n,2),r!==null&&(Ic(n,r,t,e),St(r,2),Ef(r));break}}t=t.return}}function mf(e,t,n){var r=e.pingCache;if(r===null){r=e.pingCache=new td;var i=new Set;r.set(t,i)}else i=r.get(t),i===void 0&&(i=new Set,r.set(t,i));i.has(n)||(ad=!0,i.add(n),e=hf.bind(null,e,t,n),t.then(e,e))}function hf(e,t,n){var r=e.pingCache;r!==null&&r.delete(t),e.pingedLanes|=e.suspendedLanes&n,e.warmLanes&=~n,G===e&&(q&n)===n&&(Y===4||Y===3&&(q&62914560)===q&&300>Xe()-hd?W&2?ld|=n:Vd(e,0):ld|=n,dd===q&&(dd=0)),Ef(e)}function gf(e,t){t===0&&(t=bt()),e=Li(e,t),e!==null&&(St(e,t),Ef(e))}function _f(e){var t=e.memoizedState,n=0;t!==null&&(n=t.retryLane),gf(e,n)}function vf(e,t){var n=0;switch(e.tag){case 31:case 13:var r=e.stateNode,a=e.memoizedState;a!==null&&(n=a.retryLane);break;case 19:r=e.stateNode;break;case 22:r=e.stateNode._retryCache;break;default:throw Error(i(314))}r!==null&&r.delete(t),gf(e,n)}function yf(e,t){return Ke(e,t)}var bf=null,xf=null,Sf=!1,Cf=!1,wf=!1,Tf=0;function Ef(e){e!==xf&&e.next===null&&(xf===null?bf=xf=e:xf=xf.next=e),Cf=!0,Sf||(Sf=!0,Nf())}function Df(e,t){if(!wf&&Cf){wf=!0;do for(var n=!1,r=bf;r!==null;){if(!t){if(e!==0){var i=r.pendingLanes;if(i===0)var a=0;else{var o=r.suspendedLanes,s=r.pingedLanes;a=(1<<31-ct(42|e)+1)-1,a&=i&~(o&~s),a=a&201326741?a&201326741|1:a?a|2:0}a!==0&&(n=!0,Mf(r,a))}else a=q,a=gt(r,r===G?a:0,r.cancelPendingCommit!==null||r.timeoutHandle!==-1),!(a&3)||_t(r,a)||(n=!0,Mf(r,a))}r=r.next}while(n);wf=!1}}function Of(){kf()}function kf(){Cf=Sf=!1;var e=0;Tf!==0&&hp()&&(e=Tf);for(var t=Xe(),n=null,r=bf;r!==null;){var i=r.next,a=Af(r,t);a===0?(r.next=null,n===null?bf=i:n.next=i,i===null&&(xf=n)):(n=r,(e!==0||a&3)&&(Cf=!0)),r=i}X!==0&&X!==5||Df(e,!1),Tf!==0&&(Tf=0)}function Af(e,t){for(var n=e.suspendedLanes,r=e.pingedLanes,i=e.expirationTimes,a=e.pendingLanes&-62914561;0s)break;var u=c.transferSize,d=c.initiatorType;u&&ap(d)&&(c=c.responseEnd,o+=u*(c$m){s.length=o;break}f=new Promise(jp.bind(f)),s.push(f)}}}if(0`u`?null:document;function Tm(e,t,n){var r=wm;if(r&&typeof t==`string`&&t){var i=pn(t);i=`link[rel="`+e+`"][href="`+i+`"]`,typeof n==`string`&&(i+=`[crossorigin="`+n+`"]`),ym.has(i)||(ym.add(i),e={rel:e,crossOrigin:n,href:t},r.querySelector(i)===null&&(t=r.createElement(`link`),np(t,`link`,e),Kt(t),r.head.appendChild(t)))}}function Em(e){xm.D(e),Tm(`dns-prefetch`,e,null)}function Dm(e,t){xm.C(e,t),Tm(`preconnect`,e,t)}function Om(e,t,n){xm.L(e,t,n);var r=wm;if(r&&e&&t){var i=`link[rel="preload"][as="`+pn(t)+`"]`;t===`image`&&n&&n.imageSrcSet?(i+=`[imagesrcset="`+pn(n.imageSrcSet)+`"]`,typeof n.imageSizes==`string`&&(i+=`[imagesizes="`+pn(n.imageSizes)+`"]`)):i+=`[href="`+pn(e)+`"]`;var a=i;switch(t){case`style`:a=Pm(e);break;case`script`:a=Rm(e)}if(!(vm.has(a)||(e=C({rel:`preload`,href:t===`image`&&n&&n.imageSrcSet?void 0:e,as:t},n),vm.set(a,e),r.querySelector(i)!==null||t===`style`&&r.querySelector(Fm(a))||t===`script`&&r.querySelector(zm(a))))){var o=r.createElement(`link`);np(o,`link`,e),t===`style`&&(o[Bt]=!0,o.onload=o.onerror=function(){qt(o)}),Kt(o),r.head.appendChild(o)}}}function km(e,t){xm.m(e,t);var n=wm;if(n&&e){var r=t&&typeof t.as==`string`?t.as:`script`,i=`link[rel="modulepreload"][as="`+pn(r)+`"][href="`+pn(e)+`"]`,a=i;switch(r){case`audioworklet`:case`paintworklet`:case`serviceworker`:case`sharedworker`:case`worker`:case`script`:a=Rm(e)}if(!vm.has(a)&&(e=C({rel:`modulepreload`,href:e},t),vm.set(a,e),n.querySelector(i)===null)){switch(r){case`audioworklet`:case`paintworklet`:case`serviceworker`:case`sharedworker`:case`worker`:case`script`:if(n.querySelector(zm(a)))return}r=n.createElement(`link`),np(r,`link`,e),Kt(r),n.head.appendChild(r)}}}function Am(e,t,n){xm.S(e,t,n);var r=wm;if(r&&e){var i=Gt(r).hoistableStyles,a=Pm(e);t||=`default`;var o=i.get(a);if(!o){var s={loading:0,preload:null};if(o=r.querySelector(Fm(a)))s.loading=5;else{e=C({rel:`stylesheet`,href:e,"data-precedence":t},n),(n=vm.get(a))&&Hm(e,n);var c=o=r.createElement(`link`);Kt(c),np(c,`link`,e),c._p=new Promise(function(e,t){c.onload=e,c.onerror=t}),c.addEventListener(`load`,function(){s.loading|=1}),c.addEventListener(`error`,function(){s.loading|=2}),s.loading|=4,Vm(o,t,r)}o={type:`stylesheet`,instance:o,count:1,state:s},i.set(a,o)}}}function jm(e,t){xm.X(e,t);var n=wm;if(n&&e){var r=Gt(n).hoistableScripts,i=Rm(e),a=r.get(i);a||(a=n.querySelector(zm(i)),a||(e=C({src:e,async:!0},t),(t=vm.get(i))&&Um(e,t),a=n.createElement(`script`),Kt(a),np(a,`link`,e),n.head.appendChild(a)),a={type:`script`,instance:a,count:1,state:null},r.set(i,a))}}function Mm(e,t){xm.M(e,t);var n=wm;if(n&&e){var r=Gt(n).hoistableScripts,i=Rm(e),a=r.get(i);a||(a=n.querySelector(zm(i)),a||(e=C({src:e,async:!0,type:`module`},t),(t=vm.get(i))&&Um(e,t),a=n.createElement(`script`),Kt(a),np(a,`link`,e),n.head.appendChild(a)),a={type:`script`,instance:a,count:1,state:null},r.set(i,a))}}function Nm(e,t,n,r){var a=(a=Me.current)?bm(a):null;if(!a)throw Error(i(446));switch(e){case`meta`:case`title`:return null;case`style`:return typeof n.precedence==`string`&&typeof n.href==`string`?(n=Pm(n.href),t=Gt(a).hoistableStyles,r=t.get(n),r||(r={type:`style`,instance:null,count:0,state:null},t.set(n,r)),r):{type:`void`,instance:null,count:0,state:null};case`link`:if(n.rel===`stylesheet`&&typeof n.href==`string`&&typeof n.precedence==`string`){e=Pm(n.href);var o=Gt(a).hoistableStyles,s=o.get(e);if(s||(a=a.ownerDocument||a,s={type:`stylesheet`,instance:null,count:0,state:{loading:0,preload:null}},o.set(e,s),(o=a.querySelector(Fm(e)))?o._p||(s.instance=o,s.state.loading=5):(o=vm.get(e),o||(o={rel:`preload`,as:`style`,href:n.href,crossOrigin:n.crossOrigin,integrity:n.integrity,media:n.media,hrefLang:n.hrefLang,referrerPolicy:n.referrerPolicy},vm.set(e,o)),Lm(a,e,o,s.state))),t&&r===null)throw Error(i(528,``));return s}if(t&&r!==null)throw Error(i(529,``));return null;case`script`:return t=n.async,n=n.src,typeof n==`string`&&t&&typeof t!=`function`&&typeof t!=`symbol`?(n=Rm(n),t=Gt(a).hoistableScripts,r=t.get(n),r||(r={type:`script`,instance:null,count:0,state:null},t.set(n,r)),r):{type:`void`,instance:null,count:0,state:null};default:throw Error(i(444,e))}}function Pm(e){return`href="`+pn(e)+`"`}function Fm(e){return`link[rel="stylesheet"][`+e+`]`}function Im(e){return C({},e,{"data-precedence":e.precedence,precedence:null})}function Lm(e,t,n,r){if(t=e.querySelector(`link[rel="preload"][as="style"][`+t+`]`)){if(!0!==t[Bt]){r.loading=1;return}}else t=e.createElement(`link`),t[Bt]=!0,t.onload=t.onerror=qt.bind(null,t),np(t,`link`,n),Kt(t),e.head.appendChild(t);r.preload=t,t.addEventListener(`load`,function(){return r.loading|=1}),t.addEventListener(`error`,function(){return r.loading|=2})}function Rm(e){return`[src="`+pn(e)+`"]`}function zm(e){return`script[async]`+e}function Bm(e,t,n){if(t.count++,t.instance===null)switch(t.type){case`style`:var r=e.querySelector(`style[data-href~="`+pn(n.href)+`"]`);if(r)return t.instance=r,Kt(r),r;var a=C({},n,{"data-href":n.href,"data-precedence":n.precedence,href:null,precedence:null});return r=(e.ownerDocument||e).createElement(`style`),Kt(r),np(r,`style`,a),Vm(r,n.precedence,e),t.instance=r;case`stylesheet`:a=Pm(n.href);var o=e.querySelector(Fm(a));if(o)return t.state.loading|=4,t.instance=o,Kt(o),o;r=Im(n),(a=vm.get(a))&&Hm(r,a),o=(e.ownerDocument||e).createElement(`link`),Kt(o);var s=o;return s._p=new Promise(function(e,t){s.onload=e,s.onerror=t}),np(o,`link`,r),t.state.loading|=4,Vm(o,n.precedence,e),t.instance=o;case`script`:return o=Rm(n.src),(a=e.querySelector(zm(o)))?(t.instance=a,Kt(a),a):(r=n,(a=vm.get(o))&&(r=C({},n),Um(r,a)),e=e.ownerDocument||e,a=e.createElement(`script`),Kt(a),np(a,`link`,r),e.head.appendChild(a),t.instance=a);case`void`:return null;default:throw Error(i(443,t.type))}else t.type===`stylesheet`&&!(t.state.loading&4)&&(r=t.instance,t.state.loading|=4,Vm(r,n.precedence,e));return t.instance}function Vm(e,t,n){for(var r=n.querySelectorAll(`link[rel="stylesheet"][data-precedence],style[data-precedence]`),i=r.length?r[r.length-1]:null,a=i,o=0;o title`):null)}function qm(e,t,n){if(n===1||t.itemProp!=null)return!1;switch(e){case`meta`:case`title`:return!0;case`style`:if(typeof t.precedence!=`string`||typeof t.href!=`string`||t.href===``)break;return!0;case`link`:if(typeof t.rel!=`string`||typeof t.href!=`string`||t.href===``||t.onLoad||t.onError)break;switch(t.rel){case`stylesheet`:return e=t.disabled,typeof t.precedence==`string`&&e==null;default:return!0}case`script`:if(t.async&&typeof t.async!=`function`&&typeof t.async!=`symbol`&&!t.onLoad&&!t.onError&&t.src&&typeof t.src==`string`)return!0}return!1}function Jm(e,t){return e===`img`&&t.src!=null&&t.src!==``&&t.onLoad==null&&t.loading!==`lazy`}function Ym(e){return!(e.type===`stylesheet`&&!(e.state.loading&3))}function Xm(e){return(e.width||100)*(e.height||100)*(typeof devicePixelRatio==`number`?devicePixelRatio:1)*.25}function Zm(e,t){typeof t.decode==`function`&&(e.imgCount++,t.complete||(e.imgBytes+=Xm(t),e.suspenseyImages.push(t)),e=rh.bind(e),t.decode().then(e,e))}function Qm(e,t,n,r){if(n.type===`stylesheet`&&(typeof r.media!=`string`||!1!==matchMedia(r.media).matches)&&!(n.state.loading&4)){if(n.instance===null){var i=Pm(r.href),a=t.querySelector(Fm(i));if(a){t=a._p,typeof t==`object`&&t&&typeof t.then==`function`&&(e.count++,e=nh.bind(e),t.then(e,e)),n.state.loading|=4,n.instance=a,Kt(a);return}a=t.ownerDocument||t,r=Im(r),(i=vm.get(i))&&Hm(r,i),a=a.createElement(`link`),Kt(a);var o=a;o._p=new Promise(function(e,t){o.onload=e,o.onerror=t}),np(a,`link`,r),n.instance=a}e.stylesheets===null&&(e.stylesheets=new Map),e.stylesheets.set(n,t),(t=n.state.preload)&&!(n.state.loading&3)&&(e.count++,n=nh.bind(e),t.addEventListener(`load`,n),t.addEventListener(`error`,n))}}var $m=0;function eh(e,t){return e.stylesheets&&e.count===0&&ah(e,e.stylesheets),0$m?50:800)+t);return e.unsuspend=n,function(){e.unsuspend=null,clearTimeout(r),clearTimeout(i)}}:null}function th(e){if(e.count===0&&(e.imgCount===0||!e.waitingForImages)){if(e.stylesheets)ah(e,e.stylesheets);else if(e.unsuspend){var t=e.unsuspend;e.unsuspend=null,t()}}}function nh(){this.count--,th(this)}function rh(){this.imgCount--,th(this)}var ih=null;function ah(e,t){e.stylesheets=null,e.unsuspend!==null&&(e.count++,ih=new Map,t.forEach(oh,e),ih=null,nh.call(e))}function oh(e,t){if(!(t.state.loading&4)){var n=ih.get(e);if(n)var r=n.get(null);else{n=new Map,ih.set(e,n);for(var i=e.querySelectorAll(`link[data-precedence],style[data-precedence]`),a=0;a{function n(){if(!(typeof __REACT_DEVTOOLS_GLOBAL_HOOK__>`u`||typeof __REACT_DEVTOOLS_GLOBAL_HOOK__.checkDCE!=`function`))try{__REACT_DEVTOOLS_GLOBAL_HOOK__.checkDCE(n)}catch(e){console.error(e)}}n(),t.exports=h()})),_=c(u(),1),v=g(),y={width:1200,height:900,pad:{left:76,right:46,top:55,bottom:82}},b=[[0,-1],[0,1],[-1,0],[1,0],[-1,-1],[1,-1],[-1,1],[1,1]],ee=[22,34,48,64,82,104,130,160,196],x=(e,t,n,r)=>({cx:e,cy:t,width:n,height:r}),te=(e,t)=>Math.abs(e.cx-t.cx)*2e.cx-e.width/2>=t.left&&e.cx+e.width/2<=t.right&&e.cy-e.height/2>=t.top&&e.cy+e.height/2<=t.bottom;function S(e){let t=[...e.countries,...e.models],n=Math.min(...t.map(e=>e.x)),r=Math.max(...t.map(e=>e.x)),i=Math.min(...t.map(e=>e.y)),a=Math.max(...t.map(e=>e.y)),o=(r-n)*.17,s=(a-i)*.17,c={x0:n-o,x1:r+o,y0:i-s,y1:a+s*1.22},l={left:y.pad.left,right:y.width-y.pad.right,top:y.pad.top,bottom:y.height-y.pad.bottom};return{x:e=>l.left+(e-c.x0)/(c.x1-c.x0)*(l.right-l.left),y:e=>l.bottom-(e-c.y0)/(c.y1-c.y0)*(l.bottom-l.top),bounds:l,limits:c}}function re(e,t){let n=t===`zone`?15:t===`model`?13:11;return{width:e.length*n*.59+10,height:n+7}}function C(e,t){let{x:n,y:r,bounds:i}=t,a=[...e.countries.map(e=>x(n(e.x),r(e.y),10,10)),...e.models.map(e=>x(n(e.x),r(e.y),22,22))],o=[...e.models.filter(e=>e.label).map(e=>({id:`model:${e.name}`,point:e,text:e.label,kind:`model`})),...e.countries.filter(e=>e.label).map(e=>({id:`country:${e.name}`,point:e,text:e.name,kind:`country`})),...e.zone_hulls.map(e=>({id:`zone:${e.name}`,point:{x:e.label_anchor[0],y:e.label_anchor[1]},text:e.name,kind:`zone`}))],s={};for(let e of o){let t={x:n(e.point.x),y:r(e.point.y)},o=re(e.text,e.kind),c=null;for(let e of ee){for(let[n,r]of b){let s=x(t.x+n*(e+o.width/3),t.y+r*e,o.width,o.height);if(ne(s,i)&&!a.some(e=>te(s,e))){c=s;break}}if(c)break}if(!c)throw Error(`no collision-free label location for ${e.id}`);s[e.id]={...c,anchor:t,kind:e.kind,text:e.text},a.push(c)}return s}function ie(e,t){let n=e.slice(0,-1).map(([e,n])=>({x:t.x(e),y:t.y(n)}));if(n.length<3)throw Error(`a closed hull needs three points`);let r=e=>n[(e+n.length)%n.length],i=(e,t)=>Math.hypot(e.x-t.x,e.y-t.y),a=(e,t,n)=>({x:e.x+(t.x-e.x)*n,y:e.y+(t.y-e.y)*n}),o=e=>{let t=r(e-1),n=r(e),o=r(e+1),s=Math.min(.24,14/i(t,n),14/i(n,o));return{before:a(n,t,s),current:n,after:a(n,o,s)}},s=o(0),c=`M ${s.after.x} ${s.after.y}`;for(let e=1;e<=n.length;e+=1){let t=o(e%n.length);c+=` L ${t.before.x} ${t.before.y} Q ${t.current.x} ${t.current.y} ${t.after.x} ${t.after.y}`}return`${c} Z`}function w(e){let t=S(e),n=C(e,t),r=Object.entries(n);for(let[e,n]of r)if(!ne(n,t.bounds))throw Error(`label out of bounds: ${e}`);for(let e=0;e{var t=Symbol.for(`react.transitional.element`),n=Symbol.for(`react.fragment`);function r(e,n,r){var i=null;if(r!==void 0&&(i=``+r),n.key!==void 0&&(i=``+n.key),`key`in n)for(var a in r={},n)a!==`key`&&(r[a]=n[a]);else r=n;return n=r.ref,{$$typeof:t,type:e,key:i,ref:n===void 0?null:n,props:r}}e.Fragment=n,e.jsx=r,e.jsxs=r})),T=o(((e,t)=>{t.exports=ae()}))(),oe=`wvs/`;function se(e,t){return Object.keys(e).filter(e=>!t.has(e))}function ce({active:e,geometry:t,id:n=`model-tooltip`,panel:r}){if(!e)return null;let i=e.tooltipLeft??`${Math.min(86,t.x(e.x)/y.width*100)}%`,a=e.tooltipTop??`${Math.min(82,t.y(e.y)/y.height*100)}%`,o=e.provenance.release_created&&(0,T.jsxs)(`span`,{children:[`release `,e.provenance.release_created]});return(0,T.jsxs)(`aside`,{id:n,className:`tooltip`,style:{left:i,top:a},role:`status`,children:[(0,T.jsx)(`strong`,{children:e.name}),e.tooltipScore!=null&&(0,T.jsxs)(`span`,{children:[`HLE score: `,e.tooltipScore.toFixed(3)]}),r===`secular`&&(0,T.jsxs)(`span`,{children:[`Secular-Rational: `,e.y.toFixed(3)]}),r===`self-expression`&&(0,T.jsxs)(`span`,{children:[`Self-expression: `,e.tooltipValue.toFixed(3)]}),!r&&(0,T.jsxs)(T.Fragment,{children:[(0,T.jsxs)(`span`,{children:[`Self-expression/Survival: `,e.x.toFixed(3)]}),(0,T.jsxs)(`span`,{children:[`Traditional/Secular-Rational: `,e.y.toFixed(3)]})]}),e.tooltipScore==null&&o]})}function le({model:e,placement:t,geometry:n,setActive:r,clearActive:i,markerRef:a,logo:o}){let s=n.x(e.x),c=n.y(e.y),l=e.label?t[`model:${e.name}`]:null,u=l&&Math.hypot(l.cx-s,l.cy-c)>20;return(0,T.jsxs)(`g`,{ref:a,className:`model-mark`,"data-family":e.family,"data-model":e.name,"data-x":e.x,"data-y":e.y,tabIndex:`0`,role:`button`,"aria-label":`${e.name}, ${e.family}`,"aria-describedby":`model-tooltip`,onPointerEnter:()=>r(e),onPointerLeave:i,onFocus:()=>r(e),onBlur:i,children:[u&&(0,T.jsx)(`line`,{className:`leader`,x1:s,y1:c,x2:l.cx,y2:l.cy}),(0,T.jsx)(`circle`,{className:`model-ring`,cx:s,cy:c,r:`8`,stroke:e.color}),(0,T.jsx)(`image`,{href:`${oe}${o}`,x:s-5,y:c-5,width:`10`,height:`10`,preserveAspectRatio:`xMidYMid meet`,"aria-hidden":`true`,focusable:`false`}),l&&(0,T.jsx)(`text`,{className:`model-label`,x:l.cx,y:l.cy+4,textAnchor:`middle`,children:e.label})]})}function ue(e,t,n){let r=e.map(t),i=e.map(n);if(new Set(r).size<2)return null;let a=r.reduce((e,t)=>e+t,0)/r.length,o=i.reduce((e,t)=>e+t,0)/i.length,s=r.reduce((e,t,n)=>e+(t-a)*(i[n]-o),0)/r.reduce((e,t)=>e+(t-a)**2,0),c=o-s*a,l=i.reduce((e,t,n)=>e+(t-(c+s*r[n]))**2,0),u=i.reduce((e,t)=>e+(t-o)**2,0);return{slope:s,intercept:c,n:e.length,r2:u===0?null:1-l/u}}function de({data:e,hidden:t,field:n,title:r,axisMode:i}){let a=(0,_.useMemo)(()=>e.models.filter(e=>Number.isFinite(Date.parse(e.provenance.release_created??``))).toSorted((e,t)=>e.provenance.release_created.localeCompare(t.provenance.release_created)||e.name.localeCompare(t.name)),[e]),o=(0,_.useMemo)(()=>e.models.filter(e=>Number.isFinite(e.provenance.hle_score)).toSorted((e,t)=>e.provenance.hle_score-t.provenance.hle_score||e.name.localeCompare(t.name)),[e]),s=i===`release-date`?a:o,c=s.filter(e=>!t.has(e.family)),l=e=>n===`x`?-e.x:e.y,u=e=>i===`release-date`?Date.parse(e.provenance.release_created):e.provenance.hle_score,d=ue(c,u,l),[f,p]=(0,_.useState)(null),m=1200,h=s.map(u),g=s.map(l),v=Math.min(...h),y=Math.max(...h),S=Math.min(...g),re=Math.max(...g),C=e=>96+(e-v)/(y-v||1)*1069,ie=e=>42+(re-e)/(re-S||1)*230,w=`release-${n}`,ae=`${w}-tooltip`,le=n===`y`?e.axis.y:[...e.axis.x].reverse(),de=c.map(u),fe=d&&[Math.min(...de),Math.max(...de)].map(e=>[C(e),ie(d.intercept+d.slope*e)]),pe=(0,_.useMemo)(()=>{if(i!==`release-date`)return[];let e=-1/0;return c.filter(e=>Number.isFinite(e.provenance.hle_score)).filter(t=>t.provenance.hle_score<=e?!1:(e=t.provenance.hle_score,!0))},[i,c]),me=(0,_.useMemo)(()=>{let e={left:96,right:1165,top:42,bottom:272},t=s.map(e=>x(C(u(e)),ie(l(e)),16,16)),n={};for(let r of pe){let i={x:C(u(r)),y:ie(l(r))},a={width:r.name.length*8+12,height:18},o=null;for(let n of ee){for(let[r,s]of b){let c=x(i.x+r*(n+a.width/3),i.y+s*n,a.width,a.height);if(ne(c,e)&&!t.some(e=>te(c,e))){o=c;break}}if(o)break}if(!o)for(let n=e.top+a.height/2;n<=e.bottom-a.height/2&&!o;n+=a.height+4)for(let r=e.left+a.width/2;r<=e.right-a.width/2;r+=12){let e=x(r,n,a.width,a.height);if(!t.some(t=>te(e,t))){o=e;break}}o||=x(i.x,Math.max(e.top+a.height/2,i.y-a.height),a.width,a.height),n[r.name]={...o,anchor:i},t.push(o)}return n},[pe,s,v,y,S,re]),he=(e,t)=>{let n=t.currentTarget.closest(`.scatter-shell`).getBoundingClientRect(),r=t.currentTarget.getBoundingClientRect();p({...e,tooltipValue:l(e),tooltipScore:i===`capability`?e.provenance.hle_score:null,tooltipLeft:`${Math.min(82,(r.left-n.left)/n.width*100)}%`,tooltipTop:`${Math.min(78,(r.top-n.top)/n.height*100)}%`})};return(0,T.jsxs)(`section`,{className:`release-panel`,"data-coordinate":n,"aria-labelledby":`${w}-heading`,children:[(0,T.jsx)(`h2`,{id:`${w}-heading`,children:r}),(0,T.jsxs)(`div`,{className:`scatter-shell`,children:[(0,T.jsxs)(`svg`,{id:`${w}-svg`,viewBox:`0 0 ${m} 320`,role:`img`,"aria-labelledby":`${w}-svg-title ${w}-svg-desc`,"data-axis-mode":i,"data-panel-model-count":c.length,"data-omitted-model-count":e.models.length-s.length,"data-fit-n":d?.n??0,"data-fit-r2":d?.r2??``,"data-fit-slope":d?.slope??``,children:[(0,T.jsx)(`title`,{id:`${w}-svg-title`,children:r}),(0,T.jsxs)(`desc`,{id:`${w}-svg-desc`,children:[`Scatter plot with `,i===`release-date`?`release date`:`HLE score`,` on the horizontal axis and `,le.join(` to `),` increasing upward on the vertical axis. `,c.length,` of `,s.length,` matched models are visible from `,se(Object.groupBy(e.models,e=>e.family),t).join(`, `)||`no families`,`; `,e.models.length-s.length,` plotted models lack this x value and are omitted only here. Each white-ring logo mark is a model. `,d?`The thin line is an ordinary least squares descriptive fit to the ${d.n} currently visible matched models${d.r2===null?`; R squared is unavailable because the y values are constant`:`; R squared is ${d.r2.toFixed(2)}`}.`:`The fit is hidden because fewer than two distinct x values are visible.`,` Hover or keyboard focus a mark for model-specific details.`]}),(0,T.jsxs)(`defs`,{children:[(0,T.jsx)(`marker`,{id:`${w}-arrow`,markerWidth:`8`,markerHeight:`8`,refX:`6`,refY:`3`,orient:`auto`,children:(0,T.jsx)(`path`,{d:`M0,0 L0,6 L6,3 z`,className:`scatter-arrow`})}),(0,T.jsx)(`clipPath`,{id:`${w}-fit-clip`,children:(0,T.jsx)(`rect`,{x:96,y:42,width:1069,height:230})})]}),(0,T.jsx)(`rect`,{className:`canvas`,width:m,height:320}),(0,T.jsx)(`g`,{className:`scatter-grid`,children:Array.from({length:5},(e,t)=>(0,T.jsx)(`line`,{x1:96,x2:1165,y1:42+t*230/4,y2:42+t*230/4},t))}),(0,T.jsx)(`line`,{className:`scatter-axis`,x1:96,x2:1165,y1:272,y2:272}),(0,T.jsx)(`line`,{className:`scatter-axis`,x1:96,x2:96,y1:272,y2:42,markerEnd:`url(#${w}-arrow)`}),(0,T.jsxs)(`text`,{className:`scatter-y-label`,x:`17`,y:157,textAnchor:`middle`,transform:`rotate(-90 17 157)`,children:[le.join(` -> `),` `,`↑`]}),(0,T.jsx)(`text`,{className:`scatter-tick`,x:96,y:302,children:i===`release-date`?new Date(v).toISOString().slice(0,10):v.toFixed(1)}),(0,T.jsx)(`text`,{className:`scatter-tick`,x:1165,y:302,textAnchor:`end`,children:i===`release-date`?new Date(y).toISOString().slice(0,10):y.toFixed(1)}),(0,T.jsx)(`text`,{className:`scatter-tick`,x:88,y:46,textAnchor:`end`,children:re.toFixed(2)}),(0,T.jsx)(`text`,{className:`scatter-tick`,x:88,y:272,textAnchor:`end`,children:S.toFixed(2)}),fe&&(0,T.jsxs)(`g`,{className:`release-fit`,"data-fit-n":d.n,"data-fit-r2":d.r2??``,children:[(0,T.jsx)(`line`,{clipPath:`url(#${w}-fit-clip)`,x1:fe[0][0],y1:fe[0][1],x2:fe[1][0],y2:fe[1][1]}),` `,(0,T.jsxs)(`text`,{x:102,y:55,children:[`OLS, n=`,d.n,`, R² `,d.r2===null?`unavailable`:d.r2.toFixed(2)]})]}),!d&&(0,T.jsx)(`text`,{className:`release-fit-unavailable`,x:102,y:55,children:`Fit unavailable: fewer than two release dates`}),s.map(n=>(0,T.jsxs)(`g`,{className:`release-mark`,"data-family":n.family,"data-release-model":n.name,"data-release-date":n.provenance.release_created,"data-hle-score":n.provenance.hle_score,"data-coordinate-value":l(n),display:t.has(n.family)?`none`:`inline`,tabIndex:`0`,role:`button`,"aria-label":`${n.name}, ${i===`release-date`?n.provenance.release_created:`HLE score ${n.provenance.hle_score}`}`,"aria-describedby":ae,onPointerEnter:e=>he(n,e),onPointerLeave:()=>p(null),onFocus:e=>he(n,e),onBlur:()=>p(null),children:[(0,T.jsx)(`circle`,{className:`model-ring`,cx:C(u(n)),cy:ie(l(n)),r:`8`,stroke:n.color}),(0,T.jsx)(`image`,{href:`${oe}${e.logos[n.family]}`,x:C(u(n))-5,y:ie(l(n))-5,width:`10`,height:`10`,preserveAspectRatio:`xMidYMid meet`,"aria-hidden":`true`,focusable:`false`})]},n.name)),i===`release-date`&&pe.map(e=>(0,T.jsx)(`g`,{className:`frontier-label`,"data-frontier-model":e.name,children:(0,T.jsx)(`text`,{x:me[e.name].cx,y:me[e.name].cy+4,textAnchor:`middle`,children:e.name})},`frontier-${e.name}`))]}),(0,T.jsx)(ce,{active:f,geometry:null,id:ae,panel:n===`y`?`secular`:`self-expression`})]})]})}function fe({data:e,hidden:t,axisMode:n,setAxisMode:r}){let i=n===`release-date`?`Release date`:e.capability_x.label;return(0,T.jsxs)(`section`,{className:`release-panels`,"aria-label":`Release-date and capability scatter panels`,children:[(0,T.jsxs)(`div`,{className:`release-axis-selector`,children:[(0,T.jsxs)(`label`,{children:[`Release-panel x axis `,(0,T.jsxs)(`select`,{"aria-label":`Release-panel x axis`,"aria-controls":`release-y-svg release-x-svg`,value:n,onChange:e=>r(e.target.value),children:[(0,T.jsx)(`option`,{value:`release-date`,children:`Release date`}),(0,T.jsx)(`option`,{value:`capability`,children:e.capability_x.label})]})]}),(0,T.jsxs)(`span`,{children:[(0,T.jsx)(`a`,{href:e.capability_x.source_url,children:`Artificial Analysis HLE score`}),`, saved `,e.capability_x.fetched_utc.slice(0,10),`. `,n===`capability`?`${e.capability_x.matched_models} matched, ${e.models.length-e.capability_x.matched_models} omitted.`:`Release-date labels mark running HLE score highs among shown mapped models.`]})]}),(0,T.jsx)(de,{data:e,hidden:t,field:`y`,axisMode:n,title:`${i} vs Secular-Rational`}),(0,T.jsx)(de,{data:e,hidden:t,field:`x`,axisMode:n,title:`${i} vs Self-expression`})]})}function pe({data:e}){let t=new URLSearchParams(location.search),[n,r]=(0,_.useState)(()=>new Set(t.get(`hide`)?.split(`,`).filter(Boolean))),[i,a]=(0,_.useState)(()=>t.get(`axis`)===`capability`?`capability`:`release-date`),[o,s]=(0,_.useState)(()=>e.models.find(e=>e.name===(t.get(`tooltip`)||t.get(`focus`)))??null),c=t.get(`focus`),l=(0,_.useRef)(null),u=(0,_.useMemo)(()=>Object.groupBy(e.models,e=>e.family),[e]),{labels:d,geometry:f}=(0,_.useMemo)(()=>w(e),[e]),p=se(u,n),m=e.models.filter(e=>!n.has(e.family)).length;(0,_.useEffect)(()=>{c&&l.current?.focus()},[c]);let h=e=>{e.currentTarget.matches(`:focus`)||s(null)},g=e=>r(t=>{let n=new Set(t);return n.has(e)?n.delete(e):n.add(e),n}),v=f.x(e.median.x),b=f.y(e.median.y);return(0,T.jsxs)(T.Fragment,{children:[(0,T.jsx)(`section`,{className:`controls`,"aria-label":`Model-family visibility`,children:Object.entries(u).map(([t])=>{let r=!n.has(t);return(0,T.jsxs)(`button`,{className:`chip`,type:`button`,"aria-pressed":r,onClick:()=>g(t),children:[(0,T.jsx)(`img`,{src:`${oe}${e.logos[t]}`,alt:``,"aria-hidden":`true`}),t]},t)})}),(0,T.jsxs)(`div`,{className:`chart-shell`,children:[(0,T.jsxs)(`svg`,{viewBox:`0 0 ${y.width} ${y.height}`,role:`img`,"aria-labelledby":`map-svg-title map-svg-desc`,"data-median-x":e.median.x,"data-median-y":e.median.y,"data-visible-model-count":m,children:[(0,T.jsx)(`title`,{id:`map-svg-title`,children:`Frontier LLMs on the World Values Survey`}),(0,T.jsxs)(`desc`,{id:`map-svg-desc`,children:[`World Values Survey cultural map. Horizontal direction runs from Self-expression on the left to Survival on the right. Vertical direction runs from Traditional below to Secular-Rational above. Coloured dots are selected WVS countries, outlines are cultural regions, and white-ring logo marks are models. `,m,` model marks are visible from `,p.join(`, `)||`no families`,`. Use the family controls to hide marks and labels. Hover or keyboard focus a model for model-specific details.`]}),(0,T.jsx)(`defs`,{children:(0,T.jsx)(`marker`,{id:`arrow`,markerWidth:`8`,markerHeight:`8`,refX:`6`,refY:`3`,orient:`auto`,children:(0,T.jsx)(`path`,{d:`M0,0 L0,6 L6,3 z`,className:`arrow`})})}),(0,T.jsx)(`rect`,{className:`canvas`,width:y.width,height:y.height}),(0,T.jsxs)(`g`,{className:`grid`,children:[Array.from({length:8},(e,t)=>(0,T.jsx)(`line`,{x1:f.bounds.left+t*(f.bounds.right-f.bounds.left)/7,y1:f.bounds.top,x2:f.bounds.left+t*(f.bounds.right-f.bounds.left)/7,y2:f.bounds.bottom},`v${t}`)),Array.from({length:6},(e,t)=>(0,T.jsx)(`line`,{x1:f.bounds.left,y1:f.bounds.top+t*(f.bounds.bottom-f.bounds.top)/5,x2:f.bounds.right,y2:f.bounds.top+t*(f.bounds.bottom-f.bounds.top)/5},`h${t}`))]}),(0,T.jsx)(`line`,{className:`median`,x1:f.bounds.left,y1:b,x2:f.bounds.right,y2:b}),(0,T.jsx)(`line`,{className:`median`,x1:v,y1:f.bounds.top,x2:v,y2:f.bounds.bottom}),e.zone_hulls.map(e=>(0,T.jsx)(`path`,{className:`zone`,d:ie(e.points,f),stroke:e.color},e.name)),e.countries.map(e=>(0,T.jsxs)(`g`,{children:[(0,T.jsx)(`circle`,{className:`country`,"data-country":e.name,"data-x":e.x,"data-y":e.y,cx:f.x(e.x),cy:f.y(e.y),r:`3.5`,fill:e.color}),e.label&&(0,T.jsx)(`text`,{className:`country-label`,x:d[`country:${e.name}`].cx,y:d[`country:${e.name}`].cy+4,textAnchor:`middle`,children:e.name})]},e.name)),e.zone_hulls.map(e=>(0,T.jsx)(`text`,{className:`zone-label`,x:d[`zone:${e.name}`].cx,y:d[`zone:${e.name}`].cy+5,textAnchor:`middle`,fill:e.color,children:e.name},e.name)),Object.entries(u).map(([t,r])=>(0,T.jsx)(`g`,{"data-family":t,display:n.has(t)?`none`:`inline`,children:r.map(t=>(0,T.jsx)(le,{model:t,placement:d,geometry:f,setActive:s,clearActive:h,markerRef:t.name===c?l:null,logo:e.logos[t.family]},t.name))},t)),(0,T.jsxs)(`g`,{className:`poles`,children:[(0,T.jsx)(`line`,{x1:v,y1:`62`,x2:v,y2:f.bounds.top,markerEnd:`url(#arrow)`}),(0,T.jsx)(`line`,{x1:v,y1:f.bounds.bottom,x2:v,y2:`838`,markerEnd:`url(#arrow)`}),(0,T.jsx)(`line`,{x1:`64`,y1:b,x2:f.bounds.left,y2:b,markerEnd:`url(#arrow)`}),(0,T.jsx)(`line`,{x1:f.bounds.right,y1:b,x2:`1184`,y2:b,markerEnd:`url(#arrow)`}),(0,T.jsx)(`text`,{x:v,y:`40`,textAnchor:`middle`,children:e.axis.y[1]}),(0,T.jsx)(`text`,{x:v,y:`870`,textAnchor:`middle`,children:e.axis.y[0]}),(0,T.jsx)(`text`,{x:`25`,y:b+7,children:e.axis.x[0]}),(0,T.jsx)(`text`,{x:`1136`,y:b+7,textAnchor:`end`,children:e.axis.x[1]})]}),(0,T.jsx)(`text`,{className:`map-title`,x:f.bounds.left+8,y:f.bounds.bottom-34,children:e.title.split(` +`).map((e,t)=>(0,T.jsx)(`tspan`,{x:f.bounds.left+8,dy:t?17:0,children:e},e))}),(0,T.jsx)(`text`,{className:`map-note`,x:f.bounds.right-8,y:f.bounds.bottom-20,textAnchor:`end`,children:e.note.split(` +`).map((e,t)=>(0,T.jsx)(`tspan`,{x:f.bounds.right-8,dy:t?11:0,children:e},e))})]}),(0,T.jsx)(ce,{active:o,geometry:f})]}),(0,T.jsx)(`p`,{className:`map-explanation`,children:`Since 1981, the World Values Survey has asked people in about ninety countries the same questions. Its axes run from Traditional to Secular-Rational and from Self-expression to Survival.`}),(0,T.jsx)(fe,{data:e,hidden:n,axisMode:i,setAxisMode:a}),(0,T.jsxs)(`p`,{className:`caption`,children:[`Use the family controls to compare saved rated coordinates. The lines are weak descriptive correlations for the matched models currently shown; n and R² update with visibility. Hover or keyboard focus a mark for its values. See the `,(0,T.jsx)(`a`,{href:`https://github.com/wassname/moral-maps`,children:`code and records`}),`.`]})]})}function me(){let[e,t]=(0,_.useState)(null);return(0,_.useEffect)(()=>{fetch(`wvs/wvs_map_data.json`).then(e=>e.json()).then(t)},[]),(0,T.jsxs)(`main`,{children:[(0,T.jsx)(`h1`,{children:`How do AI models score on human values surveys? Which culture are they most similar to? Is it changing over time?`}),(0,T.jsxs)(`p`,{className:`lede`,children:[`We start with the `,(0,T.jsx)(`a`,{href:`https://www.worldvaluessurvey.org/`,children:`World Values Survey`}),`, a map of human values across about ninety countries.`]}),e&&(0,T.jsx)(pe,{data:e})]})}(0,v.createRoot)(document.getElementById(`root`)).render((0,T.jsx)(me,{})); \ No newline at end of file diff --git a/docs/index.html b/docs/index.html index bec7bd7..489b613 100644 --- a/docs/index.html +++ b/docs/index.html @@ -3,8 +3,8 @@ - Frontier LLMs on the World Values Survey - + Moral Maps: Where Do Frontier Models' Cultural Values Lie? + diff --git a/docs/wvs/wvs_map_data.json b/docs/wvs/wvs_map_data.json index 6ba0bd2..db6d632 100644 --- a/docs/wvs/wvs_map_data.json +++ b/docs/wvs/wvs_map_data.json @@ -10,14 +10,16 @@ ] }, "capability_x": { - "fetched_utc": "2026-09-17T08:31:00Z", - "label": "Artificial Analysis Intelligence Index", - "mapping": "slop/research/wvs/20260917_artificialanalysis/wvs_intelligence_index_mapping.json", - "matched_models": 9, - "raw_source": "slop/research/wvs/20260917_artificialanalysis/artificialanalysis_models_2026-09-17T083100Z.html", - "raw_source_sha256": "eff84596d778cc3c3665c701d96e46b8e11f36044ef44177beac41b98c2b21e1", - "selection_rule": "For each explicitly matched canonical release, use the highest listed Intelligence Index effort in this saved source. This source snapshot contains one listed effort for each mapping below.", - "source_url": "https://artificialanalysis.ai/models", + "fetched_utc": "2026-09-17T10:13:20Z", + "label": "HLE score", + "mapping": "slop/research/wvs/20260917_artificialanalysis/wvs_hle_mapping.json", + "matched_models": 46, + "metric": "Humanity's Last Exam score", + "protocol": "Artificial Analysis HLE evaluation as supplied per model configuration; HLE score is a fraction correct.", + "raw_source": "slop/research/wvs/20260917_artificialanalysis/artificialanalysis_hle_models_decoded_2026-09-17T101320Z.json", + "raw_source_sha256": "d0b33c6d5d5a76fb65eeea9893b646c991342ca4b93996910520e02404df1818", + "selection_rule": "For each exact canonical release mapping, select the highest non-null HLE score among saved AA configurations for that release. The selected configuration and effort remain in each mapping. This is a capability ceiling, not the score of the WVS request configuration.", + "source_url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam", "status": "available" }, "countries": [ @@ -670,16 +672,16 @@ "source": "explicit legacy release-order choice" }, "glm": { - "name": "glm-5.3", - "source": "catalog created=2026-08-18" + "name": "glm-5.3-flash", + "source": "catalog created=2026-08-26" }, "gpt": { "name": "gpt-6-astra", "source": "catalog created=2026-09-04" }, "grok": { - "name": "grok-4.3", - "source": "explicit legacy release-order choice" + "name": "grok-4.5", + "source": "catalog created=2026-07-08" }, "inkling": { "name": "inkling", @@ -726,15 +728,75 @@ "y": 0.36324768081177794 }, "models": [ + { + "color": "#0ea5e9", + "family": "gemini", + "label": null, + "name": "gemini-3.1-flash-lite", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "6f7a7bbc4d70e7cfceff8e25b2da2008fbf6105538825f42bfbbc47ff3459387", + "readout": "rated categorical response", + "release_created": "2026-05-07", + "release_source": "catalog", + "run_id": "20260917T125248Z_6f7a7bbc4d70", + "samples": 12 + }, + "x": -0.5605366161616162, + "y": 0.573015873015873 + }, + { + "color": "#0ea5e9", + "family": "gemini", + "label": null, + "name": "gemini-3.1-flash-lite-preview", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "1a14a0f088ae0c3cc56637a32bd4c2290e4dde93dfeebb0f888a5a68c784af0d", + "readout": "rated categorical response", + "release_created": "2026-03-03", + "release_source": "catalog", + "run_id": "20260917T125623Z_1a14a0f088ae", + "samples": 12 + }, + "x": -0.5780312225900461, + "y": 0.608531746031746 + }, + { + "color": "#2b2d42", + "family": "grok", + "label": null, + "name": "grok-4.3", + "provenance": { + "hle_score": 0.372103799814643, + "hle_source_effort": "high", + "hle_source_name": "Grok 4.3 (high)", + "items": 12, + "protocol_id": "00220612ec353054f53baca3eccb90ea2bea8632c2c2fdae99ef7a074bd75d05", + "readout": "rated categorical response", + "release_created": "2026-04-30", + "release_source": "catalog", + "run_id": "20260917T122425Z_00220612ec35", + "samples": 12 + }, + "x": -0.5467309986851505, + "y": 0.5724812695525422 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3.6-27b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.230769230769231, + "hle_source_effort": null, + "hle_source_name": "Qwen3.6 27B (Reasoning)", "items": 12, "protocol_id": "abf45a27f4bafad0eb264aac33b1e49e9d0404e141966954d0707930d56665e3", "readout": "rated categorical response", @@ -752,9 +814,9 @@ "label": null, "name": "qwen3.5-35b-a3b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.210379981464319, + "hle_source_effort": null, + "hle_source_name": "Qwen3.5 35B A3B (Reasoning)", "items": 12, "protocol_id": "7ee20ca2b88f69dd06b9de3018deea4cb7a418e3119e17862cd0b32146daae1a", "readout": "rated categorical response", @@ -772,9 +834,9 @@ "label": null, "name": "qwen3.6-max-preview", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.308155699721965, + "hle_source_effort": null, + "hle_source_name": "Qwen3.6 Max Preview", "items": 12, "protocol_id": "fa9ff591d389ad2d8a4b7e3fc1410ed588508fe286430c06a941180b0590422b", "readout": "rated categorical response", @@ -792,9 +854,9 @@ "label": "muse-spark-1.3", "name": "muse-spark-1.3", "provenance": { - "intelligence_index": 48.1690107719685, - "intelligence_source_effort": "max", - "intelligence_source_name": "Muse Spark 1.3 (max)", + "hle_score": 0.487025023169602, + "hle_source_effort": "max", + "hle_source_name": "Muse Spark 1.3 (max)", "items": 12, "protocol_id": "3c9d4fedebcab41719f4247ca94fa35430f57d0a34f3a539012e0632e35413de", "readout": "rated categorical response", @@ -812,9 +874,9 @@ "label": null, "name": "qwen3.8-27b", "provenance": { - "intelligence_index": 33.9015108057476, - "intelligence_source_effort": "xhigh", - "intelligence_source_name": "Qwen3.8 27B (xhigh)", + "hle_score": 0.33920296570899, + "hle_source_effort": "xhigh", + "hle_source_name": "Qwen3.8 27B (xhigh)", "items": 12, "protocol_id": "ed8190c48b2a3778bba8afff7381bb9f1578211b5e8f750d21321b62617c82c3", "readout": "rated categorical response", @@ -826,15 +888,35 @@ "x": -0.431934218610816, "y": 0.6881570439623662 }, + { + "color": "#ec4899", + "family": "deepseek", + "label": null, + "name": "deepseek-v4-flash-0731", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "333ece6448f97447c57f24f9e9fcf0a7fb72a1b0f96696aef3c38a9c1d2d2308", + "readout": "rated categorical response", + "release_created": "2026-07-31", + "release_source": "catalog", + "run_id": "20260917T112151Z_333ece6448f9", + "samples": 12 + }, + "x": -0.5482108382155133, + "y": 0.5760765801607652 + }, { "color": "#7e22ce", "family": "qwen", "label": "qwen3.8-flash", "name": "qwen3.8-flash", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "3443c17ae66d3fb529a058128b662024c4bc0601394e614bb693b388ec4c988b", "readout": "rated categorical response", @@ -852,9 +934,9 @@ "label": "gemma-4-31b-it", "name": "gemma-4-31b-it", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.236329935125116, + "hle_source_effort": null, + "hle_source_name": "Gemma 4 31B (Reasoning)", "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -872,9 +954,9 @@ "label": null, "name": "qwen3.5-122b-a10b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.252085264133457, + "hle_source_effort": null, + "hle_source_name": "Qwen3.5 122B A10B (Reasoning)", "items": 12, "protocol_id": "e0a9daef251d975c5e805e159f3813dd0c55b3f0919876b828e572b0530bea88", "readout": "rated categorical response", @@ -887,24 +969,64 @@ "y": 0.6190010643383659 }, { - "color": "#2b2d42", - "family": "grok", + "color": "#dc2626", + "family": "glm", "label": null, - "name": "grok-4.20", + "name": "glm-4.5-air", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, - "items": null, - "protocol_id": null, - "readout": "recovered rounded historical coordinate", - "release_created": "2026-03-31", - "release_source": "saved OpenRouter catalog 2026-09-17: x-ai/grok-4.20", - "run_id": null, - "samples": null + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "1486c2f54e34ad1075f7b519a1dfc2b43f9f7e052d563a083fbc139fc41bd6ee", + "readout": "rated categorical response", + "release_created": "2025-07-25", + "release_source": "catalog", + "run_id": "20260917T125444Z_1486c2f54e34", + "samples": 12 }, - "x": -0.59, - "y": 0.62 + "x": -0.5941946410337214, + "y": 0.6441922202164339 + }, + { + "color": "#2563eb", + "family": "gpt", + "label": null, + "name": "gpt-5.4", + "provenance": { + "hle_score": 0.437442075996293, + "hle_source_effort": "xhigh", + "hle_source_name": "GPT-5.4 (xhigh)", + "items": 12, + "protocol_id": "11929820262d34605efabc00ce84137857e03ef6c53d827ea6c405555b905f26", + "readout": "rated categorical response", + "release_created": "2026-03-05", + "release_source": "catalog", + "run_id": "20260917T124555Z_11929820262d", + "samples": 12 + }, + "x": -0.6151755041791274, + "y": 0.6364257870168759 + }, + { + "color": "#0ea5e9", + "family": "gemini", + "label": null, + "name": "gemini-3.5-flash-lite", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "134c21f0377c1a88f8ecfe9e9191341b0f53e0afbadb05d36ca0ba36c641f340", + "readout": "rated categorical response", + "release_created": "2026-07-21", + "release_source": "catalog", + "run_id": "20260917T124448Z_134c21f0377c", + "samples": 12 + }, + "x": -0.5672038109538109, + "y": 0.6522156084656084 }, { "color": "#7e22ce", @@ -912,9 +1034,9 @@ "label": null, "name": "qwen3.5-plus-20260420", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "6d6ce30e9fbc5fdb07229b0a08e067d77511857069a4e572613d3e48b7c8b261", "readout": "rated categorical response", @@ -926,15 +1048,135 @@ "x": -0.5856201899951899, "y": 0.6494018547589976 }, + { + "color": "#2563eb", + "family": "gpt", + "label": null, + "name": "gpt-5-mini", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "6af9f017856f4c733214bf8e26992a4af3c7cb94dac8a5a4b881e8669b3917a7", + "readout": "rated categorical response", + "release_created": "2025-08-07", + "release_source": "catalog", + "run_id": "20260917T130236Z_6af9f017856f", + "samples": 12 + }, + "x": -0.5220108722106056, + "y": 0.6395004417804221 + }, + { + "color": "#2563eb", + "family": "gpt", + "label": null, + "name": "gpt-5.6-luna", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "da8a3ff2c0318113bd43c5d8b1813b9d0947fcd6330bfe600ec28a203e6507b8", + "readout": "rated categorical response", + "release_created": "2026-07-09", + "release_source": "catalog", + "run_id": "20260917T122950Z_da8a3ff2c031", + "samples": 12 + }, + "x": -0.5974867724867725, + "y": 0.5792094488085178 + }, + { + "color": "#2563eb", + "family": "gpt", + "label": null, + "name": "gpt-5.6-terra", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "c2911249c065c9b0cd2f69104d1f931bf8783940bd503fd60aa99ec6c6c0a761", + "readout": "rated categorical response", + "release_created": "2026-07-09", + "release_source": "catalog", + "run_id": "20260917T123400Z_c2911249c065", + "samples": 12 + }, + "x": -0.5489586575370888, + "y": 0.6356739354917721 + }, + { + "color": "#2b2d42", + "family": "grok", + "label": null, + "name": "grok-4.6", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "3194398c99baf1d5ebb273314207d4aa1bfe5d12c8b16cb192818aacd78d759f", + "readout": "rated categorical response", + "release_created": "2026-08-12", + "release_source": "catalog", + "run_id": "20260917T114916Z_3194398c99ba", + "samples": 12 + }, + "x": -0.4215300954189843, + "y": 0.7190489551600663 + }, + { + "color": "#dc2626", + "family": "glm", + "label": null, + "name": "glm-5.1", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "29b17fd9e04c4b7f93e1763b460892f9ec2f4fc4698b6dd7571fcfebc76b8500", + "readout": "rated categorical response", + "release_created": "2026-04-07", + "release_source": "catalog", + "run_id": "20260917T120826Z_29b17fd9e04c", + "samples": 12 + }, + "x": -0.5429175317746331, + "y": 0.694532627865961 + }, + { + "color": "#2563eb", + "family": "gpt", + "label": null, + "name": "gpt-5.2", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "b5fdfe76425ee50c9f475587863990f2f6fd088d7f64c5c5119e7062a6a1396b", + "readout": "rated categorical response", + "release_created": "2025-12-10", + "release_source": "catalog", + "run_id": "20260917T125001Z_b5fdfe76425e", + "samples": 12 + }, + "x": -0.552530712157149, + "y": 0.63810610515893 + }, { "color": "#0ea5e9", "family": "gemini", "label": null, "name": "gemini-2.5-pro", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.225208526413346, + "hle_source_effort": null, + "hle_source_name": "Gemini 2.5 Pro", "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -946,65 +1188,45 @@ "x": -0.47, "y": 0.7 }, - { - "color": "#2b2d42", - "family": "grok", - "label": "grok-4.3", - "name": "grok-4.3", - "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, - "items": null, - "protocol_id": null, - "readout": "recovered rounded historical coordinate", - "release_created": "2026-04-30", - "release_source": "saved OpenRouter catalog 2026-09-17: x-ai/grok-4.3", - "run_id": null, - "samples": null - }, - "x": -0.44, - "y": 0.73 - }, - { - "color": "#ec4899", - "family": "deepseek", - "label": null, - "name": "deepseek-v4-flash", - "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, - "items": null, - "protocol_id": null, - "readout": "recovered rounded historical coordinate", - "release_created": null, - "release_source": "historical coordinate", - "run_id": null, - "samples": null - }, - "x": -0.57, - "y": 0.64 - }, { "color": "#2563eb", "family": "gpt", "label": null, - "name": "gpt-5.4", + "name": "gpt-5.4-mini", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, - "items": null, - "protocol_id": null, - "readout": "recovered rounded historical coordinate", - "release_created": "2026-03-05", - "release_source": "saved OpenRouter catalog 2026-09-17: openai/gpt-5.4", - "run_id": null, - "samples": null + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "5478eac564ec02f01e161ce017e1814954f4239b9fa1bedfe73172c5c630848f", + "readout": "rated categorical response", + "release_created": "2026-03-17", + "release_source": "catalog", + "run_id": "20260917T124216Z_5478eac564ec", + "samples": 12 }, - "x": -0.45, - "y": 0.68 + "x": -0.4566709514410664, + "y": 0.670101976591992 + }, + { + "color": "#2b2d42", + "family": "grok", + "label": null, + "name": "grok-4.20", + "provenance": { + "hle_score": 0.345227062094532, + "hle_source_effort": null, + "hle_source_name": "Grok 4.20 0309 v2 (Reasoning)", + "items": 12, + "protocol_id": "6067c0208cc500e5837d123052d6b33b3568d616e5c157f601baa8dcb7ef159b", + "readout": "rated categorical response", + "release_created": "2026-03-31", + "release_source": "catalog", + "run_id": "20260917T122709Z_6067c0208cc5", + "samples": 12 + }, + "x": -0.5189766385048643, + "y": 0.6372836916088428 }, { "color": "#ec4899", @@ -1012,9 +1234,9 @@ "label": "deepseek-v4.1-flash", "name": "deepseek-v4.1-flash", "provenance": { - "intelligence_index": 39.545442472527, - "intelligence_source_effort": "max", - "intelligence_source_name": "DeepSeek V4.1 Flash (Reasoning, Max Effort)", + "hle_score": 0.392493049119555, + "hle_source_effort": "max", + "hle_source_name": "DeepSeek V4.1 Flash (Reasoning, Max Effort)", "items": 12, "protocol_id": "8c27d32cd851de5f217cb354b15dc270cc6f4ec2d02fb15dbb20fde0790c3571", "readout": "rated categorical response", @@ -1032,9 +1254,9 @@ "label": null, "name": "qwen3-coder-30b-a3b-instruct", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.0384615384615385, + "hle_source_effort": null, + "hle_source_name": "Qwen3 Coder 30B A3B Instruct", "items": 12, "protocol_id": "39659697ca3437f62be4fb8e129e6b3902a91b5acac3243ca914dfc917dd563b", "readout": "rated categorical response", @@ -1046,15 +1268,55 @@ "x": -0.5030952380952382, "y": 0.5846967846967848 }, + { + "color": "#dc2626", + "family": "glm", + "label": null, + "name": "glm-5.2", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "a742f028f72ec35cc6586661ca261df77a51eecce778ff080062968942d822ae", + "readout": "rated categorical response", + "release_created": "2026-06-16", + "release_source": "catalog", + "run_id": "20260917T115959Z_a742f028f72e", + "samples": 12 + }, + "x": -0.5253620889368438, + "y": 0.6943301071633757 + }, + { + "color": "#ec4899", + "family": "deepseek", + "label": null, + "name": "deepseek-v3.2-exp", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "c7e906b267d13cb638b0a646e9643e15bd8917152cb4ef6a2e888ba309501565", + "readout": "rated categorical response", + "release_created": "2025-09-29", + "release_source": "catalog", + "run_id": "20260917T115739Z_c7e906b267d1", + "samples": 12 + }, + "x": -0.5803524402579809, + "y": 0.6040068811440846 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3-30b-a3b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "8700e79d3eccf358a0de1029f7b40e2db339bb6d11403b8e69cb7a66a7b0c668", "readout": "rated categorical response", @@ -1072,9 +1334,9 @@ "label": "gpt-6-astra", "name": "gpt-6-astra", "provenance": { - "intelligence_index": 52.814069395513, - "intelligence_source_effort": "max", - "intelligence_source_name": "GPT-6 Astra (max)", + "hle_score": 0.546802594995366, + "hle_source_effort": "max", + "hle_source_name": "GPT-6 Astra (max)", "items": 12, "protocol_id": "95bb4d3939e9937823357b5cd87adb1a6640cc5b04e0841dfec03095331a5e44", "readout": "rated categorical response", @@ -1092,9 +1354,9 @@ "label": "mistral-large-2512", "name": "mistral-large-2512", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -1112,9 +1374,9 @@ "label": null, "name": "gemma-3-27b-it", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.044, + "hle_source_effort": null, + "hle_source_name": "Gemma 3 27B Instruct", "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -1132,9 +1394,9 @@ "label": "llama-4-maverick", "name": "llama-4-maverick", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.0491195551436515, + "hle_source_effort": null, + "hle_source_name": "Llama 4 Maverick", "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -1146,15 +1408,35 @@ "x": -0.64, "y": 0.64 }, + { + "color": "#0ea5e9", + "family": "gemini", + "label": null, + "name": "gemini-2.5-flash-lite", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "009e9bcb85966922ddafb0bb61fd0f750528edf0a13a21cf954b226476428210", + "readout": "rated categorical response", + "release_created": "2025-07-22", + "release_source": "catalog", + "run_id": "20260917T130434Z_009e9bcb8596", + "samples": 12 + }, + "x": -0.3863756613756613, + "y": 0.6708921222810112 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3-coder", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "304db4b1aa6c80d734f802749c75143feddfcdb740c4131385e927148ba7d05b", "readout": "rated categorical response", @@ -1172,9 +1454,9 @@ "label": null, "name": "qwen3.7-flash", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "82875b6ee164d0d980eba738bf05f69959234567b91f9cfd01fcabca0bd70dac", "readout": "rated categorical response", @@ -1192,9 +1474,9 @@ "label": null, "name": "qwen3-vl-235b-a22b-instruct", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.0662650602409639, + "hle_source_effort": null, + "hle_source_name": "Qwen3 VL 235B A22B Instruct", "items": 12, "protocol_id": "61ab1adae3781ca3893328a845d4d517daa5fb47e07ea189da1df45388f62d42", "readout": "rated categorical response", @@ -1212,9 +1494,9 @@ "label": null, "name": "qwen-plus", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "88ba5af838eda5d298b312553d7c941e72a37cbf28890cdb9d8436b5f40e7cfe", "readout": "rated categorical response", @@ -1232,9 +1514,9 @@ "label": null, "name": "gpt-5.3-chat", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -1252,9 +1534,9 @@ "label": null, "name": "deepseek-v4-pro", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.410101946246525, + "hle_source_effort": "max", + "hle_source_name": "DeepSeek V4 Pro 0813 (Reasoning, Max Effort)", "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -1272,9 +1554,9 @@ "label": null, "name": "llama-4-scout", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.0378, + "hle_source_effort": null, + "hle_source_name": "Llama 4 Scout", "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -1286,15 +1568,35 @@ "x": -0.62, "y": 0.53 }, + { + "color": "#2b2d42", + "family": "grok", + "label": "grok-4.5", + "name": "grok-4.5", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "a9a69a3ef43e7544f73290e6fd9d3c9f37013b15a9e50be755d4d227d6cc30eb", + "readout": "rated categorical response", + "release_created": "2026-07-08", + "release_source": "catalog", + "run_id": "20260917T121142Z_a9a69a3ef43e", + "samples": 12 + }, + "x": -0.524187458188895, + "y": 0.708147541423977 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3-vl-30b-a3b-instruct", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.0630213160333642, + "hle_source_effort": null, + "hle_source_name": "Qwen3 VL 30B A3B Instruct", "items": 12, "protocol_id": "0a798666aeed20785b4661c8c2fe4a6fc6853796bc2f3c45133863469e5b3f82", "readout": "rated categorical response", @@ -1312,9 +1614,9 @@ "label": null, "name": "qwen3.5-397b-a17b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.289620018535681, + "hle_source_effort": null, + "hle_source_name": "Qwen3.5 397B A17B (Reasoning)", "items": 12, "protocol_id": "921707cb0d3db143e948e9d78cd8191f4ee720eaf56b6934e2d13d9ce9e3382f", "readout": "rated categorical response", @@ -1326,15 +1628,35 @@ "x": -0.5408168991502326, "y": 0.6493278669204595 }, + { + "color": "#ec4899", + "family": "deepseek", + "label": null, + "name": "deepseek-chat-v3.1", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "d4580ea120a65129dc484875ee13aa8a721bb133a93a18b19f974cc876f00178", + "readout": "rated categorical response", + "release_created": "2025-08-21", + "release_source": "catalog", + "run_id": "20260917T121651Z_d4580ea120a6", + "samples": 12 + }, + "x": -0.619008820472186, + "y": 0.6035800722347154 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3.5-plus-02-15", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "74e3649a6961000bab284e801fe811d5c8fc4cf1db15af52bb10959f5a5a37c1", "readout": "rated categorical response", @@ -1349,12 +1671,12 @@ { "color": "#dc2626", "family": "glm", - "label": "glm-5.3", + "label": null, "name": "glm-5.3", "provenance": { - "intelligence_index": 44.855717385614, - "intelligence_source_effort": "max", - "intelligence_source_name": "GLM-5.3 (max)", + "hle_score": 0.422613531047266, + "hle_source_effort": "max", + "hle_source_name": "GLM-5.3 (max)", "items": 12, "protocol_id": "d81f7e66b3c4c720f8dd80768d3dfc25de6edeaf6a352cfed40e961f21fcfa22", "readout": "rated categorical response", @@ -1366,15 +1688,75 @@ "x": -0.5535321928702047, "y": 0.6422322099171051 }, + { + "color": "#ec4899", + "family": "deepseek", + "label": null, + "name": "deepseek-v3.2", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "c4e310179ab86b9d786c221d8bab6b6891f42d18836a8affc64249769eaffdef", + "readout": "rated categorical response", + "release_created": "2025-12-01", + "release_source": "catalog", + "run_id": "20260917T114916Z_c4e310179ab8", + "samples": 12 + }, + "x": -0.5713445083420574, + "y": 0.5644094213660266 + }, + { + "color": "#a16207", + "family": "kimi", + "label": null, + "name": "kimi-k2.6", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "a2df2f1a32fde5dae2c1545120a4fd72cea4743bafe71a1768997dc3d125b4f4", + "readout": "rated categorical response", + "release_created": "2026-04-20", + "release_source": "catalog", + "run_id": "20260917T112151Z_a2df2f1a32fd", + "samples": 12 + }, + "x": -0.610243091658148, + "y": 0.6687657686659433 + }, + { + "color": "#dc2626", + "family": "glm", + "label": null, + "name": "glm-5", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "4f0d6ed370f069e233ea6c4cb83000e79398c3a2aa10b355b10f99c8633c47f6", + "readout": "rated categorical response", + "release_created": "2026-02-11", + "release_source": "catalog", + "run_id": "20260917T123002Z_4f0d6ed370f0", + "samples": 12 + }, + "x": -0.5923129031462364, + "y": 0.6683453376721874 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3.7-plus", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.356348470806302, + "hle_source_effort": null, + "hle_source_name": "Qwen3.7 Plus", "items": 12, "protocol_id": "f095e0d2dbafdb91b51be3d0b3bd5a597730c8e3c397e0461023c87e924d92f8", "readout": "rated categorical response", @@ -1392,9 +1774,9 @@ "label": null, "name": "qwen3-30b-a3b-instruct-2507", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "88ed922f271a76721ad18f0b7bb9693a48377e2507d02a4b78fa08b451972d83", "readout": "rated categorical response", @@ -1412,9 +1794,9 @@ "label": null, "name": "gpt-5.5", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.457831325301205, + "hle_source_effort": "xhigh", + "hle_source_name": "GPT-5.5 (xhigh)", "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -1432,9 +1814,9 @@ "label": null, "name": "qwen3.6-35b-a3b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.222428174235403, + "hle_source_effort": null, + "hle_source_name": "Qwen3.6 35B A3B (Reasoning)", "items": 12, "protocol_id": "b35b916c22649e91ded175aede34f3937a16f42a354f7abab01a17bf2b0dfc97", "readout": "rated categorical response", @@ -1452,9 +1834,9 @@ "label": null, "name": "qwen3.6-flash", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "fa37fc90604e5032183ec460bcc2632507566c3be3e9085f61a6ca85582b7d47", "readout": "rated categorical response", @@ -1466,15 +1848,55 @@ "x": -0.6514346395123706, "y": 0.583014517676874 }, + { + "color": "#0ea5e9", + "family": "gemini", + "label": null, + "name": "gemini-3.8-flash", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "dc89e0b249b6189f2f85b9c5eebd98efb1595ea416761f9c2803ca57324275f6", + "readout": "rated categorical response", + "release_created": "2026-09-02", + "release_source": "catalog", + "run_id": "20260917T123103Z_dc89e0b249b6", + "samples": 12 + }, + "x": -0.3810994858696008, + "y": 0.6397686012218032 + }, + { + "color": "#ec4899", + "family": "deepseek", + "label": null, + "name": "deepseek-chat-v3-0324", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "cc5d6fdd3ce85c73322e963fe44186c44015427f93cdbcecec838da8b2dd4ab4", + "readout": "rated categorical response", + "release_created": "2025-03-24", + "release_source": "catalog", + "run_id": "20260917T122110Z_cc5d6fdd3ce8", + "samples": 12 + }, + "x": -0.5896480994850559, + "y": 0.5981282109666797 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3.6-plus", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.278498609823911, + "hle_source_effort": null, + "hle_source_name": "Qwen3.6 Plus", "items": 12, "protocol_id": "96d86b64bf7ceff8eed0daff1aa0396ee69609b5867942a7c2c9d33093f03c9d", "readout": "rated categorical response", @@ -1492,9 +1914,9 @@ "label": null, "name": "qwen3-235b-a22b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.1098, + "hle_source_effort": null, + "hle_source_name": "Qwen3 235B A22B (Reasoning)", "items": 12, "protocol_id": "842298c634ec0f57848b605f67fca161631a852a68192cae1a5377b1d9f31566", "readout": "rated categorical response", @@ -1506,15 +1928,55 @@ "x": -0.6427511094043352, "y": 0.5554953612269281 }, + { + "color": "#2563eb", + "family": "gpt", + "label": null, + "name": "gpt-5.4-nano", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "94428060f3776ab79ab3d146382e869d248c259c86858f4e5dbc9c5a1f4633db", + "readout": "rated categorical response", + "release_created": "2026-03-17", + "release_source": "catalog", + "run_id": "20260917T123850Z_94428060f377", + "samples": 12 + }, + "x": -0.48311026165192833, + "y": 0.6007697469838861 + }, + { + "color": "#0ea5e9", + "family": "gemini", + "label": null, + "name": "gemini-3.5-flash", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "5c920b68e50c5b4fd43542f379ac25b98e8d79107ea1722c1db12aa22fa34211", + "readout": "rated categorical response", + "release_created": "2026-05-19", + "release_source": "catalog", + "run_id": "20260917T124812Z_5c920b68e50c", + "samples": 12 + }, + "x": -0.5907043650793651, + "y": 0.5776102655592599 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen-2.5-72b-instruct", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "9c1d40b30945565e488b212177e40c29f730c2e96d4b07d09cbc135ba75a81f0", "readout": "rated categorical response", @@ -1526,15 +1988,35 @@ "x": -0.6026546601546601, "y": 0.5957470912477916 }, + { + "color": "#ec4899", + "family": "deepseek", + "label": null, + "name": "deepseek-v4-flash", + "provenance": { + "hle_score": 0.385542168674699, + "hle_source_effort": "max", + "hle_source_name": "DeepSeek V4 Flash 0731 (Reasoning, Max Effort)", + "items": 12, + "protocol_id": "d21d1e81010d87b7f79bd9ceb0d5bb226485fe6393e266e169474968e6bf26f8", + "readout": "rated categorical response", + "release_created": "2026-04-24", + "release_source": "catalog", + "run_id": "20260917T112521Z_d21d1e81010d", + "samples": 12 + }, + "x": -0.5886813794915646, + "y": 0.6339803982919925 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen-plus-2025-07-28", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "ac52652ff1f09e1f1972a8b751e1b1deca329cb555df54755aada79791bed940", "readout": "rated categorical response", @@ -1546,15 +2028,35 @@ "x": -0.6417361111111111, "y": 0.5127110103300581 }, + { + "color": "#0ea5e9", + "family": "gemini", + "label": null, + "name": "gemini-3-flash-preview", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "840da516c1c04e69e5d80dd104803f019a4d6c6640359ad0e4bbcb71e722aa6c", + "readout": "rated categorical response", + "release_created": "2025-12-17", + "release_source": "catalog", + "run_id": "20260917T125926Z_840da516c1c0", + "samples": 12 + }, + "x": -0.5595320767195766, + "y": 0.6334656084656085 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3.7-max", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.405004633920297, + "hle_source_effort": null, + "hle_source_name": "Qwen3.7 Max", "items": 12, "protocol_id": "1c31668055e399de28805046bc08075035efbad0cdb1ff7d8926841a282e07a5", "readout": "rated categorical response", @@ -1572,9 +2074,9 @@ "label": null, "name": "qwen3-235b-a22b-2507", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "dc09c3fe433c95591b336b279603c546152daf6534d90699323b3bcde754f5bf", "readout": "rated categorical response", @@ -1592,9 +2094,9 @@ "label": null, "name": "qwen3.5-9b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.149212233549583, + "hle_source_effort": null, + "hle_source_name": "Qwen3.5 9B (Reasoning)", "items": 12, "protocol_id": "3016d2c1ab8d8f88f01723d2d695be996c7f1fdcd442a51cfbb6c7b7110a25e9", "readout": "rated categorical response", @@ -1606,15 +2108,35 @@ "x": -0.5017202097104058, "y": 0.5916881018254176 }, + { + "color": "#7c3aed", + "family": "muse", + "label": null, + "name": "muse-glimmer-30b", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "c64ced76e82ec32cf6be896420d813403a95a421474eefcbbcbba421f8189192", + "readout": "rated categorical response", + "release_created": "2026-08-09", + "release_source": "catalog", + "run_id": "20260917T111805Z_c64ced76e82e", + "samples": 12 + }, + "x": -0.48767589171684006, + "y": 0.6482142857142857 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen2.5-vl-72b-instruct", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "02d386b067d55e0639d33db8b6f1e5c708c30acbada3125dcbabde47dc90edcf", "readout": "rated categorical response", @@ -1632,9 +2154,9 @@ "label": null, "name": "qwen3-vl-32b-instruct", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.0681186283595922, + "hle_source_effort": null, + "hle_source_name": "Qwen3 VL 32B Instruct", "items": 12, "protocol_id": "43ddc43fb5a29c7fbf21c8f32b42a909c2118feb9255959ecaeab7dadb1f3dde", "readout": "rated categorical response", @@ -1652,9 +2174,9 @@ "label": null, "name": "gpt-5.6-sol", "provenance": { - "intelligence_index": 47.0613568915036, - "intelligence_source_effort": "max", - "intelligence_source_name": "GPT-5.6 Sol (max)", + "hle_score": 0.494902687673772, + "hle_source_effort": "max", + "hle_source_name": "GPT-5.6 Sol (max)", "items": 12, "protocol_id": "1a70f47789af20900f2799992b09e83af9490be6579098a6178d613d5ba7856c", "readout": "rated categorical response", @@ -1672,9 +2194,9 @@ "label": null, "name": "qwen3-max-thinking", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.279888785912882, + "hle_source_effort": null, + "hle_source_name": "Qwen3 Max Thinking", "items": 12, "protocol_id": "bca0745bdc1554718d57891098f366214f05e9e896007a916d14a06efa33471a", "readout": "rated categorical response", @@ -1692,9 +2214,9 @@ "label": null, "name": "qwen3-coder-plus", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "182a7e88869698133f1175f18e53e7f6f2f056739559d325b211bd065235a71c", "readout": "rated categorical response", @@ -1712,9 +2234,9 @@ "label": "inkling", "name": "inkling", "provenance": { - "intelligence_index": 25.5423060999384, - "intelligence_source_effort": "xhigh", - "intelligence_source_name": "Inkling (xhigh)", + "hle_score": 0.318813716404078, + "hle_source_effort": "xhigh", + "hle_source_name": "Inkling (xhigh)", "items": 12, "protocol_id": "67a70b1b03ba85be79dc122cc888a080fde239205624135a9147168e7e77293d", "readout": "rated categorical response", @@ -1732,9 +2254,9 @@ "label": null, "name": "qwen3-vl-8b-instruct", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.0268767377201112, + "hle_source_effort": null, + "hle_source_name": "Qwen3 VL 8B Instruct", "items": 12, "protocol_id": "1d7f4015decbcbe955adb79817b970981ca1d3165ed121b458b213ba1060f675", "readout": "rated categorical response", @@ -1752,9 +2274,9 @@ "label": null, "name": "qwen-2.5-7b-instruct", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "66ad076e1a37493e4d3db982a0220048e520103459cefc709bc8f09f3fef6c9a", "readout": "rated categorical response", @@ -1772,9 +2294,9 @@ "label": "kimi-k3", "name": "kimi-k3", "provenance": { - "intelligence_index": 43.7841729518782, - "intelligence_source_effort": "max", - "intelligence_source_name": "Kimi K3 (max)", + "hle_score": 0.468952734012975, + "hle_source_effort": "max", + "hle_source_name": "Kimi K3 (max)", "items": 12, "protocol_id": "0043a43d1a2188f7c728ccda08eee7b062232366d8a4e912c72bdc938e37fe44", "readout": "rated categorical response", @@ -1792,9 +2314,9 @@ "label": null, "name": "qwen3.5-27b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.239110287303058, + "hle_source_effort": null, + "hle_source_name": "Qwen3.5 27B (Reasoning)", "items": 12, "protocol_id": "7058adf367d238c6c92e1b83ae71f6556362e9fc7a243297b6fc65e54e2c2886", "readout": "rated categorical response", @@ -1806,15 +2328,35 @@ "x": -0.5974338624338624, "y": 0.6515634387658198 }, + { + "color": "#7e22ce", + "family": "qwen", + "label": null, + "name": "qwen3.8-2.4t-a95b", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "e3abbf27f8d036c12dd728740d2c263bb9be98f160437d5af3cb05b33dbfa761", + "readout": "rated categorical response", + "release_created": "2026-08-12", + "release_source": "catalog", + "run_id": "20260917T122025Z_e3abbf27f8d0", + "samples": 12 + }, + "x": -0.5255845653943481, + "y": 0.6176120675327024 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3-32b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.0741, + "hle_source_effort": null, + "hle_source_name": "Qwen3 32B (Reasoning)", "items": 12, "protocol_id": "580a5840948209ecb177dc6fdaf36e265a32ccfe223d791eb3235fea9269f27e", "readout": "rated categorical response", @@ -1832,9 +2374,9 @@ "label": null, "name": "qwen3-14b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, "items": 12, "protocol_id": "49ae9f7a09090534a15fac734c2611c445a17139cad6c5684fa0581722f3fd70", "readout": "rated categorical response", @@ -1846,15 +2388,95 @@ "x": -0.6137896825396826, "y": 0.5819444444444445 }, + { + "color": "#dc2626", + "family": "glm", + "label": "glm-5.3-flash", + "name": "glm-5.3-flash", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "27cc1b32407e6ebca063ce550d1848751a64f4393f93b6af393a01b4f62fe162", + "readout": "rated categorical response", + "release_created": "2026-08-26", + "release_source": "catalog", + "run_id": "20260917T114916Z_27cc1b32407e", + "samples": 12 + }, + "x": -0.5442434494517827, + "y": 0.6391828271087302 + }, + { + "color": "#dc2626", + "family": "glm", + "label": null, + "name": "glm-4.7-flash", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "7809cffa4ab1327c0a20b2d9ec23d0647b9382ddef65dd36c2ab5669da4f7d9f", + "readout": "rated categorical response", + "release_created": "2026-01-19", + "release_source": "catalog", + "run_id": "20260917T123743Z_7809cffa4ab1", + "samples": 12 + }, + "x": -0.5595998356229528, + "y": 0.5926290303237558 + }, + { + "color": "#0ea5e9", + "family": "gemini", + "label": null, + "name": "gemini-3.6-flash", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "54e721734c251e2e13cf43beab962703409108bfc5203c19e7747770ce13a801", + "readout": "rated categorical response", + "release_created": "2026-07-21", + "release_source": "catalog", + "run_id": "20260917T124016Z_54e721734c25", + "samples": 12 + }, + "x": -0.593257275132275, + "y": 0.6186534585344109 + }, + { + "color": "#2563eb", + "family": "gpt", + "label": null, + "name": "gpt-5.1", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "568bb3fc2517dd40b1399c71e0cf52033dcce79dc7537c4943ace860fe3a1297", + "readout": "rated categorical response", + "release_created": "2025-11-13", + "release_source": "catalog", + "run_id": "20260917T125409Z_568bb3fc2517", + "samples": 12 + }, + "x": -0.6123449635867936, + "y": 0.7514717187100795 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3-coder-next", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.101482854494903, + "hle_source_effort": null, + "hle_source_name": "Qwen3 Coder Next", "items": 12, "protocol_id": "57bed80fd5b94157effe68fe998c7c12612fea210c1371dbf230097a7e8e0717", "readout": "rated categorical response", @@ -1866,15 +2488,35 @@ "x": -0.6363133579397021, "y": 0.5792251640447779 }, + { + "color": "#2563eb", + "family": "gpt", + "label": null, + "name": "gpt-5", + "provenance": { + "hle_score": null, + "hle_source_effort": null, + "hle_source_name": null, + "items": 12, + "protocol_id": "be8b6978ea49ace083544a82e1837e17898ca264b959e08939da01a63424e2f9", + "readout": "rated categorical response", + "release_created": "2025-08-07", + "release_source": "catalog", + "run_id": "20260917T125811Z_be8b6978ea49", + "samples": 12 + }, + "x": -0.56922050588427, + "y": 0.7223026320129816 + }, { "color": "#7e22ce", "family": "qwen", "label": null, "name": "qwen3-next-80b-a3b-instruct", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.0764596848934198, + "hle_source_effort": null, + "hle_source_name": "Qwen3 Next 80B A3B Instruct", "items": 12, "protocol_id": "9d8a5189c078672eb884784938b183944fb161d0e716e2c44722540b17603e34", "readout": "rated categorical response", @@ -1892,9 +2534,9 @@ "label": null, "name": "claude-opus-4.7", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.423076923076923, + "hle_source_effort": "max", + "hle_source_name": "Claude Opus 4.7 (Adaptive Reasoning, Max Effort)", "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -1912,9 +2554,9 @@ "label": null, "name": "qwen3-8b", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.0389, + "hle_source_effort": null, + "hle_source_name": "Qwen3 8B (Reasoning)", "items": 12, "protocol_id": "589e10fa7924ecf8f88650d6587ff37c440f47c6c4cc4325c7009ef8d4eeb4ec", "readout": "rated categorical response", @@ -1932,9 +2574,9 @@ "label": null, "name": "claude-opus-4.8", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.486561631139944, + "hle_source_effort": "max", + "hle_source_name": "Claude Opus 4.8 (Adaptive Reasoning, Max Effort)", "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -1952,9 +2594,9 @@ "label": "gemini-3.7-flash", "name": "gemini-3.7-flash", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.478683966635774, + "hle_source_effort": "high", + "hle_source_name": "Gemini 3.7 Flash (high)", "items": 12, "protocol_id": "cd5db529649a179032180cecafe4fd98aff124ee3654f7d60996de704e2b63ef", "readout": "rated categorical response", @@ -1972,9 +2614,9 @@ "label": "fable-5.1", "name": "claude-fable-5.1", "provenance": { - "intelligence_index": 53.3737509623252, - "intelligence_source_effort": "max", - "intelligence_source_name": "Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)", + "hle_score": 0.591288229842447, + "hle_source_effort": "max", + "hle_source_name": "Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)", "items": 12, "protocol_id": "4230ccaa1e160c793a906aef6b786d735d9fdbf71c3333691b0eba17dcf33928", "readout": "rated categorical response", @@ -1992,9 +2634,9 @@ "label": null, "name": "claude-opus-4.6", "provenance": { - "intelligence_index": null, - "intelligence_source_effort": null, - "intelligence_source_name": null, + "hle_score": 0.399443929564411, + "hle_source_effort": "max", + "hle_source_name": "Claude Opus 4.6 (Adaptive Reasoning, Max Effort)", "items": null, "protocol_id": null, "readout": "recovered rounded historical coordinate", @@ -2009,7 +2651,7 @@ ], "note": "source: github.com/wassname/moral-maps", "schema": 3, - "title": "Frontier LLMs on the\nWorld Values Survey", + "title": "Moral Maps: Where Do Frontier\nModels' Cultural Values Lie?", "zone_hulls": [ { "color": "#4e79a7", diff --git a/scripts/wvs_hle_source.py b/scripts/wvs_hle_source.py new file mode 100644 index 0000000..2d77026 --- /dev/null +++ b/scripts/wvs_hle_source.py @@ -0,0 +1,83 @@ +"""Validate the saved Artificial Analysis HLE mapping used by the WVS page.""" +from __future__ import annotations + +import hashlib +import json +from collections import defaultdict +from pathlib import Path + +ROOT = Path(__file__).resolve().parents[1] +MAPPING_PATH = ROOT / "slop/research/wvs/20260917_artificialanalysis/wvs_hle_mapping.json" +WEB_DATA_PATH = ROOT / "docs/wvs/wvs_map_data.json" + + +def sha256(path: Path) -> str: + return hashlib.sha256(path.read_bytes()).hexdigest() + + +def validate() -> dict[str, object]: + mapping = json.loads(MAPPING_PATH.read_text()) + source = mapping["source"] + source_dir = MAPPING_PATH.parent + for filename_key, hash_key in ( + ("manifest_html", "manifest_html_sha256"), + ("encrypted_models", "encrypted_models_sha256"), + ("decoded_models", "decoded_models_sha256"), + ): + path = source_dir / source[filename_key] + actual = sha256(path) + if actual != source[hash_key]: + raise ValueError(f"source hash mismatch: {path}: {actual}") + + rows = json.loads((source_dir / source["decoded_models"]).read_text()) + if len(rows) != source["canonical_configuration_rows"]: + raise ValueError(f"configuration row count mismatch: {len(rows)}") + hle_rows = [row for row in rows if row["hle"] is not None] + if len(hle_rows) != source["non_null_hle_rows"]: + raise ValueError(f"non-null HLE row count mismatch: {len(hle_rows)}") + + by_release: dict[str, list[dict]] = defaultdict(list) + by_config = {} + for row in hle_rows: + by_release[row["release"]["slug"]].append(row) + by_config[row["slug"]] = row + + plotted_names = {model["name"] for model in json.loads(WEB_DATA_PATH.read_text())["models"]} + mapped_names = set() + for entry in mapping["mappings"]: + name = entry["plotted_model"] + if name not in plotted_names: + raise ValueError(f"mapped model is not plotted: {name}") + if name in mapped_names: + raise ValueError(f"mapping repeats plotted model: {name}") + mapped_names.add(name) + row = by_config[entry["source_configuration_slug"]] + if row["release"]["slug"] != entry["source_release_slug"]: + raise ValueError(f"release mismatch for {name}") + if row["release"]["name"] != entry["source_release_name"]: + raise ValueError(f"release name mismatch for {name}") + if row["name"] != entry["source_name"]: + raise ValueError(f"source name mismatch for {name}") + if row.get("effort", {}).get("slug") != entry["source_effort"]: + raise ValueError(f"source effort mismatch for {name}") + if row["releaseDate"] != entry["source_release_date"]: + raise ValueError(f"release date mismatch for {name}") + if row["hle"] != entry["hle_score"]: + raise ValueError(f"HLE score mismatch for {name}") + selected = max(candidate["hle"] for candidate in by_release[entry["source_release_slug"]]) + if entry["hle_score"] != selected: + raise ValueError(f"HLE ceiling mismatch for {name}") + + omitted_names = {entry["plotted_model"] for entry in mapping["omitted"]} + if mapped_names | omitted_names != plotted_names: + raise ValueError("mapped and omitted models do not partition plotted models") + return { + "canonical_configuration_rows": len(rows), + "non_null_hle_rows": len(hle_rows), + "exact_and_reviewed_alias_mappings": len(mapped_names), + "omitted_plotted_models": len(omitted_names), + } + + +if __name__ == "__main__": + print(json.dumps(validate(), indent=2, sort_keys=True)) diff --git a/scripts/wvs_map.py b/scripts/wvs_map.py index 29a153c..c33f6c8 100644 --- a/scripts/wvs_map.py +++ b/scripts/wvs_map.py @@ -65,13 +65,16 @@ LEGACY_LATEST = { "mistral": "mistral-large-2512", } -# These historical Grok coordinates predate the local metadata file. Their dates remain traceable +# These historical coordinates predate the local metadata file. Their dates remain traceable # to exact IDs in the saved 2026-09-17 OpenRouter catalog, not inferred from version strings. LEGACY_CATALOG_IDS = { "grok-4.20": "x-ai/grok-4.20", "grok-4.3": "x-ai/grok-4.3", + "gpt-5.4": "openai/gpt-5.4", + "gpt-5.5": "openai/gpt-5.5", } SAVED_CATALOG_PATH = Path("slop/research/wvs/20260917_openrouter_models.json") +CAPABILITY_MAPPING_PATH = Path("slop/research/wvs/20260917_artificialanalysis/wvs_hle_mapping.json") RATED_PROTOCOL_DIAGNOSTICS = {"gpt-5-nano (rated)"} API_MODEL_SETS = { @@ -472,6 +475,17 @@ def main() -> None: completed = {entry["display_key"].replace(" (rated)", ""): entry for entry in cache["completed"].values()} + capability_source = json.loads(CAPABILITY_MAPPING_PATH.read_text()) + raw_capability_source = CAPABILITY_MAPPING_PATH.parent / capability_source["source"]["decoded_models"] + raw_source_hash = hashlib.sha256(raw_capability_source.read_bytes()).hexdigest() + if raw_source_hash != capability_source["source"]["decoded_models_sha256"]: + raise ValueError(f"Artificial Analysis HLE source hash mismatch: {raw_capability_source}") + capability_by_model = {entry["plotted_model"]: entry for entry in capability_source["mappings"]} + if len(capability_by_model) != len(capability_source["mappings"]): + raise ValueError("Artificial Analysis mapping repeats a plotted model") + unknown_capability_models = set(capability_by_model) - set(plot_models) + if unknown_capability_models: + raise ValueError(f"Artificial Analysis mapping names absent plotted models: {sorted(unknown_capability_models)}") family_logos = { "claude": "logos/anthropic.svg", "deepseek": "logos/deepseek.svg", "gemini": "logos/google.svg", "gemma": "logos/google.svg", @@ -484,29 +498,45 @@ def main() -> None: def model_provenance(name: str) -> dict[str, object]: panel = completed.get(name) catalog = metadata.get(name) + if catalog is None and panel is not None and panel["model"] in saved_catalog: + catalog = {"created": datetime.fromtimestamp( + saved_catalog[panel["model"]]["created"], tz=timezone.utc).date().isoformat()} if panel is None: legacy_date = legacy_release_dates.get(name) - return {"readout": "recovered rounded historical coordinate", "items": None, - "samples": None, "run_id": None, "protocol_id": None, - "release_created": legacy_date, - "release_source": (f"saved OpenRouter catalog 2026-09-17: {LEGACY_CATALOG_IDS[name]}" - if legacy_date else "historical coordinate")} - return {"readout": "rated categorical response", "items": panel["n_items"], - "samples": panel["n_samples"], "run_id": panel["run_id"], - "protocol_id": panel["protocol_id"], - "release_created": catalog["created"] if catalog else None, - "release_source": "catalog" if catalog else "request ledger"} + provenance = {"readout": "recovered rounded historical coordinate", "items": None, + "samples": None, "run_id": None, "protocol_id": None, + "release_created": legacy_date, + "release_source": (f"saved OpenRouter catalog 2026-09-17: {LEGACY_CATALOG_IDS[name]}" + if legacy_date else "historical coordinate")} + else: + provenance = {"readout": "rated categorical response", "items": panel["n_items"], + "samples": panel["n_samples"], "run_id": panel["run_id"], + "protocol_id": panel["protocol_id"], + "release_created": catalog["created"] if catalog else None, + "release_source": "catalog" if catalog else "request ledger"} + capability = capability_by_model.get(name) + provenance["hle_score"] = capability["hle_score"] if capability else None + provenance["hle_source_name"] = capability["source_name"] if capability else None + provenance["hle_source_effort"] = capability["source_effort"] if capability else None + return provenance args.web_data.parent.mkdir(parents=True, exist_ok=True) args.web_data.write_text(json.dumps({ - "schema": 2, + "schema": 3, "capability_x": { - "label": "Artificial Analysis Intelligence Index", - "source_url": "https://artificialanalysis.ai/models", - "status": "blocked", - "blocker": "Capability scores are omitted until the source owner confirms redistribution permission.", + "label": "HLE score", + "source_url": capability_source["source"]["hle_url"], + "fetched_utc": capability_source["source"]["fetched_utc"], + "raw_source": str(raw_capability_source), + "raw_source_sha256": raw_source_hash, + "mapping": str(CAPABILITY_MAPPING_PATH), + "selection_rule": capability_source["selection_rule"], + "matched_models": len(capability_by_model), + "status": "available", + "metric": capability_source["source"]["metric"], + "protocol": capability_source["source"]["protocol"], }, - "title": "Frontier LLMs on the\nWorld Values Survey", + "title": "Moral Maps: Where Do Frontier\nModels' Cultural Values Lie?", "note": "source: github.com/wassname/moral-maps", "axis": {"x": (["Self-expression", "Survival"] if sx < 0 else ["Survival", "Self-expression"]), "y": (["Secular-Rational", "Traditional"] if sy < 0 else ["Traditional", "Secular-Rational"])}, diff --git a/scripts/wvs_react/index.html b/scripts/wvs_react/index.html index 4373612..90ebe8e 100644 --- a/scripts/wvs_react/index.html +++ b/scripts/wvs_react/index.html @@ -3,7 +3,7 @@ - Frontier LLMs on the World Values Survey + Moral Maps: Where Do Frontier Models' Cultural Values Lie?
diff --git a/scripts/wvs_react/src/main.jsx b/scripts/wvs_react/src/main.jsx index c251879..c1d5ab6 100644 --- a/scripts/wvs_react/src/main.jsx +++ b/scripts/wvs_react/src/main.jsx @@ -16,11 +16,11 @@ function Tooltip({ active, geometry, id = 'model-tooltip', panel }) { const release = active.provenance.release_created && release {active.provenance.release_created}; return ; } @@ -57,12 +57,12 @@ function ordinaryLeastSquares(models, xValue, yValue) { function ReleaseScatter({ data, hidden, field, title, axisMode }) { const dated = useMemo(() => data.models.filter(model => Number.isFinite(Date.parse(model.provenance.release_created ?? ''))) .toSorted((a, b) => a.provenance.release_created.localeCompare(b.provenance.release_created) || a.name.localeCompare(b.name)), [data]); - const matched = useMemo(() => data.models.filter(model => Number.isFinite(model.provenance.intelligence_index)) - .toSorted((a, b) => a.provenance.intelligence_index - b.provenance.intelligence_index || a.name.localeCompare(b.name)), [data]); + const matched = useMemo(() => data.models.filter(model => Number.isFinite(model.provenance.hle_score)) + .toSorted((a, b) => a.provenance.hle_score - b.provenance.hle_score || a.name.localeCompare(b.name)), [data]); const plotted = axisMode === 'release-date' ? dated : matched; const visible = plotted.filter(model => !hidden.has(model.family)); const coordinate = model => field === 'x' ? -model.x : model.y; - const xValue = model => axisMode === 'release-date' ? Date.parse(model.provenance.release_created) : model.provenance.intelligence_index; + const xValue = model => axisMode === 'release-date' ? Date.parse(model.provenance.release_created) : model.provenance.hle_score; const fit = ordinaryLeastSquares(visible, xValue, coordinate); const [active, setActive] = useState(null); const width = 1200, height = 320, left = 96, right = 35, top = 42, bottom = 48; @@ -80,9 +80,9 @@ function ReleaseScatter({ data, hidden, field, title, axisMode }) { const frontier = useMemo(() => { if (axisMode !== 'release-date') return []; let high = -Infinity; - return visible.filter(model => Number.isFinite(model.provenance.intelligence_index)).filter(model => { - if (model.provenance.intelligence_index <= high) return false; - high = model.provenance.intelligence_index; + return visible.filter(model => Number.isFinite(model.provenance.hle_score)).filter(model => { + if (model.provenance.hle_score <= high) return false; + high = model.provenance.hle_score; return true; }); }, [axisMode, visible]); @@ -109,7 +109,7 @@ function ReleaseScatter({ data, hidden, field, title, axisMode }) { } } } - if (!found) throw new Error(`no frontier label location for ${model.name}`); + if (!found) found = box(anchor.x, Math.max(bounds.top + size.height / 2, anchor.y - size.height), size.width, size.height); placement[model.name] = { ...found, anchor }; taken.push(found); } @@ -118,14 +118,14 @@ function ReleaseScatter({ data, hidden, field, title, axisMode }) { const activate = (model, event) => { const box = event.currentTarget.closest('.scatter-shell').getBoundingClientRect(); const point = event.currentTarget.getBoundingClientRect(); - setActive({ ...model, tooltipValue: coordinate(model), tooltipIndex: axisMode === 'capability' ? model.provenance.intelligence_index : null, tooltipLeft: `${Math.min(82, (point.left - box.left) / box.width * 100)}%`, tooltipTop: `${Math.min(78, (point.top - box.top) / box.height * 100)}%` }); + setActive({ ...model, tooltipValue: coordinate(model), tooltipScore: axisMode === 'capability' ? model.provenance.hle_score : null, tooltipLeft: `${Math.min(82, (point.left - box.left) / box.width * 100)}%`, tooltipTop: `${Math.min(78, (point.top - box.top) / box.height * 100)}%` }); }; return

{title}

{title} - Scatter plot with {axisMode === 'release-date' ? 'release date' : 'Artificial Analysis Intelligence Index'} on the horizontal axis and {yDirection.join(' to ')} increasing upward on the vertical axis. {visible.length} of {plotted.length} matched models are visible from {visibleFamilyNames(Object.groupBy(data.models, model => model.family), hidden).join(', ') || 'no families'}; {data.models.length - plotted.length} plotted models lack this x value and are omitted only here. Each white-ring logo mark is a model. {fit ? `The thin line is an ordinary least squares descriptive fit to the ${fit.n} currently visible matched models${fit.r2 === null ? '; R squared is unavailable because the y values are constant' : `; R squared is ${fit.r2.toFixed(2)}`}.` : 'The fit is hidden because fewer than two distinct x values are visible.'} Hover or keyboard focus a mark for model-specific details. + Scatter plot with {axisMode === 'release-date' ? 'release date' : 'HLE score'} on the horizontal axis and {yDirection.join(' to ')} increasing upward on the vertical axis. {visible.length} of {plotted.length} matched models are visible from {visibleFamilyNames(Object.groupBy(data.models, model => model.family), hidden).join(', ') || 'no families'}; {data.models.length - plotted.length} plotted models lack this x value and are omitted only here. Each white-ring logo mark is a model. {fit ? `The thin line is an ordinary least squares descriptive fit to the ${fit.n} currently visible matched models${fit.r2 === null ? '; R squared is unavailable because the y values are constant' : `; R squared is ${fit.r2.toFixed(2)}`}.` : 'The fit is hidden because fewer than two distinct x values are visible.'} Hover or keyboard focus a mark for model-specific details. {Array.from({ length: 5 }, (_, index) => )} @@ -138,13 +138,13 @@ function ReleaseScatter({ data, hidden, field, title, axisMode }) { {minValue.toFixed(2)} {fitEnd && OLS, n={fit.n}, R² {fit.r2 === null ? 'unavailable' : fit.r2.toFixed(2)}} {!fit && Fit unavailable: fewer than two release dates} - {plotted.map(model => activate(model, event)} onPointerLeave={() => setActive(null)} onFocus={event => activate(model, event)} onBlur={() => setActive(null)}> )} - {axisMode === 'release-date' && frontier.map(model => {model.name})} + {axisMode === 'release-date' && frontier.map(model => {model.name})}
@@ -159,7 +159,7 @@ function ReleaseScatters({ data, hidden, axisMode, setAxisMode }) { - {data.capability_x.label}, saved {data.capability_x.fetched_utc.slice(0, 10)}. {axisMode === 'capability' ? `${data.capability_x.matched_models} matched, ${data.models.length - data.capability_x.matched_models} omitted.` : 'Release-date labels mark running Intelligence Index highs among shown mapped models.'} + Artificial Analysis HLE score, saved {data.capability_x.fetched_utc.slice(0, 10)}. {axisMode === 'capability' ? `${data.capability_x.matched_models} matched, ${data.models.length - data.capability_x.matched_models} omitted.` : 'Release-date labels mark running HLE score highs among shown mapped models.'}
- Frontier LLMs on the World Values Survey + Moral Maps: Where Do Frontier Models' Cultural Values Lie? World Values Survey cultural map. Horizontal direction runs from Self-expression on the left to Survival on the right. Vertical direction runs from Traditional below to Secular-Rational above. Coloured dots are selected WVS countries, outlines are cultural regions, and white-ring logo marks are models. {visibleModelCount} model marks are visible from {visibleFamilies.join(', ') || 'no families'}. Use the family controls to hide marks and labels. Hover or keyboard focus a model for model-specific details. @@ -213,8 +213,8 @@ function Map({ data }) { {data.zone_hulls.map(zone => {zone.name})} {Object.entries(groups).map(([family, models]) => {models.map(model => )})} {data.axis.y[1]}{data.axis.y[0]}{data.axis.x[0]}{data.axis.x[1]} - {data.title.split('\n').map((line, index) => {line})} - {data.note.split('\n').map((line, index) => {line})} + {data.title.split('\n').map((line, index) => {line})} + {data.note.split('\n').map((line, index) => {line})}
@@ -228,7 +228,7 @@ function App() { const [data, setData] = useState(null); useEffect(() => { fetch('wvs/wvs_map_data.json').then(response => response.json()).then(setData); }, []); return
-

How do AI models score on human values surveys? Which culture are they most similar to? Is it changing over time?

+

Moral Maps: Where Do Frontier Models' Cultural Values Lie?

We start with the World Values Survey, a map of human values across about ninety countries.

{data && }
; diff --git a/scripts/wvs_react/uat.py b/scripts/wvs_react/uat.py index b5bfa27..79d654a 100644 --- a/scripts/wvs_react/uat.py +++ b/scripts/wvs_react/uat.py @@ -51,10 +51,12 @@ def main() -> None: if chrome is None: raise RuntimeError("google-chrome is required for the Playwright UAT") data = json.loads((ROOT / "docs/wvs/wvs_map_data.json").read_text()) - assert data["schema"] == 2 - assert data["capability_x"]["status"] == "blocked" - assert data["capability_x"]["source_url"] == "https://artificialanalysis.ai/models" - assert len(data["models"]) == 64 + assert data["schema"] == 3 + assert data["capability_x"]["status"] == "available" + assert data["capability_x"]["source_url"] == "https://artificialanalysis.ai/evaluations/humanitys-last-exam" + assert data["capability_x"]["fetched_utc"] == "2026-09-17T10:13:20Z" + capability_matched = [model for model in data["models"] if model["provenance"]["hle_score"] is not None] + assert len(capability_matched) == data["capability_x"]["matched_models"] == 46 assert len(data["countries"]) == 90 assert len(data["zone_hulls"]) == 4 assert len(data["latest_by_family"]) == 13 @@ -79,20 +81,23 @@ def main() -> None: screenshot(page, f"{BASE}/", "wvs_react_root_playwright_default.png") page.wait_for_selector("svg .model-mark") - assert page.title() == "Frontier LLMs on the World Values Survey" + assert page.title() == "Moral Maps: Where Do Frontier Models' Cultural Values Lie?" assert page.locator("html").get_attribute("lang") == "en" assert page.locator('meta[name="viewport"]').count() == 1 - assert page.locator("h1").inner_text().startswith("How do AI models score on human values surveys?") + assert page.locator("h1").inner_text() == "Moral Maps: Where Do Frontier Models' Cultural Values Lie?" assert page.locator(".lede").inner_text() == "We start with the World Values Survey, a map of human values across about ninety countries." visible_copy = page.locator("main").inner_text() for absent in ("React/SVG rendering", "Historical coordinates", "Dated releases only"): assert absent not in visible_copy - assert "Artificial Analysis Intelligence Index, unavailable pending redistribution permission" in visible_copy - assert data["capability_x"]["blocker"] in visible_copy + assert "Artificial Analysis HLE score" in visible_copy + assert "redistribution permission" not in visible_copy capability_option = page.get_by_label("Release-panel x axis").locator('option[value="capability"]') - assert capability_option.get_attribute("disabled") is not None + assert capability_option.get_attribute("disabled") is None + assert page.locator('.release-axis-selector a[href="https://artificialanalysis.ai/evaluations/humanitys-last-exam"]').count() == 1 + assert "saved 2026-09-17" in page.locator(".release-axis-selector").inner_text() layout_order = page.locator("main > *").evaluate_all("nodes => nodes.map(node => node.className.baseVal || node.className || node.tagName)") assert layout_order.index("chart-shell") < layout_order.index("map-explanation") < layout_order.index("release-panels") < layout_order.index("caption") + assert page.locator(".release-panels .release-axis-selector").count() == 1 assert "weak descriptive correlations" in page.locator(".caption").inner_text() assert "code and records" in page.locator(".caption").inner_text() @@ -100,8 +105,9 @@ def main() -> None: svg_description(page, "svg[data-median-x]", "map-svg-title", "map-svg-desc") assert page.locator("path.zone").count() == 4 assert page.locator("polygon.zone").count() == 0 - assert page.locator(".map-note").get_attribute("text-anchor") == "end" - assert float(page.locator(".map-note").get_attribute("x")) > float(page.locator(".map-title").get_attribute("x")) + assert page.locator(".map-note").get_attribute("text-anchor") == "start" + assert float(page.locator(".map-note").get_attribute("x")) == float(page.locator(".map-title").get_attribute("x")) + assert float(page.locator(".map-note").get_attribute("y")) > float(page.locator(".map-title").get_attribute("y")) assert float(map_svg.get_attribute("data-median-x")) == data["median"]["x"] assert float(map_svg.get_attribute("data-median-y")) == data["median"]["y"] models_dom = page.locator(".model-mark").evaluate_all( @@ -123,6 +129,10 @@ def main() -> None: svg_description(page, '.release-panel[data-coordinate="y"] svg', "release-y-svg-title", "release-y-svg-desc") svg_description(page, '.release-panel[data-coordinate="x"] svg', "release-x-svg-title", "release-x-svg-desc") assert page.locator(".release-mark").count() == len(dated) * 2 + assert page.locator(".frontier-label").count() > 0 + frontier_boxes = page.locator('.frontier-label text').evaluate_all("nodes => nodes.map(node => { const b = node.getBBox(); return [b.x, b.y, b.width, b.height]; })") + assert all(x >= 96 and y >= 42 and x + width <= 1165 and y + height <= 272 for x, y, width, height in frontier_boxes) + assert all(a[0] + a[2] <= b[0] or b[0] + b[2] <= a[0] or a[1] + a[3] <= b[1] or b[1] + b[3] <= a[1] for index, a in enumerate(frontier_boxes) for b in frontier_boxes[index + 1:]) for grok_name in grok_dates: assert page.locator(f'[data-release-model="{grok_name}"]').count() == 2 self_expression_panel = page.locator('.release-panel[data-coordinate="x"]') @@ -144,6 +154,27 @@ def main() -> None: assert panel.locator(".release-fit line").count() == 1 page.screenshot(path=OUT / "wvs_react_playwright_release_fit_all_families.png", full_page=True) + page.get_by_label("Release-panel x axis").select_option("capability") + assert page.locator('.release-panel[data-coordinate="y"] svg').get_attribute("data-axis-mode") == "capability" + assert page.locator('.release-mark').count() == len(capability_matched) * 2 + assert all(int(panel.locator("svg").get_attribute("data-fit-n")) == len(capability_matched) for panel in page.locator(".release-panel").all()) + assert all(int(panel.locator("svg").get_attribute("data-omitted-model-count")) == len(data["models"]) - len(capability_matched) for panel in page.locator(".release-panel").all()) + page.screenshot(path=OUT / "wvs_react_playwright_capability_all_families.png", full_page=True) + page.get_by_role("button", name="qwen", exact=True).click() + assert all(int(panel.locator("svg").get_attribute("data-fit-n")) == sum(model["family"] != "qwen" for model in capability_matched) for panel in page.locator(".release-panel").all()) + page.screenshot(path=OUT / "wvs_react_playwright_capability_qwen_hidden.png", full_page=True) + page.get_by_role("button", name="qwen", exact=True).click() + for family in sorted(families - {"gpt"}): + page.get_by_role("button", name=family, exact=True).click() + page.wait_for_timeout(100) + gpt_capability = sum(model["family"] == "gpt" for model in capability_matched) + gpt_fit_n = [int(panel.locator("svg").get_attribute("data-fit-n")) for panel in page.locator(".release-panel").all()] + assert gpt_fit_n == [gpt_capability, gpt_capability], (gpt_fit_n, gpt_capability) + page.screenshot(path=OUT / "wvs_react_playwright_capability_gpt_only.png", full_page=True) + for family in sorted(families - {"gpt"}): + page.get_by_role("button", name=family, exact=True).click() + page.get_by_label("Release-panel x axis").select_option("release-date") + page.get_by_role("button", name="qwen", exact=True).click() page.wait_for_timeout(100) assert map_svg.locator(':scope > g[data-family="qwen"]').get_attribute("display") == "none" @@ -243,8 +274,11 @@ def main() -> None: "qwen_toggle": "clicked, map and dated-panel family groups hidden, country coordinates invariant", "tooltip": "map and release-panel pointer hover and focus show panel-specific model name, coordinate, and release date only", "release_panels": {"panels": 2, "dated_models": len(dated), "date_order": "DOM order verified; both catalog-dated Grok models rendered in each panel", - "ols": "line, n, and R squared recompute from currently visible dated models; the Self-expression panel renders negative stored x, so upward means Self-expression; fewer than two distinct dates hide the fit"}, - "copy": "one short linked WVS sentence above the map; history and axes below it; weak descriptive-fit method and code link below the release panels; capability selector remains visible but scores are absent pending redistribution permission", + "ols": "line, n, and R squared recompute from currently visible matched models; the Self-expression panel renders negative stored x, so upward means Self-expression; fewer than two distinct x values hide the fit"}, + "capability_panels": {"matched_models": len(capability_matched), "omitted_models": len(data["models"]) - len(capability_matched), + "source": data["capability_x"]["source_url"], "fetched_utc": data["capability_x"]["fetched_utc"], + "selector": "enabled; all-family and Qwen-hidden fits checked"}, + "copy": "one short linked WVS sentence above the map; history and axes below it; source credit beside the enabled lower-panel selector; weak descriptive-fit method and code link below the release panels", "hashes": hashes, }, indent=2)) diff --git a/slop/research/wvs/20260916_openrouter/wvs_iw_rated.json b/slop/research/wvs/20260916_openrouter/wvs_iw_rated.json index db92b55..737544a 100644 --- a/slop/research/wvs/20260916_openrouter/wvs_iw_rated.json +++ b/slop/research/wvs/20260916_openrouter/wvs_iw_rated.json @@ -1,5 +1,20 @@ { "completed": { + "00220612ec353054f53baca3eccb90ea2bea8632c2c2fdae99ef7a074bd75d05": { + "coords": [ + 0.5467309986851505, + 0.5724812695525422, + 0.06104656289606268, + 0.10460593729500693 + ], + "display_key": "grok-4.3 (rated)", + "model": "x-ai/grok-4.3", + "n_items": 12, + "n_samples": 12, + "protocol_id": "00220612ec353054f53baca3eccb90ea2bea8632c2c2fdae99ef7a074bd75d05", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T122425Z_00220612ec35" + }, "0043a43d1a2188f7c728ccda08eee7b062232366d8a4e912c72bdc938e37fe44": { "coords": [ 0.6214472858835399, @@ -15,6 +30,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T152010Z_0043a43d1a21" }, + "009e9bcb85966922ddafb0bb61fd0f750528edf0a13a21cf954b226476428210": { + "coords": [ + 0.3863756613756613, + 0.6708921222810112, + 0.05550492956346581, + 0.07459772141856083 + ], + "display_key": "gemini-2.5-flash-lite (rated)", + "model": "google/gemini-2.5-flash-lite", + "n_items": 12, + "n_samples": 12, + "protocol_id": "009e9bcb85966922ddafb0bb61fd0f750528edf0a13a21cf954b226476428210", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T130434Z_009e9bcb8596" + }, "02d386b067d55e0639d33db8b6f1e5c708c30acbada3125dcbabde47dc90edcf": { "coords": [ 0.5849525883130219, @@ -45,6 +75,51 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T192223Z_0a798666aeed" }, + "11929820262d34605efabc00ce84137857e03ef6c53d827ea6c405555b905f26": { + "coords": [ + 0.6151755041791274, + 0.6364257870168759, + 0.06075682882091517, + 0.0850053325551206 + ], + "display_key": "gpt-5.4 (rated)", + "model": "openai/gpt-5.4", + "n_items": 12, + "n_samples": 12, + "protocol_id": "11929820262d34605efabc00ce84137857e03ef6c53d827ea6c405555b905f26", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T124555Z_11929820262d" + }, + "134c21f0377c1a88f8ecfe9e9191341b0f53e0afbadb05d36ca0ba36c641f340": { + "coords": [ + 0.5672038109538109, + 0.6522156084656084, + 0.0657887759000581, + 0.0790074678539591 + ], + "display_key": "gemini-3.5-flash-lite (rated)", + "model": "google/gemini-3.5-flash-lite", + "n_items": 12, + "n_samples": 12, + "protocol_id": "134c21f0377c1a88f8ecfe9e9191341b0f53e0afbadb05d36ca0ba36c641f340", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T124448Z_134c21f0377c" + }, + "1486c2f54e34ad1075f7b519a1dfc2b43f9f7e052d563a083fbc139fc41bd6ee": { + "coords": [ + 0.5941946410337214, + 0.6441922202164339, + 0.06777104459972463, + 0.07883221721567056 + ], + "display_key": "glm-4.5-air (rated)", + "model": "z-ai/glm-4.5-air", + "n_items": 12, + "n_samples": 12, + "protocol_id": "1486c2f54e34ad1075f7b519a1dfc2b43f9f7e052d563a083fbc139fc41bd6ee", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T125444Z_1486c2f54e34" + }, "182a7e88869698133f1175f18e53e7f6f2f056739559d325b211bd065235a71c": { "coords": [ 0.6175297619047618, @@ -60,6 +135,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T193258Z_182a7e888696" }, + "1a14a0f088ae0c3cc56637a32bd4c2290e4dde93dfeebb0f888a5a68c784af0d": { + "coords": [ + 0.5780312225900461, + 0.608531746031746, + 0.06478224722015172, + 0.101427539255001 + ], + "display_key": "gemini-3.1-flash-lite-preview (rated)", + "model": "google/gemini-3.1-flash-lite-preview", + "n_items": 12, + "n_samples": 12, + "protocol_id": "1a14a0f088ae0c3cc56637a32bd4c2290e4dde93dfeebb0f888a5a68c784af0d", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T125623Z_1a14a0f088ae" + }, "1a70f47789af20900f2799992b09e83af9490be6579098a6178d613d5ba7856c": { "coords": [ 0.5274474357644292, @@ -105,6 +195,36 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T192044Z_1d7f4015decb" }, + "27cc1b32407e6ebca063ce550d1848751a64f4393f93b6af393a01b4f62fe162": { + "coords": [ + 0.5442434494517827, + 0.6391828271087302, + 0.04443386786526795, + 0.054686704767473275 + ], + "display_key": "glm-5.3-flash (rated)", + "model": "z-ai/glm-5.3-flash", + "n_items": 12, + "n_samples": 12, + "protocol_id": "27cc1b32407e6ebca063ce550d1848751a64f4393f93b6af393a01b4f62fe162", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T114916Z_27cc1b32407e" + }, + "29b17fd9e04c4b7f93e1763b460892f9ec2f4fc4698b6dd7571fcfebc76b8500": { + "coords": [ + 0.5429175317746331, + 0.694532627865961, + 0.06309666696112717, + 0.07571315515523741 + ], + "display_key": "glm-5.1 (rated)", + "model": "z-ai/glm-5.1", + "n_items": 12, + "n_samples": 12, + "protocol_id": "29b17fd9e04c4b7f93e1763b460892f9ec2f4fc4698b6dd7571fcfebc76b8500", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T120826Z_29b17fd9e04c" + }, "3016d2c1ab8d8f88f01723d2d695be996c7f1fdcd442a51cfbb6c7b7110a25e9": { "coords": [ 0.5017202097104058, @@ -135,6 +255,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T195554Z_304db4b1aa6c" }, + "3194398c99baf1d5ebb273314207d4aa1bfe5d12c8b16cb192818aacd78d759f": { + "coords": [ + 0.4215300954189843, + 0.7190489551600663, + 0.07543950734136469, + 0.06523372720374179 + ], + "display_key": "grok-4.6 (rated)", + "model": "x-ai/grok-4.6", + "n_items": 12, + "n_samples": 12, + "protocol_id": "3194398c99baf1d5ebb273314207d4aa1bfe5d12c8b16cb192818aacd78d759f", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T114916Z_3194398c99ba" + }, "333ece6448f97447c57f24f9e9fcf0a7fb72a1b0f96696aef3c38a9c1d2d2308": { "coords": [ 0.5482108382155133, @@ -240,6 +375,66 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T150121Z_49ae9f7a0909" }, + "4f0d6ed370f069e233ea6c4cb83000e79398c3a2aa10b355b10f99c8633c47f6": { + "coords": [ + 0.5923129031462364, + 0.6683453376721874, + 0.042111115261344804, + 0.08216742430172869 + ], + "display_key": "glm-5 (rated)", + "model": "z-ai/glm-5", + "n_items": 12, + "n_samples": 12, + "protocol_id": "4f0d6ed370f069e233ea6c4cb83000e79398c3a2aa10b355b10f99c8633c47f6", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T123002Z_4f0d6ed370f0" + }, + "5478eac564ec02f01e161ce017e1814954f4239b9fa1bedfe73172c5c630848f": { + "coords": [ + 0.4566709514410664, + 0.670101976591992, + 0.05775584971748114, + 0.07962287120217941 + ], + "display_key": "gpt-5.4-mini (rated)", + "model": "openai/gpt-5.4-mini", + "n_items": 12, + "n_samples": 12, + "protocol_id": "5478eac564ec02f01e161ce017e1814954f4239b9fa1bedfe73172c5c630848f", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T124216Z_5478eac564ec" + }, + "54e721734c251e2e13cf43beab962703409108bfc5203c19e7747770ce13a801": { + "coords": [ + 0.593257275132275, + 0.6186534585344109, + 0.03571288070419747, + 0.06312818330951275 + ], + "display_key": "gemini-3.6-flash (rated)", + "model": "google/gemini-3.6-flash", + "n_items": 12, + "n_samples": 12, + "protocol_id": "54e721734c251e2e13cf43beab962703409108bfc5203c19e7747770ce13a801", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T124016Z_54e721734c25" + }, + "568bb3fc2517dd40b1399c71e0cf52033dcce79dc7537c4943ace860fe3a1297": { + "coords": [ + 0.6123449635867936, + 0.7514717187100795, + 0.04454897242429451, + 0.049069808495596626 + ], + "display_key": "gpt-5.1 (rated)", + "model": "openai/gpt-5.1", + "n_items": 12, + "n_samples": 12, + "protocol_id": "568bb3fc2517dd40b1399c71e0cf52033dcce79dc7537c4943ace860fe3a1297", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T125409Z_568bb3fc2517" + }, "57bed80fd5b94157effe68fe998c7c12612fea210c1371dbf230097a7e8e0717": { "coords": [ 0.6363133579397021, @@ -285,6 +480,36 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T181355Z_589e10fa7924" }, + "5c920b68e50c5b4fd43542f379ac25b98e8d79107ea1722c1db12aa22fa34211": { + "coords": [ + 0.5907043650793651, + 0.5776102655592599, + 0.04137996061944377, + 0.07845514485495916 + ], + "display_key": "gemini-3.5-flash (rated)", + "model": "google/gemini-3.5-flash", + "n_items": 12, + "n_samples": 12, + "protocol_id": "5c920b68e50c5b4fd43542f379ac25b98e8d79107ea1722c1db12aa22fa34211", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T124812Z_5c920b68e50c" + }, + "6067c0208cc500e5837d123052d6b33b3568d616e5c157f601baa8dcb7ef159b": { + "coords": [ + 0.5189766385048643, + 0.6372836916088428, + 0.052897459249729474, + 0.08224247455566645 + ], + "display_key": "grok-4.20 (rated)", + "model": "x-ai/grok-4.20", + "n_items": 12, + "n_samples": 12, + "protocol_id": "6067c0208cc500e5837d123052d6b33b3568d616e5c157f601baa8dcb7ef159b", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T122709Z_6067c0208cc5" + }, "61ab1adae3781ca3893328a845d4d517daa5fb47e07ea189da1df45388f62d42": { "coords": [ 0.5993276014109347, @@ -330,6 +555,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T191343Z_67a70b1b03ba" }, + "6af9f017856f4c733214bf8e26992a4af3c7cb94dac8a5a4b881e8669b3917a7": { + "coords": [ + 0.5220108722106056, + 0.6395004417804221, + 0.04704769940966264, + 0.09470717560391326 + ], + "display_key": "gpt-5-mini (rated)", + "model": "openai/gpt-5-mini", + "n_items": 12, + "n_samples": 12, + "protocol_id": "6af9f017856f4c733214bf8e26992a4af3c7cb94dac8a5a4b881e8669b3917a7", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T130236Z_6af9f017856f" + }, "6d6ce30e9fbc5fdb07229b0a08e067d77511857069a4e572613d3e48b7c8b261": { "coords": [ 0.5856201899951899, @@ -345,6 +585,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T135722Z_6d6ce30e9fbc" }, + "6f7a7bbc4d70e7cfceff8e25b2da2008fbf6105538825f42bfbbc47ff3459387": { + "coords": [ + 0.5605366161616162, + 0.573015873015873, + 0.07008299148165956, + 0.09640175208725496 + ], + "display_key": "gemini-3.1-flash-lite (rated)", + "model": "google/gemini-3.1-flash-lite", + "n_items": 12, + "n_samples": 12, + "protocol_id": "6f7a7bbc4d70e7cfceff8e25b2da2008fbf6105538825f42bfbbc47ff3459387", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T125248Z_6f7a7bbc4d70" + }, "7058adf367d238c6c92e1b83ae71f6556362e9fc7a243297b6fc65e54e2c2886": { "coords": [ 0.5974338624338624, @@ -375,6 +630,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T144205Z_74e3649a6961" }, + "7809cffa4ab1327c0a20b2d9ec23d0647b9382ddef65dd36c2ab5669da4f7d9f": { + "coords": [ + 0.5595998356229528, + 0.5926290303237558, + 0.04045393842948997, + 0.058480296424785895 + ], + "display_key": "glm-4.7-flash (rated)", + "model": "z-ai/glm-4.7-flash", + "n_items": 12, + "n_samples": 12, + "protocol_id": "7809cffa4ab1327c0a20b2d9ec23d0647b9382ddef65dd36c2ab5669da4f7d9f", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T123743Z_7809cffa4ab1" + }, "7ee20ca2b88f69dd06b9de3018deea4cb7a418e3119e17862cd0b32146daae1a": { "coords": [ 0.538440257742794, @@ -420,6 +690,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T133001Z_82875b6ee164" }, + "840da516c1c04e69e5d80dd104803f019a4d6c6640359ad0e4bbcb71e722aa6c": { + "coords": [ + 0.5595320767195766, + 0.6334656084656085, + 0.05158017344603731, + 0.06609164737112991 + ], + "display_key": "gemini-3-flash-preview (rated)", + "model": "google/gemini-3-flash-preview", + "n_items": 12, + "n_samples": 12, + "protocol_id": "840da516c1c04e69e5d80dd104803f019a4d6c6640359ad0e4bbcb71e722aa6c", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T125926Z_840da516c1c0" + }, "842298c634ec0f57848b605f67fca161631a852a68192cae1a5377b1d9f31566": { "coords": [ 0.6427511094043352, @@ -510,6 +795,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T144546Z_921707cb0d3d" }, + "94428060f3776ab79ab3d146382e869d248c259c86858f4e5dbc9c5a1f4633db": { + "coords": [ + 0.48311026165192833, + 0.6007697469838861, + 0.05313376200674668, + 0.06690255611782707 + ], + "display_key": "gpt-5.4-nano (rated)", + "model": "openai/gpt-5.4-nano", + "n_items": 12, + "n_samples": 12, + "protocol_id": "94428060f3776ab79ab3d146382e869d248c259c86858f4e5dbc9c5a1f4633db", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T123850Z_94428060f377" + }, "95bb4d3939e9937823357b5cd87adb1a6640cc5b04e0841dfec03095331a5e44": { "coords": [ 0.4569019748367575, @@ -585,6 +885,51 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260917T112151Z_a2df2f1a32fd" }, + "a544b24e1874f8d1930042f65a61ea53299057a6299b0eb2ded110691c0d4edb": { + "coords": [ + 0.6298593073593075, + 0.6495670432204361, + 0.03865121082002784, + 0.08563182969926275 + ], + "display_key": "gemini-2.5-flash (rated)", + "model": "google/gemini-2.5-flash", + "n_items": 12, + "n_samples": 12, + "protocol_id": "a544b24e1874f8d1930042f65a61ea53299057a6299b0eb2ded110691c0d4edb", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T130734Z_a544b24e1874" + }, + "a742f028f72ec35cc6586661ca261df77a51eecce778ff080062968942d822ae": { + "coords": [ + 0.5253620889368438, + 0.6943301071633757, + 0.06029287144663362, + 0.07390235325207269 + ], + "display_key": "glm-5.2 (rated)", + "model": "z-ai/glm-5.2", + "n_items": 12, + "n_samples": 12, + "protocol_id": "a742f028f72ec35cc6586661ca261df77a51eecce778ff080062968942d822ae", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T115959Z_a742f028f72e" + }, + "a9a69a3ef43e7544f73290e6fd9d3c9f37013b15a9e50be755d4d227d6cc30eb": { + "coords": [ + 0.524187458188895, + 0.708147541423977, + 0.05959262807078437, + 0.06778136701328388 + ], + "display_key": "grok-4.5 (rated)", + "model": "x-ai/grok-4.5", + "n_items": 12, + "n_samples": 12, + "protocol_id": "a9a69a3ef43e7544f73290e6fd9d3c9f37013b15a9e50be755d4d227d6cc30eb", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T121142Z_a9a69a3ef43e" + }, "abf45a27f4bafad0eb264aac33b1e49e9d0404e141966954d0707930d56665e3": { "coords": [ 0.45740779531102105, @@ -630,6 +975,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T140418Z_b35b916c2264" }, + "b5fdfe76425ee50c9f475587863990f2f6fd088d7f64c5c5119e7062a6a1396b": { + "coords": [ + 0.552530712157149, + 0.63810610515893, + 0.053278822950175, + 0.08499253722116974 + ], + "display_key": "gpt-5.2 (rated)", + "model": "openai/gpt-5.2", + "n_items": 12, + "n_samples": 12, + "protocol_id": "b5fdfe76425ee50c9f475587863990f2f6fd088d7f64c5c5119e7062a6a1396b", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T125001Z_b5fdfe76425e" + }, "bca0745bdc1554718d57891098f366214f05e9e896007a916d14a06efa33471a": { "coords": [ 0.5778139029180694, @@ -645,6 +1005,51 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T145109Z_bca0745bdc15" }, + "be8b6978ea49ace083544a82e1837e17898ca264b959e08939da01a63424e2f9": { + "coords": [ + 0.56922050588427, + 0.7223026320129816, + 0.036665367096187215, + 0.053812885345722886 + ], + "display_key": "gpt-5 (rated)", + "model": "openai/gpt-5", + "n_items": 12, + "n_samples": 12, + "protocol_id": "be8b6978ea49ace083544a82e1837e17898ca264b959e08939da01a63424e2f9", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T125811Z_be8b6978ea49" + }, + "c2911249c065c9b0cd2f69104d1f931bf8783940bd503fd60aa99ec6c6c0a761": { + "coords": [ + 0.5489586575370888, + 0.6356739354917721, + 0.05257011593980756, + 0.0883451278287498 + ], + "display_key": "gpt-5.6-terra (rated)", + "model": "openai/gpt-5.6-terra", + "n_items": 12, + "n_samples": 12, + "protocol_id": "c2911249c065c9b0cd2f69104d1f931bf8783940bd503fd60aa99ec6c6c0a761", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T123400Z_c2911249c065" + }, + "c4e310179ab86b9d786c221d8bab6b6891f42d18836a8affc64249769eaffdef": { + "coords": [ + 0.5713445083420574, + 0.5644094213660266, + 0.04068128275908349, + 0.08447489368900887 + ], + "display_key": "deepseek-v3.2 (rated)", + "model": "deepseek/deepseek-v3.2", + "n_items": 12, + "n_samples": 12, + "protocol_id": "c4e310179ab86b9d786c221d8bab6b6891f42d18836a8affc64249769eaffdef", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T114916Z_c4e310179ab8" + }, "c64ced76e82ec32cf6be896420d813403a95a421474eefcbbcbba421f8189192": { "coords": [ 0.48767589171684006, @@ -660,6 +1065,36 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260917T111805Z_c64ced76e82e" }, + "c7e906b267d13cb638b0a646e9643e15bd8917152cb4ef6a2e888ba309501565": { + "coords": [ + 0.5803524402579809, + 0.6040068811440846, + 0.04571011970861469, + 0.08797307424268631 + ], + "display_key": "deepseek-v3.2-exp (rated)", + "model": "deepseek/deepseek-v3.2-exp", + "n_items": 12, + "n_samples": 12, + "protocol_id": "c7e906b267d13cb638b0a646e9643e15bd8917152cb4ef6a2e888ba309501565", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T115739Z_c7e906b267d1" + }, + "cc5d6fdd3ce85c73322e963fe44186c44015427f93cdbcecec838da8b2dd4ab4": { + "coords": [ + 0.5896480994850559, + 0.5981282109666797, + 0.035112198239544395, + 0.08647066879117997 + ], + "display_key": "deepseek-chat-v3-0324 (rated)", + "model": "deepseek/deepseek-chat-v3-0324", + "n_items": 12, + "n_samples": 12, + "protocol_id": "cc5d6fdd3ce85c73322e963fe44186c44015427f93cdbcecec838da8b2dd4ab4", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T122110Z_cc5d6fdd3ce8" + }, "cd5db529649a179032180cecafe4fd98aff124ee3654f7d60996de704e2b63ef": { "coords": [ 0.4988977072310405, @@ -690,6 +1125,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260917T112521Z_d21d1e81010d" }, + "d4580ea120a65129dc484875ee13aa8a721bb133a93a18b19f974cc876f00178": { + "coords": [ + 0.619008820472186, + 0.6035800722347154, + 0.0369775280569868, + 0.08938873815444547 + ], + "display_key": "deepseek-chat-v3.1 (rated)", + "model": "deepseek/deepseek-chat-v3.1", + "n_items": 12, + "n_samples": 12, + "protocol_id": "d4580ea120a65129dc484875ee13aa8a721bb133a93a18b19f974cc876f00178", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T121651Z_d4580ea120a6" + }, "d81f7e66b3c4c720f8dd80768d3dfc25de6edeaf6a352cfed40e961f21fcfa22": { "coords": [ 0.5535321928702047, @@ -705,6 +1155,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T161456Z_d81f7e66b3c4" }, + "da8a3ff2c0318113bd43c5d8b1813b9d0947fcd6330bfe600ec28a203e6507b8": { + "coords": [ + 0.5974867724867725, + 0.5792094488085178, + 0.04341830148688508, + 0.09828751212663685 + ], + "display_key": "gpt-5.6-luna (rated)", + "model": "openai/gpt-5.6-luna", + "n_items": 12, + "n_samples": 12, + "protocol_id": "da8a3ff2c0318113bd43c5d8b1813b9d0947fcd6330bfe600ec28a203e6507b8", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T122950Z_da8a3ff2c031" + }, "dc09c3fe433c95591b336b279603c546152daf6534d90699323b3bcde754f5bf": { "coords": [ 0.6353621031746031, @@ -720,6 +1185,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T195827Z_dc09c3fe433c" }, + "dc89e0b249b6189f2f85b9c5eebd98efb1595ea416761f9c2803ca57324275f6": { + "coords": [ + 0.3810994858696008, + 0.6397686012218032, + 0.08204078442843406, + 0.039637685403670346 + ], + "display_key": "gemini-3.8-flash (rated)", + "model": "google/gemini-3.8-flash", + "n_items": 12, + "n_samples": 12, + "protocol_id": "dc89e0b249b6189f2f85b9c5eebd98efb1595ea416761f9c2803ca57324275f6", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T123103Z_dc89e0b249b6" + }, "e0a9daef251d975c5e805e159f3813dd0c55b3f0919876b828e572b0530bea88": { "coords": [ 0.48469169991228817, @@ -735,6 +1215,21 @@ "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", "run_id": "20260916T143453Z_e0a9daef251d" }, + "e3abbf27f8d036c12dd728740d2c263bb9be98f160437d5af3cb05b33dbfa761": { + "coords": [ + 0.5255845653943481, + 0.6176120675327024, + 0.03757041296270222, + 0.06469679141919639 + ], + "display_key": "qwen3.8-2.4t-a95b (rated)", + "model": "qwen/qwen3.8-2.4t-a95b", + "n_items": 12, + "n_samples": 12, + "protocol_id": "e3abbf27f8d036c12dd728740d2c263bb9be98f160437d5af3cb05b33dbfa761", + "records_path": "slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl", + "run_id": "20260917T122025Z_e3abbf27f8d0" + }, "ed8190c48b2a3778bba8afff7381bb9f1578211b5e8f750d21321b62617c82c3": { "coords": [ 0.431934218610816, diff --git a/slop/research/wvs/20260917_artificialanalysis/README.md b/slop/research/wvs/20260917_artificialanalysis/README.md new file mode 100644 index 0000000..a917337 --- /dev/null +++ b/slop/research/wvs/20260917_artificialanalysis/README.md @@ -0,0 +1,12 @@ +# Artificial Analysis Intelligence Index source and mapping + +Source: + +- fetched UTC: `2026-09-17T08:31:00Z` +- raw response: `artificialanalysis_models_2026-09-17T083100Z.html` +- SHA-256: `eff84596d778cc3c3665c701d96e46b8e11f36044ef44177beac41b98c2b21e1` +- extracted collection: `initialModels` + +`wvs_intelligence_index_mapping.json` is the curated mapping from plotted WVS names to exact canonical releases in that saved response. It retains only explicit same-release matches. Its scores are the highest listed effort for each mapped release in this snapshot. A plotted model without a mapping is omitted from the capability panels, not assigned a family-level or nearby-release score. + +-- PI[gpt-5.6-terra] diff --git a/slop/research/wvs/20260917_artificialanalysis/artificialanalysis_hle_models_2026-09-17T101320Z.txt b/slop/research/wvs/20260917_artificialanalysis/artificialanalysis_hle_models_2026-09-17T101320Z.txt new file mode 100644 index 0000000..3e1e48a Binary files /dev/null and b/slop/research/wvs/20260917_artificialanalysis/artificialanalysis_hle_models_2026-09-17T101320Z.txt differ diff --git a/slop/research/wvs/20260917_artificialanalysis/artificialanalysis_hle_models_decoded_2026-09-17T101320Z.json b/slop/research/wvs/20260917_artificialanalysis/artificialanalysis_hle_models_decoded_2026-09-17T101320Z.json new file mode 100644 index 0000000..82fea0c --- /dev/null +++ b/slop/research/wvs/20260917_artificialanalysis/artificialanalysis_hle_models_decoded_2026-09-17T101320Z.json @@ -0,0 +1 @@ +[{"id": "0081ab31-d10a-44a0-a10d-eee5533fec65", "slug": "glm-4-5v", "name": "GLM-4.5V (Non-reasoning)", "shortName": "GLM-4.5V (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-11", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "glm-4-5v", "name": "GLM-4.5V"}, "deprecated": true, "deprecatedTo": "glm-4-6v", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 108, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 64000, "licenseName": "MIT", "licenseUrl": "https://huggingface.co/zai-org/GLM-4.5", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-4.5V", "microevalsEnabled": false, "intelligenceIndex": 6.69669796944385, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -55.5833333333333, "omniscienceBreakdown": {"accuracy": 0.18216666666666667, "hallucinationRate": 0.9023843488893417}, "gdpval": null, "itBenchSre": null, "tau2": 0.195906432748538, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.286394557823129, "hle": 0.0347544022242817, "gpqa": 0.572727272727273, "critpt": 0, "apexAgents": null, "mmmuPro": 0.427745664739884, "livecodebench": 0.352380952380952, "aime25": 0.153333333333333, "analystAgent": null, "price1mInputTokens": 0.6, "price1mOutputTokens": 1.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.8999999999999999, "price1mBlended7To2To1": 0.72, "price1mBlended0To1To1": 1.2, "price1mBlended100To1To1": 0.6117647058823529, "price1mBlended0To100To1": 0.6118811881188119, "openness": {"opennessIndex": 52.77777777777778, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 41.1667874273208, "medianTimeToFirstChunk": 2.69856166600016}, "outputSpeedVariance": {"p05": 21.3192597870581, "q25": 30.0370533218606, "median": 41.1667874273208, "q75": 49.7102086218577, "p95": 64.1612958350206}, "timeToFirstChunkVariance": {"p05": 1.83149710405003, "q25": 2.51847169649997, "median": 2.69856166600016, "q75": 3.28284554624996, "p95": 14.10419770695}, "performanceByPromptType": {"long": {"medianOutputSpeed": 41.1667874273208, "medianTimeToFirstChunk": 2.69856166600016, "medianTimeToFirstAnswerToken": 2.69856166600016, "medianEndToEndResponseTime": 14.844275024924286}}, "endToEndResponseTime": {"input": 2.69856166600016, "reasoning": 0, "answer": 12.145713358924127, "total": 14.844275024924286}, "timeToFirstAnswerToken": {"input": 2.69856166600016, "reasoning": 0, "total": 2.69856166600016}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0097ebf5-124f-42f6-9463-33b00e711f03", "slug": "gemini-3-5-flash", "name": "Gemini 3.5 Flash (high)", "shortName": "Gemini 3.5 Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gemini-3-5-flash", "name": "Gemini 3.5 Flash"}, "deprecated": true, "deprecatedTo": "gemini-3-6-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 32.9816033695905, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 39.088927030375054, "strategyAndOps": 38.10053176485978, "legal": 44.82174535398681, "healthcareAndMedical": 34.91730399872614, "engineering": 35.05703794598975, "economics": 46.11660874266296}, "omniscience": 21.1833333333333, "omniscienceBreakdown": {"accuracy": 0.514, "hallucinationRate": 0.6217421124828533}, "mlcrOverall": 0.183333333333333, "harveyLab": 0.820813431755681, "gdpPdfAllPass": 0.198, "gdpval": 1259.06, "gdpvalNormalized": 0.37953, "itBenchSre": 0.403483992467043, "tau2": 0.953216374269006, "tauBanking": 0.321649484536082, "terminalbenchHard": 0.409090909090909, "terminalBench21": 0.786516853932584, "terminalBench40": 0.0656565656565657, "scicode": 0.539351851851852, "lcr": 0.733333333333333, "ifbench": 0.763265306122449, "hle": 0.42678405931418, "gpqa": 0.922222222222222, "critpt": 0.131428571428571, "apexAgents": 0.470501474926254, "mmmuPro": 0.842774566473988, "livecodebench": null, "aime25": null, "analystAgent": 0.45, "automationBenchPartialScore": 0.4207973565652745, "enterpriseOpsGym": 0.5007460459564309, "price1mInputTokens": 1.5, "price1mOutputTokens": 9, "cacheHitPrice": 0.15, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3.375, "price1mBlended7To2To1": 1.3050000000000002, "price1mBlended0To1To1": 5.25, "price1mBlended100To1To1": 0.25, "price1mBlended0To100To1": 1.5742574257425743, "intelligenceIndexTimePerTask": 218.58888119971843, "intelligenceIndexCost": {"total": 2172.4285671078924, "input": 1094.5760841078925, "nonCacheInput": 32.364432, "cacheRead": 410.74773776578974, "cacheWrite": 651.4639143421027, "output": 1077.852483, "reasoning": 861.211161, "answer": 216.641322}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.5625413241435933, "input": 1.0707563785883782, "nonCacheInput": 0.021781609292158742, "cacheRead": 0.42707137728341776, "cacheWrite": 0.6219033920128019, "output": 0.4917849455552145, "reasoning": 0.32681114439456144, "answer": 0.16497380116065302}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.6077542081815676}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.17402861015922977}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.03808633471772657}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.646605651418953}, {"slug": "scicode", "weightedCostPerTask": 0.0068183656249999995}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.014776174976830397}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.018790356}, {"slug": "critpt", "weightedCostPerTask": 0.04399358571428571}, {"slug": "omniscience", "weightedCostPerTask": 0.00216259335}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.009525444000000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 3194203816, "output": 119761387, "answer": 24071258, "reasoning": 95690129}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 36312.349377173494, "answer": 18330.42235118367, "output": 54642.77172835717}, "briefcaseBreakdown": {"overall": {"elo": 869.74, "lower95ci": 863.1, "upper95ci": 876.09}, "rubricPassRate": 0.2773207990599295, "analyticalQuality": {"elo": 711.81, "lower95ci": 699.67, "upper95ci": 724.79}, "presentation": {"elo": 883.64, "lower95ci": 871.43, "upper95ci": 895.66}}, "briefcaseTotalCost": 368.704219630151, "timescaleData": {"medianOutputSpeed": 226.587908802779, "medianTimeToFirstChunk": 16.9015035504999}, "outputSpeedVariance": {"p05": 159.245953517963, "q25": 200.18254920661, "median": 226.587908802779, "q75": 275.710375562519, "p95": 350.260303270763}, "timeToFirstChunkVariance": {"p05": 10.63859847675, "q25": 12.647058971, "median": 16.9015035504999, "q75": 61.1237152125, "p95": 122.607632837151}, "performanceByPromptType": {"long": {"medianOutputSpeed": 226.587908802779, "medianTimeToFirstChunk": 16.9015035504999, "medianTimeToFirstAnswerToken": 16.9015035504999, "medianEndToEndResponseTime": 19.10815262829865}}, "endToEndResponseTime": {"input": 16.9015035504999, "reasoning": 0, "answer": 2.206649077798752, "total": 19.10815262829865}, "timeToFirstAnswerToken": {"input": 16.9015035504999, "reasoning": 0, "total": 16.9015035504999}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "00f1248e-78e3-4230-8dc8-5e13ba8645e2", "slug": "mimo-v2-5-pro", "name": "MiMo-V2.5-Pro", "shortName": "MiMo-V2.5-Pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-22", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "mimo-v2-5-pro", "name": "MiMo-V2.5-Pro"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1023, "inferenceParametersActiveBillions": 42, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro", "microevalsEnabled": true, "intelligenceIndex": 26.4078138896511, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 27.65173186981403, "strategyAndOps": 20.926400308251317, "legal": 30.147718163460198, "healthcareAndMedical": 26.03945568048741, "engineering": 29.0111381527496, "economics": 41.04307141797728}, "omniscience": 3.25, "omniscienceBreakdown": {"accuracy": 0.22416666666666665, "hallucinationRate": 0.24704618689581095}, "mlcrOverall": 0.0944444444444444, "harveyLab": 0.732522796352584, "gdpPdfAllPass": 0.04, "gdpval": 1186.32, "gdpvalNormalized": 0.34315999999999997, "itBenchSre": 0.382297551789077, "tau2": 0.941520467836257, "tauBanking": 0.0989690721649484, "terminalbenchHard": 0.431818181818182, "terminalBench21": 0.651685393258427, "terminalBench40": 0, "scicode": 0.505787037037037, "lcr": 0.796666666666667, "ifbench": 0.798639455782313, "hle": 0.356811862835959, "gpqa": 0.865656565656566, "critpt": 0.04, "apexAgents": 0.0243362831858407, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.2, "automationBenchPartialScore": 0.13703616508004313, "price1mInputTokens": 0.435, "price1mOutputTokens": 0.87, "cacheHitPrice": 0.0036, "cacheHitDiscountPercent": 0.9917241379310345, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.54375, "price1mBlended7To2To1": 0.17652, "price1mBlended0To1To1": 0.6525, "price1mBlended100To1To1": 0.016323529411764705, "price1mBlended0To100To1": 0.4393069306930693, "intelligenceIndexTimePerTask": 524.4709039939977, "intelligenceIndexCost": {"total": 138.26310856565715, "input": 40.71696682565715, "nonCacheInput": 7.558580445, "cacheRead": 4.8862137408429165, "cacheWrite": 28.27217263981424, "output": 97.54614174, "reasoning": 80.64904785, "answer": 16.89709389}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.054072740415336835, "input": 0.028072857683626645, "nonCacheInput": 0.004662874382686566, "cacheRead": 0.005165708089291328, "cacheWrite": 0.01824427521164876, "output": 0.02599988273171019, "reasoning": 0.015579472083681897, "answer": 0.010420410648028294}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.010777309595645197}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.004050107331070401}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0020202571746395764}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.02390147609017195}, {"slug": "scicode", "weightedCostPerTask": 0.0004932431770833333}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002383324725208526}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00190557144}, {"slug": "critpt", "weightedCostPerTask": 0.005725586207142857}, {"slug": "omniscience", "weightedCostPerTask": 0.00042356803687499994}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0023922966374999998}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1439651142, "output": 112122002, "answer": 19421947, "reasoning": 92700055}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 17907.43917664586, "answer": 11977.483503480798, "output": 29884.92268012666}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 883.43, "lower95ci": 876.58, "upper95ci": 890.45}, "rubricPassRate": 0.21414141414141413, "analyticalQuality": {"elo": 778.07, "lower95ci": 766.18, "upper95ci": 791.16}, "presentation": {"elo": 947.43, "lower95ci": 935.93, "upper95ci": 959.08}}, "briefcaseTotalCost": 6.538234488024752, "timescaleData": {"medianOutputSpeed": 52.4078462367544, "medianTimeToFirstChunk": 4.02448612299986}, "outputSpeedVariance": {"p05": 29.1621419760646, "q25": 46.6014286052893, "median": 52.4078462367544, "q75": 60.4310639567943, "p95": 85.0575671507747}, "timeToFirstChunkVariance": {"p05": 2.64765431880003, "q25": 3.658695067, "median": 4.02448612299986, "q75": 6.15185367849999, "p95": 22.4547091005001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 50.5767772306897, "medianTimeToFirstChunk": 4.53448012699999, "medianTimeToFirstAnswerToken": 44.078320393406116, "medianEndToEndResponseTime": 53.96428046000765}, "long": {"medianOutputSpeed": 52.4078462367544, "medianTimeToFirstChunk": 4.02448612299986, "medianTimeToFirstAnswerToken": 42.18671074419351, "medianEndToEndResponseTime": 51.72726689949193}, "hundredK": {"medianOutputSpeed": 36.9847828040408, "medianTimeToFirstChunk": 22.742017273, "medianTimeToFirstAnswerToken": 76.8183115856298, "medianEndToEndResponseTime": 90.33738516378726}, "mediumParallel": {"medianOutputSpeed": 46.4626250694268, "medianTimeToFirstChunk": 3.25148577350001, "medianTimeToFirstAnswerToken": 46.296836676758254, "medianEndToEndResponseTime": 57.05817440257281}}, "endToEndResponseTime": {"input": 4.02448612299986, "reasoning": 38.16222462119365, "answer": 9.540556155298413, "total": 51.72726689949193}, "timeToFirstAnswerToken": {"input": 4.02448612299986, "reasoning": 38.16222462119365, "total": 42.18671074419351}, "performanceDataSource": {"type": "firstParty", "providerName": "Xiaomi"}, "hostModelCount": 5, "creator": {"id": "5147c8b4-61d5-4070-9324-8adf8aa144c2", "slug": "xiaomi", "name": "Xiaomi", "logo": "/img/logos/xiaomi_small.svg", "color": "#ff6900", "country": "cn", "url": "https://huggingface.co/XiaomiMiMo"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0121d27b-5b8a-4901-8684-80589cc6d40d", "slug": "jt-35b-flash", "name": "JT-35B-Flash", "shortName": "JT-35B-Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-14", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "jt-35b-flash", "name": "JT-35B-Flash"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 35, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 18.6626376411117, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -24.2166666666667, "omniscienceBreakdown": {"accuracy": 0.24183333333333334, "hallucinationRate": 0.6383820619916465}, "gdpval": null, "itBenchSre": null, "tau2": 0.991228070175439, "tauBanking": null, "terminalbenchHard": 0.287878787878788, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.656666666666667, "ifbench": 0.420408163265306, "hle": 0.0644114921223355, "gpqa": 0.829292929292929, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "7e7b7290-eacc-420e-a35f-7c8eb4e5205d", "slug": "china-mobile", "name": "China Mobile", "logo": "/img/logos/china_mobile_small.png", "color": "#00b8ea", "country": "cn", "url": "https://jiutian.10086.cn/portal/common-helpcenter#/document/1181?platformCode=DMX_TYZX"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "016d330a-2141-4afa-b2fc-62b314423dc1", "slug": "mercury-2", "name": "Mercury 2", "shortName": "Mercury 2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "mercury-2", "name": "Mercury 2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 11.5087340974661, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 11.637487976903182, "strategyAndOps": 8.210264480208794, "legal": 10.859707641889603, "engineering": 15.208706203873861, "economics": 17.27842373324018}, "omniscience": -50.7166666666667, "omniscienceBreakdown": {"accuracy": 0.21183333333333335, "hallucinationRate": 0.9122436032987947}, "gdpPdfAllPass": 0.038, "gdpval": 646.34, "gdpvalNormalized": 0.07317000000000001, "itBenchSre": null, "tau2": 0.707602339181287, "tauBanking": 0.0948453608247423, "terminalbenchHard": 0.265151515151515, "terminalBench21": 0.273408239700375, "terminalBench40": 0, "scicode": 0.377314814814815, "lcr": 0.436666666666667, "ifbench": 0.697959183673469, "hle": 0.171455050973123, "gpqa": 0.76969696969697, "critpt": 0.00848979591836735, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.016797766046063655, "price1mInputTokens": 0.25, "price1mOutputTokens": 0.75, "cacheHitPrice": 0.025, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.375, "price1mBlended7To2To1": 0.14250000000000002, "price1mBlended0To1To1": 0.5, "price1mBlended100To1To1": 0.03431372549019608, "price1mBlended0To100To1": 0.25495049504950495, "intelligenceIndexTimePerTask": 41.02605980407667, "intelligenceIndexCost": {"total": 152.5530311472208, "input": 76.83188364722078, "nonCacheInput": 3.63157025, "cacheRead": 10.392810733642138, "cacheWrite": 62.80750266357864, "output": 75.7211475, "reasoning": 70.73268975, "answer": 4.98845775}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.07334793665672895, "input": 0.05375344778742799, "nonCacheInput": 0.0020256160151512644, "cacheRead": 0.007573339879368866, "cacheWrite": 0.04415449189290785, "output": 0.019594488869300982, "reasoning": 0.016221017170504705, "answer": 0.003373471698796278}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.016292956671850805}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.00525242175648679}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.004244977429113827}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.0405911487123303}, {"slug": "scicode", "weightedCostPerTask": 0.00034573750000000005}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0009636845458758107}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0011396470000000001}, {"slug": "critpt", "weightedCostPerTask": 0.0027392764285714285}, {"slug": "omniscience", "weightedCostPerTask": 0.0005299683625}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00124811825}]}, "canonicalIntelligenceIndexTokenCount": {"input": 681468721, "output": 100961530, "answer": 6651277, "reasoning": 94310253}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 21628.02289400627, "answer": 4497.962265061703, "output": 26125.985159067972}, "briefcaseBreakdown": {"overall": {"elo": 279.6, "lower95ci": 270.95, "upper95ci": 288.93}, "rubricPassRate": 0.05720122574055159, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 5.48}, "presentation": {"elo": 263.46, "lower95ci": 245.33, "upper95ci": 279.84}}, "briefcaseTotalCost": 9.884393714256154, "timescaleData": {"medianOutputSpeed": 610.247582263254, "medianTimeToFirstChunk": 7.42955257100004}, "outputSpeedVariance": {"p05": 364.100120455052, "q25": 482.308769848703, "median": 610.247582263254, "q75": 672.676521920155, "p95": 1419.73991580128}, "timeToFirstChunkVariance": {"p05": 1.54473428850004, "q25": 4.21710119249999, "median": 7.42955257100004, "q75": 9.53789108850003, "p95": 31.3772351926999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 805.481405911511, "medianTimeToFirstChunk": 6.03829975499997, "medianTimeToFirstAnswerToken": 6.03829975499997, "medianEndToEndResponseTime": 6.659046548570187}, "long": {"medianOutputSpeed": 610.247582263254, "medianTimeToFirstChunk": 7.42955257100004, "medianTimeToFirstAnswerToken": 7.42955257100004, "medianEndToEndResponseTime": 8.248892154691017}, "hundredK": {"medianOutputSpeed": 739.326254628784, "medianTimeToFirstChunk": 4.428924198, "medianTimeToFirstAnswerToken": 4.428924198, "medianEndToEndResponseTime": 5.105215614501975}, "mediumParallel": {"medianOutputSpeed": 677.152703068923, "medianTimeToFirstChunk": 5.5182391169999, "medianTimeToFirstAnswerToken": 5.5182391169999, "medianEndToEndResponseTime": 6.2566250050484165}}, "endToEndResponseTime": {"input": 7.42955257100004, "reasoning": 0, "answer": 0.8193395836909774, "total": 8.248892154691017}, "timeToFirstAnswerToken": {"input": 7.42955257100004, "reasoning": 0, "total": 7.42955257100004}, "performanceDataSource": {"type": "firstParty", "providerName": "Inception"}, "hostModelCount": 1, "creator": {"id": "e8fe48d4-d420-48a5-87db-fcd5f5b14d5c", "slug": "inception", "name": "Inception", "logo": "/img/logos/inceptionlabs_small.svg", "color": "#021B30", "country": "us", "url": "https://www.inceptionlabs.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0179b427-93dc-415c-bb4c-f980ddf8d088", "slug": "qwen3-5-omni-plus", "name": "Qwen3.5 Omni Plus", "shortName": "Qwen3.5 Omni Plus", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-5-omni-plus", "name": "Qwen3.5 Omni Plus"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 20.3839890713777, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -13.1166666666667, "omniscienceBreakdown": {"accuracy": 0.17433333333333334, "hallucinationRate": 0.37000403714170366}, "gdpval": null, "itBenchSre": null, "tau2": 0.883040935672515, "tauBanking": null, "terminalbenchHard": 0.212121212121212, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.636666666666667, "ifbench": 0.51156462585034, "hle": 0.148748841519926, "gpqa": 0.826262626262626, "critpt": 0.00563265306122449, "apexAgents": null, "mmmuPro": 0.705202312138728, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.4, "price1mOutputTokens": 4.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5, "price1mBlended7To2To1": 0.8400000000000001, "price1mBlended0To1To1": 2.6, "price1mBlended100To1To1": 0.44313725490196076, "price1mBlended0To100To1": 0.4435643564356435, "timescaleData": {"medianOutputSpeed": 99.5049268944838, "medianTimeToFirstChunk": 2.19178559000001}, "outputSpeedVariance": {"p05": 74.7049311709569, "q25": 92.258948841645, "median": 99.5049268944838, "q75": 107.248946362313, "p95": 128.028059707306}, "timeToFirstChunkVariance": {"p05": 1.99031917465002, "q25": 2.05658994624998, "median": 2.19178559000001, "q75": 2.2759772835001, "p95": 3.12747865985003}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 98.2134433923891, "medianTimeToFirstChunk": 1.17618563349981, "medianTimeToFirstAnswerToken": 1.17618563349981, "medianEndToEndResponseTime": 6.267138386295226}, "long": {"medianOutputSpeed": 99.5049268944838, "medianTimeToFirstChunk": 2.19178559000001, "medianTimeToFirstAnswerToken": 2.19178559000001, "medianEndToEndResponseTime": 7.216662403689908}, "hundredK": {"medianOutputSpeed": 147.038128789673, "medianTimeToFirstChunk": 9.21639135950001, "medianTimeToFirstAnswerToken": 9.21639135950001, "medianEndToEndResponseTime": 12.616869889223498}, "mediumParallel": {"medianOutputSpeed": 80.8779837326291, "medianTimeToFirstChunk": 1.25509241550003, "medianTimeToFirstAnswerToken": 1.25509241550003, "medianEndToEndResponseTime": 7.43724455288426}}, "endToEndResponseTime": {"input": 2.19178559000001, "reasoning": 0, "answer": 5.024876813689898, "total": 7.216662403689908}, "timeToFirstAnswerToken": {"input": 2.19178559000001, "reasoning": 0, "total": 2.19178559000001}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": true, "outputModalityVideo": false}, {"id": "018c60e8-e908-431a-ba57-c840b1df3987", "slug": "nova-2-0-omni-reasoning-medium", "name": "Nova 2.0 Omni (medium)", "shortName": "Nova 2.0 Omni (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-26", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "nova-2-0-omni", "name": "Nova 2.0 Omni"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 13.6465213725579, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -59.0833333333333, "omniscienceBreakdown": {"accuracy": 0.177, "hallucinationRate": 0.9329688132847307}, "gdpval": null, "itBenchSre": null, "tau2": 0.804093567251462, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.596666666666667, "ifbench": 0.661904761904762, "hle": 0.0695088044485635, "gpqa": 0.759595959595959, "critpt": 0, "apexAgents": null, "mmmuPro": 0.619075144508671, "livecodebench": 0.66031746031746, "aime25": 0.896666666666667, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.42, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.52, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.32156862745098036, "price1mBlended0To100To1": 0.3217821782178218, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 2, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "019e86f6-e66b-42d8-8a50-235a06b53003", "slug": "gpt-5-2-codex", "name": "GPT-5.2 Codex (xhigh)", "shortName": "GPT-5.2 Codex (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-11", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-2-codex", "name": "GPT-5.2 Codex"}, "deprecated": true, "deprecatedTo": "gpt-5-3-codex", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 28.5016971971953, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -2.16666666666667, "omniscienceBreakdown": {"accuracy": 0.4106666666666667, "hallucinationRate": 0.7335972850678733}, "gdpval": null, "itBenchSre": null, "tau2": 0.921052631578947, "tauBanking": null, "terminalbenchHard": 0.371212121212121, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.823333333333333, "ifbench": 0.776190476190476, "hle": 0.357275254865616, "gpqa": 0.898989898989899, "critpt": 0.0866938775510204, "apexAgents": null, "mmmuPro": 0.763005780346821, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.75, "price1mOutputTokens": 14, "cacheHitPrice": 0.175, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4.8125, "price1mBlended7To2To1": 1.8725, "price1mBlended0To1To1": 7.875, "price1mBlended100To1To1": 0.32598039215686275, "price1mBlended0To100To1": 1.8712871287128714, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "021b1b31-d2fc-4653-ab74-c10bd2f41c8e", "slug": "qwen3-5-122b-a10b-non-reasoning", "name": "Qwen3.5 122B A10B (Non-reasoning)", "shortName": "Qwen3.5 122B A10B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-24", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-5-122b-a10b", "name": "Qwen3.5 122B A10B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 125, "inferenceParametersActiveBillions": 10, "sizeClass": "medium", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B", "microevalsEnabled": false, "intelligenceIndex": 17.7480154665397, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.9666666666667, "omniscienceBreakdown": {"accuracy": 0.19116666666666668, "hallucinationRate": 0.9159282917782815}, "gdpval": 833.05, "gdpvalNormalized": 0.16652499999999998, "itBenchSre": null, "tau2": 0.845029239766082, "tauBanking": 0.103092783505155, "terminalbenchHard": 0.295454545454545, "terminalBench21": 0.471910112359551, "terminalBench40": null, "scicode": null, "lcr": 0.613333333333333, "ifbench": 0.508163265306122, "hle": 0.159406858202039, "gpqa": 0.827272727272727, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": 0.702890173410405, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.4, "price1mOutputTokens": 3.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.41, "price1mBlended0To3To1": 1.1, "price1mBlended7To2To1": 0.68, "price1mBlended0To1To1": 1.8, "price1mBlended100To1To1": 0.4274509803921569, "price1mBlended0To100To1": 0.42772277227722777, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 140.803711166391, "medianTimeToFirstChunk": 2.32729853799992}, "outputSpeedVariance": {"p05": 106.5379194788, "q25": 128.027416901503, "median": 140.803711166391, "q75": 153.393003692105, "p95": 171.011888091758}, "timeToFirstChunkVariance": {"p05": 2.26598184929999, "q25": 2.29120493250003, "median": 2.32729853799992, "q75": 2.54884154999997, "p95": 2.69563630490003}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 144.256092049239, "medianTimeToFirstChunk": 1.04996428299999, "medianTimeToFirstAnswerToken": 1.04996428299999, "medianEndToEndResponseTime": 4.516022408499015}, "long": {"medianOutputSpeed": 140.803711166391, "medianTimeToFirstChunk": 2.32729853799992, "medianTimeToFirstAnswerToken": 2.32729853799992, "medianEndToEndResponseTime": 5.878341304260097}, "hundredK": {"medianOutputSpeed": 155.607823844995, "medianTimeToFirstChunk": 19.228959253, "medianTimeToFirstAnswerToken": 19.228959253, "medianEndToEndResponseTime": 22.442165296534565}, "mediumParallel": {"medianOutputSpeed": 136.682305085642, "medianTimeToFirstChunk": 1.0728622465001, "medianTimeToFirstAnswerToken": 1.0728622465001, "medianEndToEndResponseTime": 4.7309802427302}}, "endToEndResponseTime": {"input": 2.32729853799992, "reasoning": 0, "answer": 3.5510427662601765, "total": 5.878341304260097}, "timeToFirstAnswerToken": {"input": 2.32729853799992, "reasoning": 0, "total": 2.32729853799992}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "025ec6b6-df4a-449f-9a03-24e4388d6863", "slug": "gemma-4-12b-non-reasoning", "name": "Gemma 4 12B (Non-reasoning)", "shortName": "Gemma 4 12B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-03", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-4-12b", "name": "Gemma 4 12B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 12, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-4-12B-it", "microevalsEnabled": false, "intelligenceIndex": 9.37989472421056, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -52.8, "omniscienceBreakdown": {"accuracy": 0.11883333333333333, "hallucinationRate": 0.7340646869680348}, "gdpval": null, "itBenchSre": null, "tau2": 0.318713450292398, "tauBanking": null, "terminalbenchHard": 0.113636363636364, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.35, "ifbench": 0.451700680272109, "hle": 0.0634847080630213, "gpqa": 0.660606060606061, "critpt": 0, "apexAgents": null, "mmmuPro": 0.619653179190751, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15000000000000002, "price1mBlended7To2To1": 0.12000000000000002, "price1mBlended0To1To1": 0.2, "price1mBlended100To1To1": 0.10196078431372549, "price1mBlended0To100To1": 0.10198019801980199, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 108.464233372756, "medianTimeToFirstChunk": 2.40063595399999}, "outputSpeedVariance": {"p05": 89.9454382592033, "q25": 98.4637695793243, "median": 108.464233372756, "q75": 121.919927393681, "p95": 133.294934138452}, "timeToFirstChunkVariance": {"p05": 2.23278717080004, "q25": 2.34363153349994, "median": 2.40063595399999, "q75": 2.49801602750008, "p95": 2.92706252730003}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 130.648170250593, "medianTimeToFirstChunk": 1.37614842200003, "medianTimeToFirstAnswerToken": 1.37614842200003, "medianEndToEndResponseTime": 5.2032207724276125}, "long": {"medianOutputSpeed": 108.464233372756, "medianTimeToFirstChunk": 2.40063595399999, "medianTimeToFirstAnswerToken": 2.40063595399999, "medianEndToEndResponseTime": 7.010450493339091}, "hundredK": {"medianOutputSpeed": 45.2131854794271, "medianTimeToFirstChunk": 13.8618395584999, "medianTimeToFirstAnswerToken": 13.8618395584999, "medianEndToEndResponseTime": 24.92056047581969}, "mediumParallel": {"medianOutputSpeed": 118.422726759421, "medianTimeToFirstChunk": 2.00902238900006, "medianTimeToFirstAnswerToken": 2.00902238900006, "medianEndToEndResponseTime": 6.231184922174656}}, "endToEndResponseTime": {"input": 2.40063595399999, "reasoning": 0, "answer": 4.6098145393391015, "total": 7.010450493339091}, "timeToFirstAnswerToken": {"input": 2.40063595399999, "reasoning": 0, "total": 2.40063595399999}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "033ade17-d9ec-44e0-b792-b5f1fcd5ab4c", "slug": "gemini-3-5-flash-minimal", "name": "Gemini 3.5 Flash (minimal)", "shortName": "Gemini 3.5 Flash (minimal)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-19", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "effort": {"slug": "minimal", "label": "minimal", "level": 10}, "release": {"slug": "gemini-3-5-flash", "name": "Gemini 3.5 Flash"}, "deprecated": true, "deprecatedTo": "gemini-3-7-flash-minimal", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 23.848790860577, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 0.666666666666667, "omniscienceBreakdown": {"accuracy": 0.43016666666666664, "hallucinationRate": 0.7431997660134543}, "gdpval": null, "itBenchSre": null, "tau2": 0.587719298245614, "tauBanking": null, "terminalbenchHard": 0.462121212121212, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.613333333333333, "ifbench": 0.472789115646259, "hle": 0.240963855421687, "gpqa": 0.828282828282828, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": 0.801156069364162, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.5, "price1mOutputTokens": 9, "cacheHitPrice": 0.15, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3.375, "price1mBlended7To2To1": 1.3050000000000002, "price1mBlended0To1To1": 5.25, "price1mBlended100To1To1": 0.25, "price1mBlended0To100To1": 1.5742574257425743, "timescaleData": {"medianOutputSpeed": 221.962498668663, "medianTimeToFirstChunk": 0.883517405500015}, "outputSpeedVariance": {"p05": 155.66680459937, "q25": 176.427845355178, "median": 221.962498668663, "q75": 243.408015840569, "p95": 260.892569096363}, "timeToFirstChunkVariance": {"p05": 0.702287913249995, "q25": 0.761413370249926, "median": 0.883517405500015, "q75": 0.974085892750025, "p95": 3.23484768519999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 231.562282662624, "medianTimeToFirstChunk": 0.730467440999973, "medianTimeToFirstAnswerToken": 0.730467440999973, "medianEndToEndResponseTime": 2.8897137321089525}, "long": {"medianOutputSpeed": 221.962498668663, "medianTimeToFirstChunk": 0.883517405500015, "medianTimeToFirstAnswerToken": 0.883517405500015, "medianEndToEndResponseTime": 3.1361501835549266}, "hundredK": {"medianOutputSpeed": 239.177249438581, "medianTimeToFirstChunk": 1.88881545799995, "medianTimeToFirstAnswerToken": 1.88881545799995, "medianEndToEndResponseTime": 3.9793152909633545}, "mediumParallel": {"medianOutputSpeed": 207.943871525324, "medianTimeToFirstChunk": 0.743870443000106, "medianTimeToFirstAnswerToken": 0.743870443000106, "medianEndToEndResponseTime": 3.1483654460620674}}, "endToEndResponseTime": {"input": 0.883517405500015, "reasoning": 0, "answer": 2.252632778054912, "total": 3.1361501835549266}, "timeToFirstAnswerToken": {"input": 0.883517405500015, "reasoning": 0, "total": 0.883517405500015}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "033e4aa9-a556-4224-87b0-341ed1070257", "slug": "claude-3-5-haiku", "name": "Claude 3.5 Haiku", "shortName": "Claude 3.5 Haiku", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-10-22", "knowledgeCutoffDate": "2024-07-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-3-5-haiku", "name": "Claude 3.5 Haiku"}, "deprecated": true, "deprecatedTo": "claude-4-5-haiku", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.938372415746, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -22.5166666666667, "omniscienceBreakdown": {"accuracy": 0.132, "hallucinationRate": 0.41148233486943164}, "gdpval": 407.74, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.245614035087719, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": 0.101123595505618, "terminalBench40": null, "scicode": null, "lcr": 0.273333333333333, "ifbench": 0.427891156462585, "hle": 0.0363, "gpqa": 0.408080808080808, "critpt": 0, "apexAgents": null, "mmmuPro": 0.45606936416185, "livecodebench": 0.314285714285714, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "037dec2f-51e8-4127-a1f1-85155dae7a1d", "slug": "gpt-35-turbo", "name": "GPT-3.5 Turbo", "shortName": "GPT-3.5 Turbo", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2022-11-30", "knowledgeCutoffDate": "2021-09-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-3-5-turbo", "name": "GPT-3.5 Turbo"}, "deprecated": true, "deprecatedTo": "gpt-4", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 4096, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.48558234391291, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": 0.296969696969697, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.5, "price1mOutputTokens": 1.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.75, "price1mBlended7To2To1": 0.6, "price1mBlended0To1To1": 1, "price1mBlended100To1To1": 0.5098039215686274, "price1mBlended0To100To1": 0.5099009900990099, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0399e614-5d46-484f-9183-e4f32d74e1c6", "slug": "gemini-2-0-flash-thinking-exp-0121", "name": "Gemini 2.0 Flash Thinking Experimental (Jan '25)", "shortName": "Gemini 2.0 Flash Thinking exp. (Jan)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-21", "knowledgeCutoffDate": "2024-08-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-2-0-flash-thinking-exp-0121", "name": "Gemini 2.0 Flash Thinking Experimental (Jan '25)"}, "deprecated": true, "deprecatedTo": "gemini-2-5-flash-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.41808559069261, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0635, "gpqa": 0.701010101010101, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.320634920634921, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": true, "outputModalitySpeech": true, "outputModalityVideo": false}, {"id": "04586102-6a28-48f8-a82e-85775d7ed779", "slug": "qwen2-5-coder-32b-instruct", "name": "Qwen2.5 Coder Instruct 32B", "shortName": "Qwen2.5 Coder 32B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-11-11", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen2-5-coder-32b-instruct", "name": "Qwen2.5 Coder Instruct 32B"}, "deprecated": true, "deprecatedTo": "qwen3-32b-instruct", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 6.74052379746597, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0351, "gpqa": 0.417171717171717, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.295238095238095, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "04751bd4-0c5d-416b-a5f2-83727c5bfcda", "slug": "sonar-reasoning", "name": "Sonar Reasoning", "shortName": "Sonar Reasoning", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "sonar-reasoning", "name": "Sonar Reasoning"}, "deprecated": true, "deprecatedTo": "sonar-reasoning-pro", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 127000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.6724759846559, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": 0.623232323232323, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "941fc0f0-1d4e-405a-95b2-2d49494e0e6c", "slug": "perplexity", "name": "Perplexity", "logo": "/img/logos/perplexity.svg", "color": "#1B818E", "country": "us", "url": "https://perplexity.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "04781a0e-40f0-4e2a-a4e5-18e389364a79", "slug": "gemma-3-270m", "name": "Gemma 3 270M", "shortName": "Gemma 3 270M", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-14", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-3-270m", "name": "Gemma 3 270M"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 0.268, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "Gemma license", "licenseUrl": "https://ai.google.dev/gemma/terms", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-3-270m", "microevalsEnabled": false, "intelligenceIndex": 5.11705960692171, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -29.2666666666667, "omniscienceBreakdown": {"accuracy": 0.008833333333333334, "hallucinationRate": 0.30418698503447117}, "gdpval": null, "itBenchSre": null, "tau2": 0.0906432748538012, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.12108843537415, "hle": 0.036144578313253, "gpqa": 0.224242424242424, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.00317460317460317, "aime25": 0.0233333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "04787c2b-0751-4269-8029-075b727d7aed", "slug": "grok-4-20-0309", "name": "Grok 4.20 0309 (Reasoning)", "shortName": "Grok 4.20 0309", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "grok-4-20-0309", "name": "Grok 4.20 0309"}, "deprecated": true, "deprecatedTo": "grok-4-20", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 25.2162736582441, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 12.95, "omniscienceBreakdown": {"accuracy": 0.28883333333333333, "hallucinationRate": 0.22404499648464965}, "gdpval": null, "itBenchSre": null, "tau2": 0.964912280701754, "tauBanking": null, "terminalbenchHard": 0.409090909090909, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.676666666666667, "ifbench": 0.829251700680272, "hle": 0.323911028730306, "gpqa": 0.884848484848485, "critpt": 0.06, "apexAgents": 0.14233038348082597, "mmmuPro": 0.731791907514451, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.514, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.1400000000000001, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 0.27450980392156865, "price1mBlended0To100To1": 2.0396039603960396, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "04d023f3-025c-4d78-9571-53edda3eaf2a", "slug": "gpt-5-1-codex", "name": "GPT-5.1 Codex (high)", "shortName": "GPT-5.1 Codex (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-13", "knowledgeCutoffDate": "2024-09-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5-1-codex", "name": "GPT-5.1 Codex"}, "deprecated": true, "deprecatedTo": "gpt-5-2-codex", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 23.6972790075055, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -6.5, "omniscienceBreakdown": {"accuracy": 0.399, "hallucinationRate": 0.7720465890183028}, "gdpval": null, "itBenchSre": null, "tau2": 0.830409356725146, "tauBanking": null, "terminalbenchHard": 0.348484848484849, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.693333333333333, "ifbench": 0.7, "hle": 0.257182576459685, "gpqa": 0.85959595959596, "critpt": 0.0571428571428571, "apexAgents": null, "mmmuPro": 0.72485549132948, "livecodebench": 0.848677248677249, "aime25": 0.956666666666667, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 2.125, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 1.3357843137254901, "price1mBlended0To100To1": 1.3366336633663367, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "04ee6719-0327-463b-a1a1-70a6a78254f9", "slug": "muse-spark-1-2", "name": "Muse Spark 1.2 (xhigh)", "shortName": "Muse Spark 1.2 (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-05", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "muse-spark-1-2", "name": "Muse Spark 1.2"}, "deprecated": true, "deprecatedTo": "muse-spark-1-3-xhigh", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1048576, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 39.8039107970943, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 44.65628198839838, "strategyAndOps": 43.205521490734384, "legal": 47.0750219472539, "healthcareAndMedical": 44.082991607569426, "engineering": 41.798162634152995, "economics": 53.15819033827617}, "omniscience": 27.2, "omniscienceBreakdown": {"accuracy": 0.4538333333333333, "hallucinationRate": 0.3329264571254196}, "mlcrOverall": 0.311111111111111, "gdpPdfAllPass": 0.174, "gdpval": 1523.32, "gdpvalNormalized": 0.51166, "itBenchSre": null, "tau2": null, "tauBanking": 0.348453608247423, "terminalbenchHard": null, "terminalBench21": 0.801498127340824, "terminalBench40": 0.0707070707070707, "scicode": 0.574074074074074, "lcr": 0.79, "ifbench": null, "hle": 0.454587581093605, "gpqa": 0.904040404040404, "critpt": 0.177142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.4061337838423964, "enterpriseOpsGym": 0.4726947179946285, "price1mInputTokens": 1.25, "price1mOutputTokens": 4.25, "cacheHitPrice": 0.15, "cacheHitDiscountPercent": 0.88, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2, "price1mBlended7To2To1": 0.78, "price1mBlended0To1To1": 2.75, "price1mBlended100To1To1": 0.20098039215686275, "price1mBlended0To100To1": 1.2797029702970297, "intelligenceIndexTimePerTask": 241.9089238266331, "intelligenceIndexCost": {"total": 1385.40074776, "input": 851.85285351, "nonCacheInput": 32.32779875, "cacheRead": 498.4701046349999, "cacheWrite": 321.0549501250001, "output": 533.54789425, "reasoning": 389.5471375, "answer": 144.00075675}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.9746948879931989, "input": 0.7712283726084276, "nonCacheInput": 0.02279531757313043, "cacheRead": 0.47682765660031157, "cacheWrite": 0.27160539843498555, "output": 0.2034665153847713, "reasoning": 0.09630674815054069, "answer": 0.1071597672342306}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.28464733139010995}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.08796960808863637}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.025590856380136986}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.4984427495000001}, {"slug": "scicode", "weightedCostPerTask": 0.00604795251736111}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.010062393060704354}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.019130218249999997}, {"slug": "critpt", "weightedCostPerTask": 0.03457536}, {"slug": "omniscience", "weightedCostPerTask": 0.0015681879312499998}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.006660230875}]}, "canonicalIntelligenceIndexTokenCount": {"input": 3605840230, "output": 125540681, "answer": 33882531, "reasoning": 91658150}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 22660.411329538983, "answer": 25214.06287864249, "output": 47874.47420818148}, "briefcaseBreakdown": {"overall": {"elo": 1343.5, "lower95ci": 1337.23, "upper95ci": 1350.78}, "rubricPassRate": 0.45151515151515154, "analyticalQuality": {"elo": 1392.05, "lower95ci": 1379.65, "upper95ci": 1405.49}, "presentation": {"elo": 1334.32, "lower95ci": 1322.11, "upper95ci": 1346.21}}, "briefcaseTotalCost": 172.68604771000003, "timescaleData": {"medianOutputSpeed": 207.906781841771, "medianTimeToFirstChunk": 14.904570012}, "outputSpeedVariance": {"p05": 112.578992829779, "q25": 173.50167177397, "median": 207.906781841771, "q75": 326.910890564034, "p95": 384.699286629098}, "timeToFirstChunkVariance": {"p05": 7.44681807850002, "q25": 10.601831481, "median": 14.904570012, "q75": 23.04881363, "p95": 36.871951736}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 256.965332938138, "medianTimeToFirstChunk": 11.6985669769999, "medianTimeToFirstAnswerToken": 19.48171802361007, "medianEndToEndResponseTime": 21.427505785262614}, "long": {"medianOutputSpeed": 207.906781841771, "medianTimeToFirstChunk": 14.904570012, "medianTimeToFirstAnswerToken": 24.524265830879614, "medianEndToEndResponseTime": 26.929189785599515}, "hundredK": {"medianOutputSpeed": 323.730727067231, "medianTimeToFirstChunk": 14.272084437, "medianTimeToFirstAnswerToken": 20.45005839121365, "medianEndToEndResponseTime": 21.99455187976706}, "mediumParallel": {"medianOutputSpeed": 196.094148776521, "medianTimeToFirstChunk": 10.4111545009998, "medianTimeToFirstAnswerToken": 20.610336947179277, "medianEndToEndResponseTime": 23.16013255872415}}, "endToEndResponseTime": {"input": 14.904570012, "reasoning": 9.619695818879611, "answer": 2.404923954719903, "total": 26.929189785599515}, "timeToFirstAnswerToken": {"input": 14.904570012, "reasoning": 9.619695818879611, "total": 24.524265830879614}, "performanceDataSource": {"type": "firstParty", "providerName": "Meta"}, "hostModelCount": 2, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "050c61cd-cddc-463a-a30a-a82aaa37be59", "slug": "gpt-5-6-luna-low", "name": "GPT-5.6 Luna (low)", "shortName": "GPT-5.6 Luna (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gpt-5-6-luna", "name": "GPT-5.6 Luna"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 21.5456033424265, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 23.75315400078851, "strategyAndOps": 22.52400566668051, "legal": 24.601034884429556, "healthcareAndMedical": 20.51395278297947, "engineering": 23.205541116112798, "economics": 28.527675104263185}, "omniscience": -14.65, "omniscienceBreakdown": {"accuracy": 0.39616666666666667, "hallucinationRate": 0.8987027325420922}, "mlcrOverall": 0.0611111111111111, "gdpPdfAllPass": 0.142, "gdpval": 1075.16, "gdpvalNormalized": 0.28758000000000006, "itBenchSre": null, "tau2": null, "tauBanking": 0.127835051546392, "terminalbenchHard": null, "terminalBench21": 0.434456928838951, "terminalBench40": 0, "scicode": 0.460648148148148, "lcr": 0.7, "ifbench": null, "hle": 0.198331788693234, "gpqa": 0.835353535353535, "critpt": 0.0257142857142857, "apexAgents": null, "mmmuPro": 0.739884393063584, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.11692162258271627, "price1mInputTokens": 0.2, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.02, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.25, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.45, "price1mBlended7To2To1": 0.174, "price1mBlended0To1To1": 0.7, "price1mBlended100To1To1": 0.03333333333333334, "price1mBlended0To100To1": 0.2099009900990099, "intelligenceIndexTimePerTask": 24.135089482622774, "intelligenceIndexCost": {"total": 27.020226781529374, "input": 14.877708781529375, "nonCacheInput": 5.5958482, "cacheRead": 3.5442781668235326, "cacheWrite": 5.737582414705842, "output": 12.142517999999999, "reasoning": 6.1705152, "answer": 5.9720028}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.009827249754655997, "input": 0.006810324749469599, "nonCacheInput": 0.004303583115768349, "cacheRead": 0.0008072532149511116, "cacheWrite": 0.001699488418750139, "output": 0.0030169250051863983, "reasoning": 0.0006704943091965392, "answer": 0.00234643069598986}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.0018783697328211273}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0008156248257822373}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.000856311462070063}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.001179994316105567}, {"slug": "scicode", "weightedCostPerTask": 0.00014673875}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0001440088785912882}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0034076668}, {"slug": "critpt", "weightedCostPerTask": 0.00036740971428571436}, {"slug": "omniscience", "weightedCostPerTask": 7.3635675e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0009574896000000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 228143479, "output": 10118765, "answer": 4976669, "reasoning": 5142096}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 558.7452576637828, "answer": 1955.358913324883, "output": 2514.104170988666}, "briefcaseBreakdown": {"overall": {"elo": 743.81, "lower95ci": 734.84, "upper95ci": 752.42}, "rubricPassRate": 0.13079299691040164, "analyticalQuality": {"elo": 597.87, "lower95ci": 580.96, "upper95ci": 614.07}, "presentation": {"elo": 879.82, "lower95ci": 866.48, "upper95ci": 896.27}}, "briefcaseTotalCost": 1.1395443045781506, "timescaleData": {"medianOutputSpeed": 103.932453563994, "medianTimeToFirstChunk": 2.19333649399994}, "outputSpeedVariance": {"p05": 79.4716927833675, "q25": 93.2306584990193, "median": 103.932453563994, "q75": 125.856317266328, "p95": 167.0898520251}, "timeToFirstChunkVariance": {"p05": 1.45332912835011, "q25": 1.64708326849996, "median": 2.19333649399994, "q75": 3.14406705600015, "p95": 3.9022351555}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 113.820745561218, "medianTimeToFirstChunk": 1.82867960300001, "medianTimeToFirstAnswerToken": 1.82867960300001, "medianEndToEndResponseTime": 6.221551900002116}, "long": {"medianOutputSpeed": 103.932453563994, "medianTimeToFirstChunk": 2.19333649399994, "medianTimeToFirstAnswerToken": 2.19333649399994, "medianEndToEndResponseTime": 7.004153354896393}, "hundredK": {"medianOutputSpeed": 121.871376117387, "medianTimeToFirstChunk": 2.25674499849999, "medianTimeToFirstAnswerToken": 2.25674499849999, "medianEndToEndResponseTime": 6.359431092061435}, "mediumParallel": {"medianOutputSpeed": 108.741774293024, "medianTimeToFirstChunk": 2.7325951235, "medianTimeToFirstAnswerToken": 2.7325951235, "medianEndToEndResponseTime": 7.330644063299909}}, "endToEndResponseTime": {"input": 2.19333649399994, "reasoning": 0, "answer": 4.810816860896453, "total": 7.004153354896393}, "timeToFirstAnswerToken": {"input": 2.19333649399994, "reasoning": 0, "total": 2.19333649399994}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "05776db7-f5c0-40f7-b824-079160f8cfa8", "slug": "claude-fable-5-1-low", "name": "Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)", "shortName": "Claude Fable 5.1 (low with fallback)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "claude-fable-5-1", "name": "Claude Fable 5.1"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 47.0391672014862, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 49.04848646056599, "strategyAndOps": 51.60260866548881, "legal": 53.764822531797805, "engineering": 48.97817778707237, "economics": 55.401479861754716}, "omniscience": 34.1333333333333, "omniscienceBreakdown": {"accuracy": 0.6023333333333334, "hallucinationRate": 0.6563285834031852}, "harveyLab": 0.923288464321899, "gdpPdfAllPass": 0.28, "gdpval": 1503.72, "gdpvalNormalized": 0.50186, "itBenchSre": null, "tau2": null, "tauBanking": 0.389690721649485, "terminalbenchHard": null, "terminalBench21": 0.850187265917603, "terminalBench40": 0.404040404040404, "scicode": 0.56712962962963, "lcr": 0.823333333333333, "ifbench": null, "hle": 0.48887859128823, "gpqa": 0.880808080808081, "critpt": 0.277142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.522404059498186, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.975, "cacheWritePrice": 12.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.175, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 245.15966981775648, "intelligenceIndexCost": {"total": 3157.6632471925045, "input": 1551.7684570879546, "nonCacheInput": 349.925614093125, "cacheRead": 311.11079576616146, "cacheWrite": 890.7320472286683, "output": 1605.8947901045499, "reasoning": 572.5184255392, "answer": 1033.3763645653498}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.371025320183763, "input": 1.2950064810231467, "nonCacheInput": 0.25564665107881146, "cacheRead": 0.3711607001287225, "cacheWrite": 0.6681991298156129, "output": 1.076018839160616, "reasoning": 0.4140716302258042, "answer": 0.6619472089348118}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 1.0081955282831103}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.1426701374481728}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0758105973421492}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.7323980999332493}, {"slug": "scicode", "weightedCostPerTask": 0.006897253472222223}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.012383309694852412}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.19233032}, {"slug": "critpt", "weightedCostPerTask": 0.12559421428571427}, {"slug": "omniscience", "weightedCostPerTask": 0.0012967197242922499}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.07344914}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1338003902, "output": 32508373, "answer": 20845317, "reasoning": 11663056}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 8289.274270012003, "answer": 13272.568454756867, "output": 21561.84272476887}, "briefcaseBreakdown": {"overall": {"elo": 1483.73, "lower95ci": 1475.72, "upper95ci": 1491.57}, "rubricPassRate": 0.5535353535353535, "analyticalQuality": {"elo": 1723.19, "lower95ci": 1707.7, "upper95ci": 1738.47}, "presentation": {"elo": 1278.4, "lower95ci": 1262.79, "upper95ci": 1293.33}}, "briefcaseTotalCost": 611.6386204917536, "timescaleData": {"medianOutputSpeed": 54.4569637558875, "medianTimeToFirstChunk": 5.04397649449998}, "outputSpeedVariance": {"p05": 41.0852994556774, "q25": 46.1619891374107, "median": 54.4569637558875, "q75": 64.7176594252389, "p95": 75.5856518332628}, "timeToFirstChunkVariance": {"p05": 3.01761328635, "q25": 4.49486042675002, "median": 5.04397649449998, "q75": 7.84685268924999, "p95": 19.7629255844501}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 54.4078253126972, "medianTimeToFirstChunk": 5.28434891950005, "medianTimeToFirstAnswerToken": 5.28434891950005, "medianEndToEndResponseTime": 14.474203451019335}, "long": {"medianOutputSpeed": 54.4569637558875, "medianTimeToFirstChunk": 5.04397649449998, "medianTimeToFirstAnswerToken": 5.04397649449998, "medianEndToEndResponseTime": 14.225538695458045}, "hundredK": {"medianOutputSpeed": 63.4689778094914, "medianTimeToFirstChunk": 10.6495360755, "medianTimeToFirstAnswerToken": 10.6495360755, "medianEndToEndResponseTime": 18.527400463056406}, "mediumParallel": {"medianOutputSpeed": 52.9497569269744, "medianTimeToFirstChunk": 6.75150794599999, "medianTimeToFirstAnswerToken": 6.75150794599999, "medianEndToEndResponseTime": 16.194421927447998}}, "endToEndResponseTime": {"input": 5.04397649449998, "reasoning": 0, "answer": 9.181562200958064, "total": 14.225538695458045}, "timeToFirstAnswerToken": {"input": 5.04397649449998, "reasoning": 0, "total": 5.04397649449998}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "05a32e26-e609-4377-951b-8fa23d329926", "slug": "mistral-medium-3-1", "name": "Mistral Medium 3.1", "shortName": "Mistral Medium 3.1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-12", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-medium-3-1", "name": "Mistral Medium 3.1"}, "deprecated": true, "deprecatedTo": "mistral-medium-3-5", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.53417902519296, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 9.117023417252936, "strategyAndOps": 8.528876472350865, "legal": 10.007216096386658, "engineering": 10.943038924930493, "economics": 13.912674158171146}, "omniscience": -46.2833333333333, "omniscienceBreakdown": {"accuracy": 0.2075, "hallucinationRate": 0.8458464773922187}, "gdpPdfAllPass": 0.012, "gdpval": 536.15, "gdpvalNormalized": 0.018074999999999987, "itBenchSre": null, "tau2": 0.406432748538012, "tauBanking": 0.0824742268041237, "terminalbenchHard": 0.106060606060606, "terminalBench21": 0.138576779026217, "terminalBench40": 0, "scicode": 0.324074074074074, "lcr": 0.426666666666667, "ifbench": 0.397959183673469, "hle": 0.0468025949953661, "gpqa": 0.587878787878788, "critpt": 0, "apexAgents": null, "mmmuPro": 0.541618497109827, "livecodebench": 0.406349206349206, "aime25": 0.383333333333333, "analystAgent": null, "automationBenchPartialScore": 0.04146227762526245, "price1mInputTokens": 0.4, "price1mOutputTokens": 2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.535, "price1mBlended0To3To1": 0.8, "price1mBlended7To2To1": 0.56, "price1mBlended0To1To1": 1.2, "price1mBlended100To1To1": 0.4156862745098039, "price1mBlended0To100To1": 0.4158415841584158, "intelligenceIndexTimePerTask": 93.6992149353388, "intelligenceIndexCost": {"total": 405.8702124, "input": 370.15170040000004, "nonCacheInput": 7.3556528000000005, "cacheRead": 0, "cacheWrite": 362.79604760000007, "output": 35.718512, "reasoning": 0, "answer": 35.718512}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.39219786538109047, "input": 0.3658099186240063, "nonCacheInput": 0.004538321285055976, "cacheRead": 0, "cacheWrite": 0.3612715973389503, "output": 0.02638794675708419, "reasoning": 0, "answer": 0.02638794675708419}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.09231191736263737}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.021757906909090907}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.008381153637747338}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.2638380096969697}, {"slug": "scicode", "weightedCostPerTask": 0.00018749722222222224}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0004427631881371641}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0023020608000000006}, {"slug": "critpt", "weightedCostPerTask": 0.0007732097142857143}, {"slug": "omniscience", "weightedCostPerTask": 1.036805e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0021929788000000006}]}, "canonicalIntelligenceIndexTokenCount": {"input": 925379251, "output": 17859256, "answer": 17859256, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 13193.973378542094, "output": 13193.973378542094}, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 538.05, "lower95ci": 528.75, "upper95ci": 546.37}, "rubricPassRate": 0.1303030303030303, "analyticalQuality": {"elo": 336.5, "lower95ci": 318.11, "upper95ci": 353.85}, "presentation": {"elo": 518.73, "lower95ci": 501.59, "upper95ci": 535.5}}, "briefcaseTotalCost": 56.002563200000004, "timescaleData": {"medianOutputSpeed": 138.497426338393, "medianTimeToFirstChunk": 2.21166616450002}, "outputSpeedVariance": {"p05": 72.5924335088956, "q25": 106.449597374689, "median": 138.497426338393, "q75": 161.633310232337, "p95": 184.795161464882}, "timeToFirstChunkVariance": {"p05": 2.11777384360005, "q25": 2.15996779124995, "median": 2.21166616450002, "q75": 2.50131444975003, "p95": 4.5941808532}, "performanceByPromptType": {"long": {"medianOutputSpeed": 138.497426338393, "medianTimeToFirstChunk": 2.21166616450002, "medianTimeToFirstAnswerToken": 2.21166616450002, "medianEndToEndResponseTime": 5.821841553451595}}, "endToEndResponseTime": {"input": 2.21166616450002, "reasoning": 0, "answer": 3.6101753889515744, "total": 5.821841553451595}, "timeToFirstAnswerToken": {"input": 2.21166616450002, "reasoning": 0, "total": 2.21166616450002}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "05e45a36-b5c6-47a1-8adb-9ddc19add5b3", "slug": "gpt-5-nano-minimal", "name": "GPT-5 nano (minimal)", "shortName": "GPT-5 nano (minimal)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-05-30", "isReasoning": false, "reasoningTokens": 0, "effort": {"slug": "minimal", "label": "minimal", "level": 10}, "release": {"slug": "gpt-5-nano", "name": "GPT-5 nano"}, "deprecated": true, "deprecatedTo": "gpt-5-4-nano-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.08879356535892, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -64.0666666666667, "omniscienceBreakdown": {"accuracy": 0.13083333333333333, "hallucinationRate": 0.8876318312559923}, "gdpval": null, "itBenchSre": null, "tau2": 0.257309941520468, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.2, "ifbench": 0.325170068027211, "hle": 0.0398517145505097, "gpqa": 0.428282828282828, "critpt": 0, "apexAgents": null, "mmmuPro": 0.317919075144509, "livecodebench": 0.46984126984127, "aime25": 0.273333333333333, "analystAgent": null, "price1mInputTokens": 0.05, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.005, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.13, "price1mBlended0To3To1": 0.1375, "price1mBlended7To2To1": 0.053500000000000006, "price1mBlended0To1To1": 0.225, "price1mBlended100To1To1": 0.009313725490196078, "price1mBlended0To100To1": 0.05346534653465347, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 147.643604575912, "medianTimeToFirstChunk": 0.915346703999944}, "outputSpeedVariance": {"p05": 108.443880440344, "q25": 137.877222060043, "median": 147.643604575912, "q75": 170.384793812072, "p95": 202.129473845837}, "timeToFirstChunkVariance": {"p05": 0.758663924899906, "q25": 0.845070323249956, "median": 0.915346703999944, "q75": 1.10655501950004, "p95": 1.46914285934999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 147.643604575912, "medianTimeToFirstChunk": 0.915346703999944, "medianTimeToFirstAnswerToken": 0.915346703999944, "medianEndToEndResponseTime": 4.30188011624078}}, "endToEndResponseTime": {"input": 0.915346703999944, "reasoning": 0, "answer": 3.386533412240836, "total": 4.30188011624078}, "timeToFirstAnswerToken": {"input": 0.915346703999944, "reasoning": 0, "total": 0.915346703999944}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 3, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "073b5329-c4b3-4f1f-8f97-4753aadf4398", "slug": "gemini-2-5-pro-05-06", "name": "Gemini 2.5 Pro Preview (May' 25)", "shortName": "Gemini 2.5 Pro (May)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-06", "knowledgeCutoffDate": "2025-01-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-pro-05-06", "name": "Gemini 2.5 Pro Preview (May' 25)"}, "deprecated": true, "deprecatedTo": "gemini-2-5-pro", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 14.5215571266208, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.1993, "gpqa": 0.822222222222222, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.77037037037037, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 1.29, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 1.3375, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.3366336633663367, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "076f2674-bc4b-4925-be59-50832eb8c090", "slug": "o3-mini-high", "name": "o3-mini (high)", "shortName": "o3-mini (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-31", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "o3-mini", "name": "o3-mini"}, "deprecated": true, "deprecatedTo": "gpt-5-mini", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 10.9643866525084, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 9.991843975933422, "strategyAndOps": 6.407860819698365, "legal": 11.206432214968626, "engineering": 13.363857142857144, "economics": 16.023999999999997}, "omniscience": -42.5666666666667, "omniscienceBreakdown": {"accuracy": 0.21266666666666667, "hallucinationRate": 0.8107535986452159}, "gdpPdfAllPass": 0.02, "gdpval": 420.79, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.312865497076023, "tauBanking": 0.0515463917525773, "terminalbenchHard": 0.0606060606060606, "terminalBench21": 0.0449438202247191, "terminalBench40": 0, "scicode": 0.428240740740741, "lcr": 0.43, "ifbench": 0.671428571428571, "hle": 0.1204, "gpqa": 0.772727272727273, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.734391534391534, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.005301828617801993, "price1mInputTokens": 1.1, "price1mOutputTokens": 4.4, "cacheHitPrice": 0.55, "cacheHitDiscountPercent": 0.5, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.9250000000000003, "price1mBlended7To2To1": 1.0450000000000002, "price1mBlended0To1To1": 2.75, "price1mBlended100To1To1": 0.5931372549019609, "price1mBlended0To100To1": 1.1326732673267328, "intelligenceIndexTimePerTask": 80.142709479359, "canonicalIntelligenceIndexTokenCount": {"input": 50859424, "output": 68108448, "answer": 5475768, "reasoning": 62632680}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 14188.545062275443, "answer": 2800.558416342179, "output": 16989.103478617624}, "briefcaseBreakdown": {"overall": {"elo": 161.06, "lower95ci": 150.66, "upper95ci": 170.9}, "rubricPassRate": 0.045454545454545456, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 154.58, "lower95ci": 134.53, "upper95ci": 173.55}}, "timescaleData": {"medianOutputSpeed": 223.922509707261, "medianTimeToFirstChunk": 19.230031875}, "outputSpeedVariance": {"p05": 144.292817208534, "q25": 178.488103474075, "median": 223.922509707261, "q75": 249.140893143923, "p95": 295.26207839552}, "timeToFirstChunkVariance": {"p05": 9.53725019654998, "q25": 12.60008616825, "median": 19.230031875, "q75": 28.57835540575, "p95": 99.0658113021}, "performanceByPromptType": {"long": {"medianOutputSpeed": 223.922509707261, "medianTimeToFirstChunk": 19.230031875, "medianTimeToFirstAnswerToken": 19.230031875, "medianEndToEndResponseTime": 21.462947184200765}}, "endToEndResponseTime": {"input": 19.230031875, "reasoning": 0, "answer": 2.2329153092007648, "total": 21.462947184200765}, "timeToFirstAnswerToken": {"input": 19.230031875, "reasoning": 0, "total": 19.230031875}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "078f4dc8-5350-40a2-a5ea-e8359f795b70", "slug": "o1-preview", "name": "o1-preview", "shortName": "o1-preview", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-12", "knowledgeCutoffDate": "2023-10-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "o1-preview", "name": "o1-preview"}, "deprecated": true, "deprecatedTo": "o3", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.3759356934695, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": 0.764646464646465, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": 0.796666666666667, "analystAgent": null, "price1mInputTokens": 16.5, "price1mOutputTokens": 66, "cacheHitPrice": 8.25, "cacheHitDiscountPercent": 0.5, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 28.875, "price1mBlended7To2To1": 15.675, "price1mBlended0To1To1": 41.25, "price1mBlended100To1To1": 8.897058823529411, "price1mBlended0To100To1": 16.99009900990099, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "07c35e00-2b12-44c8-91cc-408629cd569e", "slug": "deepseek-v3-2-0925", "name": "DeepSeek V3.2 Exp (Non-reasoning)", "shortName": "DeepSeek V3.2 Exp (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-29", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v3-2-0925", "name": "DeepSeek V3.2 Exp"}, "deprecated": true, "deprecatedTo": "deepseek-v3-2", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "microevalsEnabled": false, "intelligenceIndex": 13.8833794351459, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -48.2, "omniscienceBreakdown": {"accuracy": 0.22833333333333333, "hallucinationRate": 0.9205183585313175}, "gdpval": null, "itBenchSre": null, "tau2": 0.339181286549708, "tauBanking": null, "terminalbenchHard": 0.25, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.446666666666667, "ifbench": 0.431292517006803, "hle": 0.0903614457831325, "gpqa": 0.738383838383838, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.554497354497354, "aime25": 0.576666666666667, "analystAgent": null, "price1mInputTokens": 0.28, "price1mOutputTokens": 0.42, "cacheHitPrice": 0.028, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.315, "price1mBlended7To2To1": 0.1176, "price1mBlended0To1To1": 0.35, "price1mBlended100To1To1": 0.03431372549019608, "price1mBlended0To100To1": 0.2813861386138614, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 2, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "08242385-ee91-4de6-be7f-271a6d9780ce", "slug": "apodex-1-1", "name": "Apodex 1.1", "shortName": "Apodex 1.1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "apodex-1-1", "name": "Apodex 1.1"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 30.3655647703264, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -21.9, "omniscienceBreakdown": {"accuracy": 0.31683333333333336, "hallucinationRate": 0.7843376433276409}, "gdpval": 1273.14, "gdpvalNormalized": 0.38657, "itBenchSre": null, "tau2": null, "tauBanking": 0.251546391752577, "terminalbenchHard": null, "terminalBench21": 0.696629213483146, "terminalBench40": null, "scicode": 0.454861111111111, "lcr": 0.793333333333333, "ifbench": null, "hle": 0.340593141797961, "gpqa": 0.863636363636364, "critpt": 0.0457142857142857, "apexAgents": 0.311946902654867, "mmmuPro": 0.791907514450867, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 3, "cacheHitPrice": 0.03, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.975, "price1mBlended7To2To1": 0.381, "price1mBlended0To1To1": 1.65, "price1mBlended100To1To1": 0.06176470588235294, "price1mBlended0To100To1": 0.32673267326732675, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Apodex"}, "hostModelCount": 1, "creator": {"id": "904308e3-2682-4750-b66e-d440865eb05f", "slug": "apodex", "name": "Apodex", "logo": "/img/logos/apodex.svg", "color": "#0FD9D2", "country": "us", "url": "https://www.apodex.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0904b596-8932-43bd-9b21-324f128e1723", "slug": "gpt-5-6-sol-low", "name": "GPT-5.6 Sol (low)", "shortName": "GPT-5.6 Sol (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gpt-5-6-sol", "name": "GPT-5.6 Sol"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 33.7979387646002, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 38.59663280607847, "strategyAndOps": 42.367458543368954, "legal": 42.27809054405068, "healthcareAndMedical": 36.1171890139149, "engineering": 34.76788495821448, "economics": 44.5291003822984}, "omniscience": 18.8666666666667, "omniscienceBreakdown": {"accuracy": 0.5716666666666667, "hallucinationRate": 0.8941634241245137}, "mlcrOverall": 0.127777777777778, "gdpPdfAllPass": 0.21, "gdpval": 1354.85, "gdpvalNormalized": 0.42742499999999994, "itBenchSre": null, "tau2": 0.760233918128655, "tauBanking": 0.290721649484536, "terminalbenchHard": 0.606060606060606, "terminalBench21": 0.767790262172285, "terminalBench40": 0.0101010101010101, "scicode": 0.563657407407407, "lcr": 0.78, "ifbench": 0.66530612244898, "hle": 0.393883225208526, "gpqa": 0.897979797979798, "critpt": 0.148571428571429, "apexAgents": null, "mmmuPro": 0.809826589595376, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.4098567011344805, "price1mInputTokens": 4, "price1mOutputTokens": 20, "cacheHitPrice": 0.4, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 8, "price1mBlended7To2To1": 3.08, "price1mBlended0To1To1": 12, "price1mBlended100To1To1": 0.6274509803921569, "price1mBlended0To100To1": 4.158415841584159, "intelligenceIndexTimePerTask": 61.08354433084354, "intelligenceIndexCost": {"total": 637.281597607988, "input": 384.3521176079881, "nonCacheInput": 107.279908, "cacheRead": 111.77645133843583, "cacheWrite": 165.29575826955224, "output": 252.92948, "reasoning": 95.94166, "answer": 156.98782}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.2606419442090313, "input": 0.1811539787500265, "nonCacheInput": 0.08148580908245436, "cacheRead": 0.03976239054446097, "cacheWrite": 0.059905779123111194, "output": 0.07948796545900477, "reasoning": 0.016744731730087704, "answer": 0.06274323372891706}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.0627793796591974}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.026773153256862494}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.023488789598781493}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.05243900018432626}, {"slug": "scicode", "weightedCostPerTask": 0.0024094625}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0022390763670064873}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.06303887600000001}, {"slug": "critpt", "weightedCostPerTask": 0.0075075771428571424}, {"slug": "omniscience", "weightedCostPerTask": 0.0008830555}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.019083574000000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 339320257, "output": 12646474, "answer": 7849391, "reasoning": 4797083}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 837.2365865043852, "answer": 3137.161686445854, "output": 3974.398272950239}, "briefcaseBreakdown": {"overall": {"elo": 1042.06, "lower95ci": 1034.27, "upper95ci": 1050.92}, "rubricPassRate": 0.23939393939393938, "analyticalQuality": {"elo": 969.85, "lower95ci": 956.06, "upper95ci": 984.21}, "presentation": {"elo": 1205.12, "lower95ci": 1189.3, "upper95ci": 1221.66}}, "briefcaseTotalCost": 38.086156993246426, "timescaleData": {"medianOutputSpeed": 65.4393906476627, "medianTimeToFirstChunk": 3.19412595799998}, "outputSpeedVariance": {"p05": 31.9756108712231, "q25": 59.5149622018048, "median": 65.4393906476627, "q75": 76.518214733654, "p95": 106.49199145812}, "timeToFirstChunkVariance": {"p05": 1.80340446820002, "q25": 2.30179779474997, "median": 3.19412595799998, "q75": 4.27448906899998, "p95": 8.02977895114996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 62.8668848386467, "medianTimeToFirstChunk": 2.71918141050001, "medianTimeToFirstAnswerToken": 2.71918141050001, "medianEndToEndResponseTime": 10.672494212355762}, "long": {"medianOutputSpeed": 65.4393906476627, "medianTimeToFirstChunk": 3.19412595799998, "medianTimeToFirstAnswerToken": 3.19412595799998, "medianEndToEndResponseTime": 10.834783901960503}, "hundredK": {"medianOutputSpeed": 83.7941100842483, "medianTimeToFirstChunk": 2.76802057650002, "medianTimeToFirstAnswerToken": 2.76802057650002, "medianEndToEndResponseTime": 8.735027082056195}, "mediumParallel": {"medianOutputSpeed": 54.4966049919603, "medianTimeToFirstChunk": 6.62295743350023, "medianTimeToFirstAnswerToken": 6.62295743350023, "medianEndToEndResponseTime": 15.797840897777746}}, "endToEndResponseTime": {"input": 3.19412595799998, "reasoning": 0, "answer": 7.640657943960523, "total": 10.834783901960503}, "timeToFirstAnswerToken": {"input": 3.19412595799998, "reasoning": 0, "total": 3.19412595799998}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "093883ed-f5fc-443b-8e18-afbfb166699e", "slug": "qwen3-coder-480b-a35b-instruct", "name": "Qwen3 Coder 480B A35B Instruct", "shortName": "Qwen3 Coder 480B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-22", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-coder-480b-a35b-instruct", "name": "Qwen3 Coder 480B A35B Instruct"}, "deprecated": true, "deprecatedTo": "qwen3-coder-next", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 480, "inferenceParametersActiveBillions": 35, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 11.8990256096549, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -22.2, "omniscienceBreakdown": {"accuracy": 0.15683333333333332, "hallucinationRate": 0.4492982802925479}, "gdpval": null, "itBenchSre": null, "tau2": 0.435672514619883, "tauBanking": null, "terminalbenchHard": 0.189393939393939, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.456666666666667, "ifbench": 0.404761904761905, "hle": 0.0454124189063948, "gpqa": 0.618181818181818, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.585185185185185, "aime25": 0.393333333333333, "analystAgent": null, "price1mInputTokens": 1.5, "price1mOutputTokens": 7.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 2.1, "price1mBlended0To1To1": 4.5, "price1mBlended100To1To1": 1.5588235294117647, "price1mBlended0To100To1": 1.5594059405940595, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 51.2974507195324, "medianTimeToFirstChunk": 3.03576110300003}, "outputSpeedVariance": {"p05": 33.1981874878415, "q25": 47.1394320866302, "median": 51.2974507195324, "q75": 61.0639072468461, "p95": 78.3075414690487}, "timeToFirstChunkVariance": {"p05": 2.65463546539983, "q25": 2.84881182300002, "median": 3.03576110300003, "q75": 3.2002847645, "p95": 3.75526177010005}, "performanceByPromptType": {"long": {"medianOutputSpeed": 51.2974507195324, "medianTimeToFirstChunk": 3.03576110300003, "medianTimeToFirstAnswerToken": 3.03576110300003, "medianEndToEndResponseTime": 12.782834163876647}}, "endToEndResponseTime": {"input": 3.03576110300003, "reasoning": 0, "answer": 9.747073060876616, "total": 12.782834163876647}, "timeToFirstAnswerToken": {"input": 3.03576110300003, "reasoning": 0, "total": 3.03576110300003}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 5, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "093b9df2-ebee-4309-943f-5a7e88360adf", "slug": "gemini-3-5-flash-lite", "name": "Gemini 3.5 Flash-Lite", "shortName": "Gemini 3.5 Flash-Lite", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-07-21", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gemini-3-5-flash-lite", "name": "Gemini 3.5 Flash-Lite"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 22.6606674839812, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 24.26750149332541, "strategyAndOps": 23.23652909566923, "legal": 30.922908535903623, "healthcareAndMedical": 23.67824675610797, "engineering": 24.891422612126828, "economics": 32.05086324142723}, "omniscience": 5.23333333333333, "omniscienceBreakdown": {"accuracy": 0.2946666666666667, "hallucinationRate": 0.3435727788279773}, "mlcrOverall": 0.0722222222222222, "gdpPdfAllPass": 0.136, "gdpval": 1063.25, "gdpvalNormalized": 0.281625, "itBenchSre": null, "tau2": null, "tauBanking": 0.175257731958763, "terminalbenchHard": null, "terminalBench21": 0.535580524344569, "terminalBench40": 0.0101010101010101, "scicode": 0.413194444444444, "lcr": 0.76, "ifbench": null, "hle": 0.188137164040778, "gpqa": 0.838383838383838, "critpt": 0, "apexAgents": null, "mmmuPro": 0.790173410404624, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.25011270511840955, "enterpriseOpsGym": 0.423455684870188, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": 0.03, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.331, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.056862745098039215, "price1mBlended0To100To1": 0.3217821782178218, "intelligenceIndexTimePerTask": 45.434200119688164, "intelligenceIndexCost": {"total": 266.9441129366118, "input": 118.25620543661181, "nonCacheInput": 6.5410419, "cacheRead": 30.069722951487574, "cacheWrite": 81.64544058512423, "output": 148.6879075, "reasoning": 122.0987625, "answer": 26.589145}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.12352689651593446, "input": 0.07976014869581427, "nonCacheInput": 0.004420434677479369, "cacheRead": 0.02108940475429524, "cacheWrite": 0.054250309264039676, "output": 0.04376674782012017, "reasoning": 0.026012881416245023, "answer": 0.017753866403875142}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.017996824535402002}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.010441611076120362}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.007077872423235336}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.07064363935811745}, {"slug": "scicode", "weightedCostPerTask": 0.0012601281597222223}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002707601232622799}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0039496541999999996}, {"slug": "critpt", "weightedCostPerTask": 0.007036145285714286}, {"slug": "omniscience", "weightedCostPerTask": 0.0004648802449999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00194854}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1296279040, "output": 59475163, "answer": 10635658, "reasoning": 48839505}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 10405.152566498009, "answer": 7101.546561550058, "output": 17506.699128048065}, "briefcaseBreakdown": {"overall": {"elo": 645.32, "lower95ci": 637.26, "upper95ci": 653.71}, "rubricPassRate": 0.1484848484848485, "analyticalQuality": {"elo": 389.97, "lower95ci": 374.81, "upper95ci": 405.23}, "presentation": {"elo": 757.45, "lower95ci": 741.84, "upper95ci": 773.84}}, "briefcaseTotalCost": 10.918073551477216, "timescaleData": {"medianOutputSpeed": 370.715217893811, "medianTimeToFirstChunk": 8.88025009650005}, "outputSpeedVariance": {"p05": 258.45215850927, "q25": 286.92311086066, "median": 370.715217893811, "q75": 416.182774749479, "p95": 481.3790987164}, "timeToFirstChunkVariance": {"p05": 5.71037849585004, "q25": 7.0151188347501, "median": 8.88025009650005, "q75": 17.6545874327499, "p95": 48.2890601297999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 359.824169094916, "medianTimeToFirstChunk": 7.38038298700002, "medianTimeToFirstAnswerToken": 7.38038298700002, "medianEndToEndResponseTime": 8.769950567348154}, "long": {"medianOutputSpeed": 370.715217893811, "medianTimeToFirstChunk": 8.88025009650005, "medianTimeToFirstAnswerToken": 8.88025009650005, "medianEndToEndResponseTime": 10.228994296537778}, "hundredK": {"medianOutputSpeed": 344.587311437641, "medianTimeToFirstChunk": 7.72165953800001, "medianTimeToFirstAnswerToken": 7.72165953800001, "medianEndToEndResponseTime": 9.17267059790807}, "mediumParallel": {"medianOutputSpeed": 335.145016062526, "medianTimeToFirstChunk": 5.88464405999997, "medianTimeToFirstAnswerToken": 5.88464405999997, "medianEndToEndResponseTime": 7.376535557818688}}, "endToEndResponseTime": {"input": 8.88025009650005, "reasoning": 0, "answer": 1.3487442000377277, "total": 10.228994296537778}, "timeToFirstAnswerToken": {"input": 8.88025009650005, "reasoning": 0, "total": 8.88025009650005}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 4, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0985ada8-2ed8-404d-bd8b-7357666ce40f", "slug": "qwen3-5-2b-non-reasoning", "name": "Qwen3.5 2B (Non-reasoning)", "shortName": "Qwen3.5 2B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-5-2b", "name": "Qwen3.5 2B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 2.27, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-2B", "microevalsEnabled": false, "intelligenceIndex": 6.18559190112645, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -83.1333333333333, "omniscienceBreakdown": {"accuracy": 0.07383333333333333, "hallucinationRate": 0.9773258952672306}, "gdpval": -130.44, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.815789473684211, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": 0, "terminalBench40": null, "scicode": null, "lcr": 0.14, "ifbench": 0.291156462585034, "hle": 0.0495829471733086, "gpqa": 0.438383838383838, "critpt": 0, "apexAgents": null, "mmmuPro": 0.426589595375723, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "09f43999-b67b-4c1b-b050-44df41ed7e62", "slug": "devstral-2", "name": "Devstral 2", "shortName": "Devstral 2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-09", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "devstral-2", "name": "Devstral 2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 125, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": "Modified MIT License", "licenseUrl": "http://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512", "microevalsEnabled": true, "intelligenceIndex": 9.40586079574885, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 9.377466631414405, "strategyAndOps": 8.478046609276442, "legal": 10.460414527795093, "engineering": 11.61096779425394, "economics": 13.617070686592522}, "omniscience": -46.7, "omniscienceBreakdown": {"accuracy": 0.20816666666666667, "hallucinationRate": 0.8526625973479267}, "gdpPdfAllPass": 0.024, "gdpval": 688.65, "gdpvalNormalized": 0.09432499999999999, "itBenchSre": null, "tau2": 0.248538011695906, "tauBanking": 0.105154639175258, "terminalbenchHard": 0.189393939393939, "terminalBench21": 0.303370786516854, "terminalBench40": 0, "scicode": 0.327546296296296, "lcr": 0.323333333333333, "ifbench": 0.380952380952381, "hle": 0.0356811862835959, "gpqa": 0.593939393939394, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.447619047619048, "aime25": 0.366666666666667, "analystAgent": null, "automationBenchPartialScore": 0.03106312467124685, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "intelligenceIndexTimePerTask": 89.48348260038338, "intelligenceIndexCost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "intelligenceIndexCostPerTask": {"cost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0}, {"slug": "gdpval-aa", "weightedCostPerTask": 0}, {"slug": "automationbench-aa", "weightedCostPerTask": 0}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0}, {"slug": "scicode", "weightedCostPerTask": 0}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0}, {"slug": "gdp-pdf", "weightedCostPerTask": 0}, {"slug": "critpt", "weightedCostPerTask": 0}, {"slug": "omniscience", "weightedCostPerTask": 0}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0}]}, "canonicalIntelligenceIndexTokenCount": {"input": 926814213, "output": 17659621, "answer": 17659621, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 12544.288298302885, "output": 12544.288298302885}, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 5, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 483.02, "lower95ci": 472.48, "upper95ci": 493.95}, "rubricPassRate": 0.11156601842374617, "analyticalQuality": {"elo": 294.38, "lower95ci": 275.36, "upper95ci": 314.29}, "presentation": {"elo": 444, "lower95ci": 424.94, "upper95ci": 462.61}}, "briefcaseTotalCost": 0, "timescaleData": {"medianOutputSpeed": 136.132364823342, "medianTimeToFirstChunk": 2.300304117}, "outputSpeedVariance": {"p05": 79.7851261810981, "q25": 109.555904389483, "median": 136.132364823342, "q75": 157.946430554028, "p95": 191.926051087618}, "timeToFirstChunkVariance": {"p05": 2.1256288285, "q25": 2.22917702150002, "median": 2.300304117, "q75": 2.50887993899999, "p95": 4.2853207783}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 144.707203405825, "medianTimeToFirstChunk": 0.744668790999981, "medianTimeToFirstAnswerToken": 0.744668790999981, "medianEndToEndResponseTime": 4.199921800055598}, "long": {"medianOutputSpeed": 136.132364823342, "medianTimeToFirstChunk": 2.300304117, "medianTimeToFirstAnswerToken": 2.300304117, "medianEndToEndResponseTime": 5.973199983084795}, "hundredK": {"medianOutputSpeed": 133.778450039846, "medianTimeToFirstChunk": 35.4318277085, "medianTimeToFirstAnswerToken": 35.4318277085, "medianEndToEndResponseTime": 39.1693504548846}, "mediumParallel": {"medianOutputSpeed": 119.062339308303, "medianTimeToFirstChunk": 0.67206823399988, "medianTimeToFirstAnswerToken": 0.67206823399988, "medianEndToEndResponseTime": 4.871548967410363}}, "endToEndResponseTime": {"input": 2.300304117, "reasoning": 0, "answer": 3.6728958660847955, "total": 5.973199983084795}, "timeToFirstAnswerToken": {"input": 2.300304117, "reasoning": 0, "total": 2.300304117}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0a603978-03b9-4f47-a273-2f7fd969be85", "slug": "claude-35-sonnet", "name": "Claude 3.5 Sonnet (Oct '24)", "shortName": "Claude 3.5 Sonnet (Oct)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-10-22", "knowledgeCutoffDate": "2024-04-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-35-sonnet", "name": "Claude 3.5 Sonnet (Oct '24)"}, "deprecated": true, "deprecatedTo": "claude-3-7-sonnet", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.87908981990033, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0369, "gpqa": 0.598989898989899, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.380952380952381, "aime25": null, "analystAgent": null, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 3.75, "pricePer1k1mpImages": 4, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 2.31, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 0.47058823529411764, "price1mBlended0To100To1": 3.118811881188119, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0a7dda4d-cc9c-4a90-abc1-abb5772c901b", "slug": "deepseek-v3-1-terminus-reasoning", "name": "DeepSeek V3.1 Terminus (Reasoning)", "shortName": "DeepSeek V3.1 Terminus", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-22", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-v3-1-terminus", "name": "DeepSeek V3.1 Terminus"}, "deprecated": true, "deprecatedTo": "deepseek-v3-2-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus", "microevalsEnabled": false, "intelligenceIndex": 15.4047236054576, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 16.278318397460865, "strategyAndOps": 12.472557273082135, "legal": 18.86617034975458, "engineering": 18.726403654177155, "economics": 23.882625193080017}, "omniscience": -26.4, "omniscienceBreakdown": {"accuracy": 0.277, "hallucinationRate": 0.7482710926694329}, "gdpPdfAllPass": 0.054, "gdpval": 826.12, "gdpvalNormalized": 0.16306, "itBenchSre": null, "tau2": 0.371345029239766, "tauBanking": 0.210309278350515, "terminalbenchHard": 0.303030303030303, "terminalBench21": 0.449438202247191, "terminalBench40": 0, "scicode": 0.37962962962963, "lcr": 0.693333333333333, "ifbench": 0.570068027210884, "hle": 0.163577386468953, "gpqa": 0.791919191919192, "critpt": 0.0171428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.797883597883598, "aime25": 0.896666666666667, "analystAgent": null, "automationBenchPartialScore": 0.027062733944745267, "price1mInputTokens": 1.635, "price1mOutputTokens": 2.75, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.91375, "price1mBlended7To2To1": 1.7465, "price1mBlended0To1To1": 2.1925, "price1mBlended100To1To1": 1.6459313725490194, "price1mBlended0To100To1": 1.646039603960396, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 464.01, "lower95ci": 453.88, "upper95ci": 473.24}, "rubricPassRate": 0.09696969696969697, "analyticalQuality": {"elo": 242.49, "lower95ci": 222.61, "upper95ci": 260.38}, "presentation": {"elo": 445.57, "lower95ci": 426.85, "upper95ci": 463.87}}, "briefcaseTotalCost": 134.50940412000003, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0b226b82-1462-4860-bf1a-f8aed7024791", "slug": "qwen3-omni-30b-a3b-instruct", "name": "Qwen3 Omni 30B A3B Instruct", "shortName": "Qwen3 Omni 30B A3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-22", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-omni-30b-a3b-instruct", "name": "Qwen3 Omni 30B A3B Instruct"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 35.3, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 65536, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 6.00611816793457, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -69.2666666666667, "omniscienceBreakdown": {"accuracy": 0.14333333333333334, "hallucinationRate": 0.9758754863813229}, "gdpval": null, "itBenchSre": null, "tau2": 0.16374269005848, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.31156462585034, "hle": 0.046339202965709, "gpqa": 0.62020202020202, "critpt": 0, "apexAgents": null, "mmmuPro": 0.554913294797688, "livecodebench": 0.422222222222222, "aime25": 0.523333333333333, "analystAgent": null, "price1mInputTokens": 0.25, "price1mOutputTokens": 0.97, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.43, "price1mBlended7To2To1": 0.32199999999999995, "price1mBlended0To1To1": 0.61, "price1mBlended100To1To1": 0.25705882352941173, "price1mBlended0To100To1": 0.25712871287128714, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 97.0625871769834, "medianTimeToFirstChunk": 1.84687940449998}, "outputSpeedVariance": {"p05": 82.868935764665, "q25": 92.346991181213, "median": 97.0625871769834, "q75": 97.4666279058931, "p95": 99.8058149135232}, "timeToFirstChunkVariance": {"p05": 1.81657086335, "q25": 1.82324932850001, "median": 1.84687940449998, "q75": 1.912534756, "p95": 3.431032854}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 107.061785627885, "medianTimeToFirstChunk": 0.914616265999967, "medianTimeToFirstAnswerToken": 0.914616265999967, "medianEndToEndResponseTime": 5.584816721444}, "long": {"medianOutputSpeed": 97.0625871769834, "medianTimeToFirstChunk": 1.84687940449998, "medianTimeToFirstAnswerToken": 1.84687940449998, "medianEndToEndResponseTime": 6.9981948035867845}, "mediumParallel": {"medianOutputSpeed": 101.594931019508, "medianTimeToFirstChunk": 0.828128242000005, "medianTimeToFirstAnswerToken": 0.828128242000005, "medianEndToEndResponseTime": 5.7496336260037735}}, "endToEndResponseTime": {"input": 1.84687940449998, "reasoning": 0, "answer": 5.151315399086805, "total": 6.9981948035867845}, "timeToFirstAnswerToken": {"input": 1.84687940449998, "reasoning": 0, "total": 1.84687940449998}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": true, "outputModalityVideo": false}, {"id": "0b7efa66-2115-49e0-a1b7-a2ba225fe9f6", "slug": "grok-build-0-1-06-16", "name": "Grok Build 0.1 0616", "shortName": "Grok Build 0.1 0616", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "grok-build-0-1-0616", "name": "Grok Build 0.1 0616"}, "deprecated": true, "deprecatedTo": "grok-4-5", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 27.1714438189407, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 6.36666666666667, "omniscienceBreakdown": {"accuracy": 0.5151666666666667, "hallucinationRate": 0.9312478514953593}, "gdpval": 1138.29, "gdpvalNormalized": 0.31914499999999996, "itBenchSre": null, "tau2": null, "tauBanking": 0.134020618556701, "terminalbenchHard": null, "terminalBench21": 0.52059925093633, "terminalBench40": null, "scicode": null, "lcr": 0.746666666666667, "ifbench": null, "hle": 0.382761816496756, "gpqa": 0.894949494949495, "critpt": 0.0914285714285714, "apexAgents": null, "mmmuPro": 0.765317919075144, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1, "price1mOutputTokens": 2, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": 1.028, "price1mBlended0To3To1": 1.25, "price1mBlended7To2To1": 0.54, "price1mBlended0To1To1": 1.5, "price1mBlended100To1To1": 0.22549019607843138, "price1mBlended0To100To1": 1.00990099009901, "timescaleData": {"medianOutputSpeed": 51.0342246761299, "medianTimeToFirstChunk": 0.58140631699996}, "outputSpeedVariance": {"p05": 27.8781452969935, "q25": 41.7829506255221, "median": 51.0342246761299, "q75": 65.1313335248795, "p95": 117.729581807726}, "timeToFirstChunkVariance": {"p05": 0.423857007800092, "q25": 0.48628633525, "median": 0.58140631699996, "q75": 0.927008731250062, "p95": 3.46806328279997}, "performanceByPromptType": {"long": {"medianOutputSpeed": 51.0342246761299, "medianTimeToFirstChunk": 0.58140631699996, "medianTimeToFirstAnswerToken": 39.770793687774585, "medianEndToEndResponseTime": 49.56814053046824}}, "endToEndResponseTime": {"input": 0.58140631699996, "reasoning": 39.189387370774625, "answer": 9.797346842693656, "total": 49.56814053046824}, "timeToFirstAnswerToken": {"input": 0.58140631699996, "reasoning": 39.189387370774625, "total": 39.770793687774585}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 1, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0c64b008-20c3-408d-bd68-15136df8cd2c", "slug": "granite-4-2-3b", "name": "Granite 4.2 3B", "shortName": "Granite 4.2 3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-25", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "granite-4-2-3b", "name": "Granite 4.2 3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.2-3b", "microevalsEnabled": false, "intelligenceIndex": 9.05588232376756, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 8.550363203360488, "strategyAndOps": 3.3316329022354494, "legal": 12.356215657900783, "engineering": 16.09647590361446, "economics": 19.443443775100402}, "omniscience": -14.7166666666667, "omniscienceBreakdown": {"accuracy": 0.092, "hallucinationRate": 0.26339941262848754}, "gdpPdfAllPass": 0.002, "gdpval": 389.62, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": null, "tauBanking": 0.0556701030927835, "terminalbenchHard": null, "terminalBench21": 0.138576779026217, "terminalBench40": 0, "scicode": 0.253472222222222, "lcr": 0.243333333333333, "ifbench": null, "hle": 0.0662650602409639, "gpqa": 0.558585858585859, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.003767979122295127, "price1mInputTokens": 0.03, "price1mOutputTokens": 0.12, "cacheHitPrice": 0.0075, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.0525, "price1mBlended7To2To1": 0.02325, "price1mBlended0To1To1": 0.075, "price1mBlended100To1To1": 0.008823529411764706, "price1mBlended0To100To1": 0.03089108910891089, "intelligenceIndexTimePerTask": 83.18858294835225, "intelligenceIndexCost": {"total": 14.856445839, "input": 3.8257640789999994, "nonCacheInput": 0.42976578, "cacheRead": 2.607864327, "cacheWrite": 0.7881339719999995, "output": 11.03068176, "reasoning": 9.4977492, "answer": 1.5329325599999999}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.005962288257714593, "input": 0.00373299080970506, "nonCacheInput": 0.00022278121203464407, "cacheRead": 0.0028862322976982518, "cacheWrite": 0.0006239772999721645, "output": 0.002229297448009534, "reasoning": 0.0013425736028452916, "answer": 0.0008867238451642424}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.00235081711003228}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0006289464974999998}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.00011593262487014842}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.0017656220206363636}, {"slug": "scicode", "weightedCostPerTask": 0.00016449335416666666}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0002047688841519926}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00014401575}, {"slug": "critpt", "weightedCostPerTask": 0.0003078150428571428}, {"slug": "omniscience", "weightedCostPerTask": 9.331690349999998e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00018656007}]}, "canonicalIntelligenceIndexTokenCount": {"input": 388311902, "output": 91922348, "answer": 12774438, "reasoning": 79147910}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 11188.113357044096, "answer": 7389.365376368686, "output": 18577.478733412783}, "openness": {"opennessIndex": 72.22222222222223, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "briefcaseBreakdown": {"overall": {"elo": 120.61, "lower95ci": 109.23, "upper95ci": 130.59}, "rubricPassRate": 0.047474747474747475, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 1.4261623800862497, "timescaleData": {"medianOutputSpeed": 208.072046742699, "medianTimeToFirstChunk": 0.429255480000052}, "outputSpeedVariance": {"p05": 187.090870466659, "q25": 203.05530596987, "median": 208.072046742699, "q75": 217.218968050053, "p95": 224.459766287713}, "timeToFirstChunkVariance": {"p05": 0.366053800300119, "q25": 0.379155059000027, "median": 0.429255480000052, "q75": 0.46862341450003, "p95": 1.82743765965}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 220.954798573376, "medianTimeToFirstChunk": 0.195801468499987, "medianTimeToFirstAnswerToken": 9.247426565186121, "medianEndToEndResponseTime": 11.510332839357655}, "long": {"medianOutputSpeed": 208.072046742699, "medianTimeToFirstChunk": 0.429255480000052, "medianTimeToFirstAnswerToken": 10.041310685441422, "medianEndToEndResponseTime": 12.444324486801765}, "hundredK": {"medianOutputSpeed": 114.057551786199, "medianTimeToFirstChunk": 5.93480832000001, "medianTimeToFirstAnswerToken": 23.46981559202179, "medianEndToEndResponseTime": 27.85356741002723}, "mediumParallel": {"medianOutputSpeed": 161.064227067648, "medianTimeToFirstChunk": 0.277560703999938, "medianTimeToFirstAnswerToken": 12.694967327507884, "medianEndToEndResponseTime": 15.79931898338487}}, "endToEndResponseTime": {"input": 0.429255480000052, "reasoning": 9.61205520544137, "answer": 2.4030138013603426, "total": 12.444324486801765}, "timeToFirstAnswerToken": {"input": 0.429255480000052, "reasoning": 9.61205520544137, "total": 10.041310685441422}, "performanceDataSource": {"type": "firstParty", "providerName": "IBM"}, "hostModelCount": 1, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0d94dc87-12c8-4d4a-8d99-804ce3f17bc2", "slug": "nova-2-0-pro-reasoning-medium", "name": "Nova 2.0 Pro Preview (medium)", "shortName": "Nova 2.0 Pro Preview (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-27", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "nova-2-0-pro-preview", "name": "Nova 2.0 Pro Preview"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 14.1554948903666, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -49.05, "omniscienceBreakdown": {"accuracy": 0.21966666666666668, "hallucinationRate": 0.9100811618966254}, "mlcrOverall": 0.0388888888888889, "gdpval": 629.57, "gdpvalNormalized": 0.06478500000000002, "itBenchSre": null, "tau2": 0.926900584795322, "tauBanking": null, "terminalbenchHard": 0.242424242424242, "terminalBench21": 0.295880149812734, "terminalBench40": null, "scicode": null, "lcr": 0.64, "ifbench": 0.790476190476191, "hle": 0.0940685820203892, "gpqa": 0.784848484848485, "critpt": 0, "apexAgents": null, "mmmuPro": 0.645086705202312, "livecodebench": 0.73015873015873, "aime25": 0.89, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": 0.312, "cacheHitDiscountPercent": 0.7504, "cacheWritePrice": null, "pricePer1k1mpImages": 1.76, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 1.4684000000000001, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 0.4161764705882353, "price1mBlended0To100To1": 1.3366336633663367, "timescaleData": {"medianOutputSpeed": 113.708637314852, "medianTimeToFirstChunk": 14.874424886}, "outputSpeedVariance": {"p05": 102.006747805664, "q25": 108.954546964713, "median": 113.708637314852, "q75": 144.758931563939, "p95": 159.747571379035}, "timeToFirstChunkVariance": {"p05": 7.47781609199999, "q25": 9.51535208449998, "median": 14.874424886, "q75": 21.223105721, "p95": 34.4142262538001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 128.793231193764, "medianTimeToFirstChunk": 19.1961127464999, "medianTimeToFirstAnswerToken": 34.724879137888, "medianEndToEndResponseTime": 38.60707073573502}, "long": {"medianOutputSpeed": 113.708637314852, "medianTimeToFirstChunk": 14.874424886, "medianTimeToFirstAnswerToken": 32.46323825346765, "medianEndToEndResponseTime": 36.860441595334564}, "hundredK": {"medianOutputSpeed": 133.156305755872, "medianTimeToFirstChunk": 13.3951278295001, "medianTimeToFirstAnswerToken": 28.41506990919994, "medianEndToEndResponseTime": 32.1700554291249}, "mediumParallel": {"medianOutputSpeed": 117.564817797372, "medianTimeToFirstChunk": 22.7785005970001, "medianTimeToFirstAnswerToken": 39.79039273846614, "medianEndToEndResponseTime": 44.043365773832654}}, "endToEndResponseTime": {"input": 14.874424886, "reasoning": 17.588813367467655, "answer": 4.397203341866914, "total": 36.860441595334564}, "timeToFirstAnswerToken": {"input": 14.874424886, "reasoning": 17.588813367467655, "total": 32.46323825346765}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0de09623-2b1a-4c8d-86ef-7f5245d4e24b", "slug": "inkling", "name": "Inkling (xhigh)", "shortName": "Inkling", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-07-15", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "inkling", "name": "Inkling"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 975, "inferenceParametersActiveBillions": 41, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/thinkingmachines/Inkling", "microevalsEnabled": true, "intelligenceIndex": 25.5423060999384, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 30.311317630892194, "strategyAndOps": 24.169040496696873, "legal": 32.06600646919207, "healthcareAndMedical": 26.07008782619019, "engineering": 28.269606611862038, "economics": 39.165271740809395}, "omniscience": 2, "omniscienceBreakdown": {"accuracy": 0.4155, "hallucinationRate": 0.6766467065868264}, "mlcrOverall": 0.122222222222222, "gdpPdfAllPass": 0.128, "gdpval": 1165.19, "gdpvalNormalized": 0.33259500000000003, "itBenchSre": null, "tau2": null, "tauBanking": 0.290721649484536, "terminalbenchHard": null, "terminalBench21": 0.550561797752809, "terminalBench40": 0.0101010101010101, "scicode": 0.469907407407407, "lcr": 0.773333333333333, "ifbench": null, "hle": 0.318813716404078, "gpqa": 0.871717171717172, "critpt": 0.0542857142857143, "apexAgents": null, "mmmuPro": 0.734682080924856, "livecodebench": null, "aime25": null, "analystAgent": 0.2375, "automationBenchPartialScore": 0.04984889684475201, "enterpriseOpsGym": 0.37958818263205013, "price1mInputTokens": 1, "price1mOutputTokens": 4.05, "cacheHitPrice": 0.17, "cacheHitDiscountPercent": 0.83, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.7625, "price1mBlended7To2To1": 0.724, "price1mBlended0To1To1": 2.525, "price1mBlended100To1To1": 0.2161764705882353, "price1mBlended0To100To1": 1.0301980198019802, "intelligenceIndexTimePerTask": 424.81304283428176, "intelligenceIndexCost": {"total": 1026.135227006439, "input": 472.70339120643916, "nonCacheInput": 21.064496, "cacheRead": 357.79166066856067, "cacheWrite": 93.8472345378785, "output": 553.4318357999999, "reasoning": 501.35508089999996, "answer": 52.0767549}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.6070445010820831, "input": 0.4666877952660252, "nonCacheInput": 0.014608601127756447, "cacheRead": 0.371122547835551, "cacheWrite": 0.08095664630271783, "output": 0.14035670581605783, "reasoning": 0.09476657807148725, "answer": 0.04559012774457057}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.2150543560461207}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.04230530037019063}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0109748770875232}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.2642667713292703}, {"slug": "scicode", "weightedCostPerTask": 0.0058730653472222226}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.013587134089434658}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0141165244}, {"slug": "critpt", "weightedCostPerTask": 0.032502435928571424}, {"slug": "omniscience", "weightedCostPerTask": 0.0031644794337499994}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00519955705}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2219568558, "output": 136649836, "answer": 12858458, "reasoning": 123791378}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 23399.155079379572, "answer": 11256.82166532607, "output": 34655.976744705644}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 835.63, "lower95ci": 828.03, "upper95ci": 842.94}, "rubricPassRate": 0.19292929292929292, "analyticalQuality": {"elo": 751.43, "lower95ci": 737.07, "upper95ci": 764.58}, "presentation": {"elo": 873.11, "lower95ci": 859.43, "upper95ci": 886.79}}, "briefcaseTotalCost": 130.46630933464655, "timescaleData": {"medianOutputSpeed": 75.7136305068423, "medianTimeToFirstChunk": 2.7959400945}, "outputSpeedVariance": {"p05": 43.6882536761574, "q25": 60.173288287009, "median": 75.7136305068423, "q75": 90.2010768620284, "p95": 103.181302693288}, "timeToFirstChunkVariance": {"p05": 2.36506849899992, "q25": 2.66553882800008, "median": 2.7959400945, "q75": 3.22115991200001, "p95": 4.95484075534997}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 65.4094472185434, "medianTimeToFirstChunk": 2.66959195149999, "medianTimeToFirstAnswerToken": 33.24621482552735, "medianEndToEndResponseTime": 40.8903705440342}, "long": {"medianOutputSpeed": 75.7136305068423, "medianTimeToFirstChunk": 2.7959400945, "medianTimeToFirstAnswerToken": 29.21126302395929, "medianEndToEndResponseTime": 35.81509375632411}, "hundredK": {"medianOutputSpeed": 102.870609373977, "medianTimeToFirstChunk": 9.12703541049999, "medianTimeToFirstAnswerToken": 28.568934434634052, "medianEndToEndResponseTime": 33.42940919066757}, "mediumParallel": {"medianOutputSpeed": 67.7757910037083, "medianTimeToFirstChunk": 3.15188821799995, "medianTimeToFirstAnswerToken": 32.66094994020945, "medianEndToEndResponseTime": 40.03821537076183}}, "endToEndResponseTime": {"input": 2.7959400945, "reasoning": 26.41532292945929, "answer": 6.603830732364822, "total": 35.81509375632411}, "timeToFirstAnswerToken": {"input": 2.7959400945, "reasoning": 26.41532292945929, "total": 29.21126302395929}, "performanceDataSource": {"type": "firstParty", "providerName": "Thinking Machines"}, "hostModelCount": 6, "creator": {"id": "8f3f9fdd-e42f-4814-a35e-5da1925b539b", "slug": "thinking-machines", "name": "Thinking Machines", "logo": "/img/logos/thinking_machines.svg", "color": "#676767", "country": "us", "url": "https://thinkingmachines.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0de67206-4d36-4d10-b8f6-cf37fa747a03", "slug": "kimi-k2-6", "name": "Kimi K2.6", "shortName": "Kimi K2.6", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 4451, "release": {"slug": "kimi-k2-6", "name": "Kimi K2.6"}, "deprecated": true, "deprecatedTo": "kimi-k3", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1000, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Modified MIT", "licenseUrl": "https://huggingface.co/moonshotai/Kimi-K2.6/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-K2.6", "microevalsEnabled": true, "intelligenceIndex": 27.4619499742844, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 28.84771177854233, "strategyAndOps": 22.67863481161259, "legal": 29.92908792639539, "engineering": 30.942519855646367, "economics": 40.9646953197405}, "omniscience": 5.3, "omniscienceBreakdown": {"accuracy": 0.326, "hallucinationRate": 0.4050445103857567}, "harveyLab": 0.841221595020987, "gdpPdfAllPass": 0.13, "gdpval": 1096.33, "gdpvalNormalized": 0.29816499999999996, "itBenchSre": 0.311864406779661, "tau2": 0.95906432748538, "tauBanking": 0.232989690721649, "terminalbenchHard": 0.439393939393939, "terminalBench21": 0.659176029962547, "terminalBench40": 0.00505050505050505, "scicode": 0.515046296296296, "lcr": 0.81, "ifbench": 0.759863945578231, "hle": 0.374884151992586, "gpqa": 0.911111111111111, "critpt": 0.08, "apexAgents": 0.284660766961652, "mmmuPro": 0.79364161849711, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.1302075985638627, "enterpriseOpsGym": 0.3852581319009251, "price1mInputTokens": 0.95, "price1mOutputTokens": 4, "cacheHitPrice": 0.16, "cacheHitDiscountPercent": 0.831578947368421, "cacheWritePrice": null, "pricePer1k1mpImages": 1.3, "price1mBlended0To3To1": 1.7125, "price1mBlended7To2To1": 0.702, "price1mBlended0To1To1": 2.475, "price1mBlended100To1To1": 0.2053921568627451, "price1mBlended0To100To1": 0.9801980198019802, "intelligenceIndexTimePerTask": 1094.857419589722, "intelligenceIndexCost": {"total": 1528.2008800608073, "input": 805.8703840608073, "nonCacheInput": 21.07191485, "cacheRead": 286.9822880281909, "cacheWrite": 497.8161811826164, "output": 722.3304959999999, "reasoning": 666.212328, "answer": 56.118168}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.799769615295709, "input": 0.6104211891501573, "nonCacheInput": 0.014975854891872616, "cacheRead": 0.22465516120805454, "cacheWrite": 0.3707901730502302, "output": 0.1893484261455515, "reasoning": 0.14737956316241402, "answer": 0.04196886298313746}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.17485764831169276}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.06025213170456084}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.03049102154240744}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.4151794390168377}, {"slug": "scicode", "weightedCostPerTask": 0.004334814079861112}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.01721663204124189}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.015178976299999999}, {"slug": "critpt", "weightedCostPerTask": 0.07331727414285714}, {"slug": "omniscience", "weightedCostPerTask": 0.0038550479562499997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.005086630199999999}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2339837296, "output": 180582624, "answer": 14029542, "reasoning": 166553082}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 36844.89079060351, "answer": 10492.215745784366, "output": 47337.10653638787}, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 823.87, "lower95ci": 817.39, "upper95ci": 830.07}, "rubricPassRate": 0.20606060606060606, "analyticalQuality": {"elo": 796.02, "lower95ci": 784.75, "upper95ci": 807.83}, "presentation": {"elo": 786.61, "lower95ci": 773.78, "upper95ci": 798.69}}, "briefcaseTotalCost": 106.08030664242693, "timescaleData": {"medianOutputSpeed": 38.1614429942052, "medianTimeToFirstChunk": 2.97757324700001}, "outputSpeedVariance": {"p05": 34.3603374253351, "q25": 35.5815468267716, "median": 38.1614429942052, "q75": 43.4255497217225, "p95": 57.9858026824186}, "timeToFirstChunkVariance": {"p05": 2.59138118959998, "q25": 2.78414057000003, "median": 2.97757324700001, "q75": 3.71407090599996, "p95": 10.0876998948}, "performanceByPromptType": {"long": {"medianOutputSpeed": 38.1614429942052, "medianTimeToFirstChunk": 2.97757324700001, "medianTimeToFirstAnswerToken": 119.61362395073996, "medianEndToEndResponseTime": 132.71585386578602}}, "endToEndResponseTime": {"input": 2.97757324700001, "reasoning": 116.63605070373995, "answer": 13.102229915046053, "total": 132.71585386578602}, "timeToFirstAnswerToken": {"input": 2.97757324700001, "reasoning": 116.63605070373995, "total": 119.61362395073996}, "performanceDataSource": {"type": "firstParty", "providerName": "Kimi"}, "hostModelCount": 14, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0e34f05c-387e-4968-be15-ccec4a55d8c1", "slug": "deepseek-r1-0120", "name": "DeepSeek R1 (Jan '25)", "shortName": "DeepSeek R1 (Jan)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2347, "release": {"slug": "deepseek-r1-0120", "name": "DeepSeek R1 (Jan '25)"}, "deprecated": true, "deprecatedTo": "deepseek-r1", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "microevalsEnabled": false, "intelligenceIndex": 11.4109820044475, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 11.242476759628154, "strategyAndOps": 9.00043607622408, "legal": 12.681501650165018, "engineering": 14.940714285714286, "economics": 16.165833333333335}, "omniscience": -32.2166666666667, "omniscienceBreakdown": {"accuracy": 0.30516666666666664, "hallucinationRate": 0.9028544015351403}, "gdpPdfAllPass": 0.024, "gdpval": 478.84, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.114035087719298, "tauBanking": 0.0639175257731959, "terminalbenchHard": 0.0606060606060606, "terminalBench21": 0.191011235955056, "terminalBench40": 0, "scicode": 0.383101851851852, "lcr": 0.576666666666667, "ifbench": 0.389795918367347, "hle": 0.085, "gpqa": 0.708080808080808, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.616931216931217, "aime25": 0.68, "analystAgent": null, "automationBenchPartialScore": 0.002418527292355699, "price1mInputTokens": 2, "price1mOutputTokens": 4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2.5, "price1mBlended7To2To1": 2.2, "price1mBlended0To1To1": 3, "price1mBlended100To1To1": 2.019607843137255, "price1mBlended0To100To1": 2.01980198019802, "intelligenceIndexCost": {"total": 460.73639000000003, "input": 287.397002, "nonCacheInput": 30.06376, "cacheRead": 0, "cacheWrite": 257.333242, "output": 173.339388, "reasoning": 148.604668, "answer": 24.73472}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.2617212405141733, "input": 0.20266117790621602, "nonCacheInput": 0.01736825926096474, "cacheRead": 0, "cacheWrite": 0.18529291864525124, "output": 0.05906006260795726, "reasoning": 0.045567350456643965, "answer": 0.013492712151313294}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.09142795384615383}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.09893898545454546}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0019024899543378998}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.03585309696969697}, {"slug": "scicode", "weightedCostPerTask": 0.0027974916666666672}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0034471474513438362}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.007706744000000001}, {"slug": "critpt", "weightedCostPerTask": 0.009360208571428573}, {"slug": "omniscience", "weightedCostPerTask": 0.0005700845999999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.009717038}]}, "canonicalIntelligenceIndexTokenCount": {"input": 143698501, "output": 43334847, "answer": 6183680, "reasoning": 37151167}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 11391.837614160992, "answer": 3373.178037828324, "output": 14765.015651989315}, "briefcaseBreakdown": {"overall": {"elo": 149.56, "lower95ci": 139.24, "upper95ci": 159.57}, "rubricPassRate": 0.04171011470281543, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 101.55, "lower95ci": 82.38, "upper95ci": 119.75}}, "briefcaseTotalCost": 55.466291999999996, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 5, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0e49fe2d-dd3c-4ae5-b56f-a1c89e14b89e", "slug": "deepseek-r1-distill-llama-8b", "name": "DeepSeek R1 Distill Llama 8B", "shortName": "DeepSeek R1 Distill Llama 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-r1-distill-llama-8b", "name": "DeepSeek R1 Distill Llama 8B"}, "deprecated": true, "deprecatedTo": "deepseek-v3-0324", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.1 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B", "microevalsEnabled": false, "intelligenceIndex": 6.4762216011156, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.175510204081633, "hle": null, "gpqa": 0.302020202020202, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.232804232804233, "aime25": 0.413333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0e5f6140-1154-4583-a3e0-8c032a338892", "slug": "qwen3-0.6b-instruct", "name": "Qwen3 0.6B (Non-reasoning)", "shortName": "Qwen3 0.6B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-0.6b-instruct", "name": "Qwen3 0.6B"}, "deprecated": true, "deprecatedTo": "qwen3-5-0-8b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 0.752, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-0.6B", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -84.95, "omniscienceBreakdown": {"accuracy": 0.04583333333333333, "hallucinationRate": 0.9383406113537118}, "gdpval": null, "itBenchSre": null, "tau2": 0.146198830409357, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.219047619047619, "hle": 0.0493, "gpqa": 0.231313131313131, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.073015873015873, "aime25": 0.103333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0e66bae9-41f1-42fc-9276-ce8cb6f72919", "slug": "qwen3-5-397b-a17b", "name": "Qwen3.5 397B A17B (Reasoning)", "shortName": "Qwen3.5 397B A17B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 3186, "release": {"slug": "qwen3-5-397b-a17b", "name": "Qwen3.5 397B A17B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 397, "inferenceParametersActiveBillions": 17, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-397B-A17B", "microevalsEnabled": true, "intelligenceIndex": 19.1073499294815, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 20.2887288009959, "strategyAndOps": 16.30512926958091, "legal": 21.75801717084825, "engineering": 22.077968645382157, "economics": 28.0761798154155}, "omniscience": -30.75, "omniscienceBreakdown": {"accuracy": 0.308, "hallucinationRate": 0.8894508670520231}, "harveyLab": 0.723838471558836, "gdpPdfAllPass": 0.122, "gdpval": 905.4, "gdpvalNormalized": 0.2027, "itBenchSre": 0.340866290018832, "tau2": 0.956140350877193, "tauBanking": 0.134020618556701, "terminalbenchHard": 0.409090909090909, "terminalBench21": 0.51310861423221, "terminalBench40": 0, "scicode": 0.447916666666667, "lcr": 0.773333333333333, "ifbench": 0.787755102040816, "hle": 0.289620018535681, "gpqa": 0.892929292929293, "critpt": 0.0170612244897959, "apexAgents": 0.153392330383481, "mmmuPro": 0.772832369942197, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.06886670023070866, "enterpriseOpsGym": 0.3088630259623993, "price1mInputTokens": 0.6, "price1mOutputTokens": 3.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.615, "price1mBlended0To3To1": 1.35, "price1mBlended7To2To1": 0.9, "price1mBlended0To1To1": 2.1, "price1mBlended100To1To1": 0.6294117647058823, "price1mBlended0To100To1": 0.6297029702970297, "intelligenceIndexTimePerTask": 208.18626767422126, "intelligenceIndexCost": {"total": 940.9678692, "input": 598.6954932, "nonCacheInput": 12.114073199999998, "cacheRead": 0, "cacheWrite": 586.58142, "output": 342.27237599999995, "reasoning": 286.6227552, "answer": 55.6496208}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.47457695829894075, "input": 0.4073794441792204, "nonCacheInput": 0.00818241117316254, "cacheRead": 0, "cacheWrite": 0.39919703300605786, "output": 0.06719751411972026, "reasoning": 0.031469974817920805, "answer": 0.03572753930179947}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.11214348329670329}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.03714979554545454}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.02432796292237443}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.26022617000000003}, {"slug": "scicode", "weightedCostPerTask": 0.0025959152083333335}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00805264796107507}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0077706114}, {"slug": "critpt", "weightedCostPerTask": 0.01639848}, {"slug": "omniscience", "weightedCostPerTask": 0.002301583965}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.003610308}]}, "canonicalIntelligenceIndexTokenCount": {"input": 997825822, "output": 95075660, "answer": 15458228, "reasoning": 79617432}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 8741.65967164467, "answer": 9924.316472722072, "output": 18665.97614436674}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 562.65, "lower95ci": 554.47, "upper95ci": 570.1}, "rubricPassRate": 0.12121212121212122, "analyticalQuality": {"elo": 385.59, "lower95ci": 369.63, "upper95ci": 400.73}, "presentation": {"elo": 576.45, "lower95ci": 561.43, "upper95ci": 592.3}}, "briefcaseTotalCost": 68.0337132, "timescaleData": {"medianOutputSpeed": 86.7358275480268, "medianTimeToFirstChunk": 2.13469218099999}, "outputSpeedVariance": {"p05": 73.9521695527265, "q25": 78.9679711163519, "median": 86.7358275480268, "q75": 89.2379265108403, "p95": 97.5491971962573}, "timeToFirstChunkVariance": {"p05": 1.94011822069981, "q25": 2.09920843450002, "median": 2.13469218099999, "q75": 2.3453350645, "p95": 3.1568188378}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 81.7250053507533, "medianTimeToFirstChunk": 1.65427613700001, "medianTimeToFirstAnswerToken": 40.6386724833336, "medianEndToEndResponseTime": 46.75675100598482}, "long": {"medianOutputSpeed": 86.7358275480268, "medianTimeToFirstChunk": 2.13469218099999, "medianTimeToFirstAnswerToken": 38.866917952822696, "medianEndToEndResponseTime": 44.631548488262546}, "hundredK": {"medianOutputSpeed": 93.4709789566174, "medianTimeToFirstChunk": 5.77721746049997, "medianTimeToFirstAnswerToken": 39.86266339852438, "medianEndToEndResponseTime": 45.21191731221308}, "mediumParallel": {"medianOutputSpeed": 82.2869524408821, "medianTimeToFirstChunk": 1.63454424949998, "medianTimeToFirstAnswerToken": 40.3527116562822, "medianEndToEndResponseTime": 46.429009114973695}}, "endToEndResponseTime": {"input": 2.13469218099999, "reasoning": 36.732225771822705, "answer": 5.7646305354398475, "total": 44.631548488262546}, "timeToFirstAnswerToken": {"input": 2.13469218099999, "reasoning": 36.732225771822705, "total": 38.866917952822696}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 10, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0faadeeb-320c-45cf-9c76-5f8768f342e6", "slug": "lfm2-1-2b", "name": "LFM2 1.2B", "shortName": "LFM2 1.2B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-10", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "lfm2-1-2b", "name": "LFM2 1.2B"}, "deprecated": true, "deprecatedTo": "lfm2-5-1-2b-instruct", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1.17, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32768, "licenseName": "lfm 1.0", "licenseUrl": "https://huggingface.co/LiquidAI/LFM2-1.2B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LiquidAI/LFM2-1.2B", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -72.4333333333333, "omniscienceBreakdown": {"accuracy": 0.04933333333333333, "hallucinationRate": 0.8138148667601683}, "gdpval": null, "itBenchSre": null, "tau2": 0.125730994152047, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.219727891156463, "hle": 0.0556070435588508, "gpqa": 0.228282828282828, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0201058201058201, "aime25": 0.0333333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5b1886c4-43ba-4007-b840-9d21a2b7d42c", "slug": "liquidai", "name": "Liquid AI", "logo": "/img/logos/liquidai_small.svg", "color": "#000000", "country": "us", "url": "https://www.liquid.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0fc6308e-fbd2-42d3-a216-06da3c43e34e", "slug": "kimi-k2-6-non-reasoning", "name": "Kimi K2.6 (Non-reasoning)", "shortName": "Kimi K2.6 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-20", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "kimi-k2-6", "name": "Kimi K2.6"}, "deprecated": true, "deprecatedTo": "kimi-k3-low", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1000, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Modified MIT", "licenseUrl": "https://huggingface.co/moonshotai/Kimi-K2.6/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-K2.6", "microevalsEnabled": false, "intelligenceIndex": 23.5695903898533, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -9.18333333333333, "omniscienceBreakdown": {"accuracy": 0.243, "hallucinationRate": 0.4423161602818142}, "gdpval": null, "itBenchSre": null, "tau2": 0.93859649122807, "tauBanking": null, "terminalbenchHard": 0.378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.696666666666667, "ifbench": 0.442857142857143, "hle": 0.195551436515292, "gpqa": 0.787878787878788, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.95, "price1mOutputTokens": 4, "cacheHitPrice": 0.16, "cacheHitDiscountPercent": 0.831578947368421, "cacheWritePrice": null, "pricePer1k1mpImages": 1.3, "price1mBlended0To3To1": 1.7125, "price1mBlended7To2To1": 0.702, "price1mBlended0To1To1": 2.475, "price1mBlended100To1To1": 0.2053921568627451, "price1mBlended0To100To1": 0.9801980198019802, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 38.2703356733092, "medianTimeToFirstChunk": 3.06574721350003}, "outputSpeedVariance": {"p05": 33.8018243290324, "q25": 36.1708726523575, "median": 38.2703356733092, "q75": 41.2982472609693, "p95": 48.6321824141795}, "timeToFirstChunkVariance": {"p05": 2.7370580514, "q25": 2.81274234625002, "median": 3.06574721350003, "q75": 4.26832351875016, "p95": 9.0529138056}, "performanceByPromptType": {"long": {"medianOutputSpeed": 38.2703356733092, "medianTimeToFirstChunk": 3.06574721350003, "medianTimeToFirstAnswerToken": 3.06574721350003, "medianEndToEndResponseTime": 16.130696637205084}}, "endToEndResponseTime": {"input": 3.06574721350003, "reasoning": 0, "answer": 13.064949423705055, "total": 16.130696637205084}, "timeToFirstAnswerToken": {"input": 3.06574721350003, "reasoning": 0, "total": 3.06574721350003}, "performanceDataSource": {"type": "firstParty", "providerName": "Kimi"}, "hostModelCount": 12, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "0fec07d5-a9b2-407a-b5f8-5bf10bd86b59", "slug": "magistral-small", "name": "Magistral Small 1", "shortName": "Magistral Small 1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "magistral-small", "name": "Magistral Small 1"}, "deprecated": true, "deprecatedTo": "magistral-small-2509", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 23.6, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 40000, "licenseName": "Apache 2.0", "licenseUrl": "https://choosealicense.com/licenses/apache-2.0/", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Magistral-Small-2506", "microevalsEnabled": false, "intelligenceIndex": 8.22425322380767, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -44.4, "omniscienceBreakdown": {"accuracy": 0.18016666666666667, "hallucinationRate": 0.7613336043911364}, "gdpval": null, "itBenchSre": null, "tau2": 0.266081871345029, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.247619047619048, "hle": 0.0755329008341057, "gpqa": 0.641414141414141, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.514285714285714, "aime25": 0.413333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1071dea1-43e7-4fe9-b936-3034bb622b2e", "slug": "granite-4-2-30b", "name": "Granite 4.2 30B", "shortName": "Granite 4.2 30B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-25", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "granite-4-2-30b", "name": "Granite 4.2 30B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.2-30b", "microevalsEnabled": false, "intelligenceIndex": 14.8312405050789, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -12.9166666666667, "omniscienceBreakdown": {"accuracy": 0.10083333333333333, "hallucinationRate": 0.2557924003707136}, "gdpPdfAllPass": 0.018, "gdpval": 721.01, "gdpvalNormalized": 0.11050499999999999, "itBenchSre": null, "tau2": null, "tauBanking": 0.144329896907216, "terminalbenchHard": null, "terminalBench21": 0.265917602996255, "terminalBench40": null, "scicode": 0.378472222222222, "lcr": 0.49, "ifbench": null, "hle": 0.111677479147359, "gpqa": 0.644444444444444, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.16, "price1mOutputTokens": 0.65, "cacheHitPrice": 0.04, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.2825, "price1mBlended7To2To1": 0.125, "price1mBlended0To1To1": 0.405, "price1mBlended100To1To1": 0.04715686274509805, "price1mBlended0To100To1": 0.16485148514851483, "openness": {"opennessIndex": 72.22222222222223, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {"medianOutputSpeed": 75.0005977776162, "medianTimeToFirstChunk": 0.795767127999966}, "outputSpeedVariance": {"p05": 24.832810768319, "q25": 31.8868233911394, "median": 75.0005977776162, "q75": 76.9034143997869, "p95": 78.6347357106878}, "timeToFirstChunkVariance": {"p05": 0.737885433400004, "q25": 0.748317296000039, "median": 0.795767127999966, "q75": 0.965401847999999, "p95": 92.3708286329998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 76.544201060173, "medianTimeToFirstChunk": 0.340179283500035, "medianTimeToFirstAnswerToken": 26.4688731923666, "medianEndToEndResponseTime": 33.001046669583246}, "long": {"medianOutputSpeed": 75.0005977776162, "medianTimeToFirstChunk": 0.795767127999966, "medianTimeToFirstAnswerToken": 27.462221253208238, "medianEndToEndResponseTime": 34.1288347845103}, "hundredK": {"medianOutputSpeed": 64.1835789746785, "medianTimeToFirstChunk": 8.885669829, "medianTimeToFirstAnswerToken": 40.04628804240679, "medianEndToEndResponseTime": 47.83644259575849}, "mediumParallel": {"medianOutputSpeed": 74.1187227619176, "medianTimeToFirstChunk": 0.511538477999806, "medianTimeToFirstAnswerToken": 27.495273834912965, "medianEndToEndResponseTime": 34.24120767414126}}, "endToEndResponseTime": {"input": 0.795767127999966, "reasoning": 26.666454125208272, "answer": 6.666613531302068, "total": 34.1288347845103}, "timeToFirstAnswerToken": {"input": 0.795767127999966, "reasoning": 26.666454125208272, "total": 27.462221253208238}, "performanceDataSource": {"type": "firstParty", "providerName": "IBM"}, "hostModelCount": 1, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "122a1fa1-976a-4089-87a2-5a0a13e2a52c", "slug": "k2-7b-ph2", "name": "K2 Horizon 7B", "shortName": "K2 Horizon 7B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-03", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "k2-horizon-7b", "name": "K2 Horizon 7B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 524288, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/IFM/K2-Horizon-7B", "microevalsEnabled": false, "intelligenceIndex": 21.0473319421354, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 21.678815209092555, "strategyAndOps": 21.048708437329484, "legal": 23.332728920695534, "engineering": 24.70826830920084, "economics": 31.856915701266594}, "omniscience": -16.5666666666667, "omniscienceBreakdown": {"accuracy": 0.12766666666666668, "hallucinationRate": 0.3362628964463126}, "gdpPdfAllPass": 0.032, "gdpval": 1091.08, "gdpvalNormalized": 0.29553999999999997, "itBenchSre": null, "tau2": null, "tauBanking": 0.276288659793814, "terminalbenchHard": null, "terminalBench21": 0.441947565543071, "terminalBench40": 0.0101010101010101, "scicode": 0.275462962962963, "lcr": 0.696666666666667, "ifbench": null, "hle": 0.182113067655236, "gpqa": 0.752525252525252, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.209005917720684, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "canonicalIntelligenceIndexTokenCount": {"input": 8271270890, "output": 159994456, "answer": 27538039, "reasoning": 132456417}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 49501.375402382466, "answer": 22661.927400091412, "output": 72163.30280247387}, "briefcaseBreakdown": {"overall": {"elo": 1020.86, "lower95ci": 1011.12, "upper95ci": 1030.87}, "rubricPassRate": 0.2624618514750763, "analyticalQuality": {"elo": 1061.74, "lower95ci": 1042.38, "upper95ci": 1080.96}, "presentation": {"elo": 993.43, "lower95ci": 975.17, "upper95ci": 1011.24}}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "8b8b84fb-4b24-45be-b9e2-74ed50d00ff7", "slug": "mbzuai", "name": "MBZUAI Institute of Foundation Models", "logo": "/img/logos/mbzuai_small.svg", "color": "#1521a9", "country": "ae", "url": "https://mbzuai.ac.ae/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1299b9a8-af50-4742-a58b-24ff7eb48f9f", "slug": "lfm-40b", "name": "LFM 40B", "shortName": "LFM 40B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "lfm-40b", "name": "LFM 40B"}, "deprecated": true, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 40.3, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 32000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.41798540794277, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0493, "gpqa": 0.327272727272727, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0962962962962963, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5b1886c4-43ba-4007-b840-9d21a2b7d42c", "slug": "liquidai", "name": "Liquid AI", "logo": "/img/logos/liquidai_small.svg", "color": "#000000", "country": "us", "url": "https://www.liquid.ai"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "12adec16-19fe-4d92-aeff-5ef3eb7e780a", "slug": "minimax-m2-5", "name": "MiniMax-M2.5", "shortName": "MiniMax-M2.5", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "minimax-m2-5", "name": "MiniMax-M2.5"}, "deprecated": true, "deprecatedTo": "minimax-m2-7", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 230, "inferenceParametersActiveBillions": 10, "sizeClass": "large", "contextWindowTokens": 204800, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/MiniMaxAI/MiniMax-M2.5", "microevalsEnabled": false, "intelligenceIndex": 22.7966473221872, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -38.8666666666667, "omniscienceBreakdown": {"accuracy": 0.2618333333333333, "hallucinationRate": 0.8812372996161661}, "gdpval": null, "itBenchSre": null, "tau2": 0.953216374269006, "tauBanking": null, "terminalbenchHard": 0.348484848484849, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.733333333333333, "ifbench": 0.716326530612245, "hle": 0.205282669138091, "gpqa": 0.848484848484848, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.03, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.375, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5249999999999999, "price1mBlended7To2To1": 0.20099999999999998, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.04411764705882353, "price1mBlended0To100To1": 0.3089108910891089, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 95.8899950233982, "medianTimeToFirstChunk": 1.65560997}, "outputSpeedVariance": {"p05": 68.5030407398283, "q25": 73.8061786436475, "median": 95.8899950233982, "q75": 112.721325258983, "p95": 125.426796045709}, "timeToFirstChunkVariance": {"p05": 1.40919107910006, "q25": 1.57394905725007, "median": 1.65560997, "q75": 1.81877605025001, "p95": 2.99695640554987}, "performanceByPromptType": {"long": {"medianOutputSpeed": 95.8899950233982, "medianTimeToFirstChunk": 1.65560997, "medianTimeToFirstAnswerToken": 22.51284329775206, "medianEndToEndResponseTime": 27.727151629690074}}, "endToEndResponseTime": {"input": 1.65560997, "reasoning": 20.85723332775206, "answer": 5.214308331938015, "total": 27.727151629690074}, "timeToFirstAnswerToken": {"input": 1.65560997, "reasoning": 20.85723332775206, "total": 22.51284329775206}, "performanceDataSource": {"type": "firstParty", "providerName": "MiniMax"}, "hostModelCount": 9, "creator": {"id": "a31a9071-6144-4dbb-92dc-2e02d653ecea", "slug": "minimax", "name": "MiniMax", "logo": "/img/logos/minimax_small.svg", "color": "#EB3568", "country": "cn", "url": "https://minimaxi.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "12f6a061-0ab3-4c76-b225-49abee253651", "slug": "mistral-small-4-non-reasoning", "name": "Mistral Small 4 (Non-reasoning)", "shortName": "Mistral Small 4 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-16", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-small-4", "name": "Mistral Small 4"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 119, "inferenceParametersActiveBillions": 6.5, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-Small-4-119B-2603", "microevalsEnabled": false, "intelligenceIndex": 8.99008610259603, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -48.5166666666667, "omniscienceBreakdown": {"accuracy": 0.16566666666666666, "hallucinationRate": 0.7800639232920495}, "gdpval": null, "itBenchSre": null, "tau2": 0.184210526315789, "tauBanking": null, "terminalbenchHard": 0.106060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.283333333333333, "ifbench": 0.327891156462585, "hle": 0.0379981464318814, "gpqa": 0.570707070707071, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.464739884393064, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.2, "price1mBlended0To3To1": 0.26249999999999996, "price1mBlended7To2To1": 0.195, "price1mBlended0To1To1": 0.375, "price1mBlended100To1To1": 0.15441176470588236, "price1mBlended0To100To1": 0.15445544554455445, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 164.94271197541, "medianTimeToFirstChunk": 0.751727317000075}, "outputSpeedVariance": {"p05": 96.1068787704054, "q25": 130.868852526541, "median": 164.94271197541, "q75": 176.381826460902, "p95": 198.939849344303}, "timeToFirstChunkVariance": {"p05": 0.684627976750022, "q25": 0.714500837999992, "median": 0.751727317000075, "q75": 0.798643344249996, "p95": 1.54968883959995}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 153.695072413684, "medianTimeToFirstChunk": 0.541346199000031, "medianTimeToFirstAnswerToken": 0.541346199000031, "medianEndToEndResponseTime": 3.7945409315819933}, "long": {"medianOutputSpeed": 164.94271197541, "medianTimeToFirstChunk": 0.751727317000075, "medianTimeToFirstAnswerToken": 0.751727317000075, "medianEndToEndResponseTime": 3.783082834390507}, "hundredK": {"medianOutputSpeed": 129.079477326709, "medianTimeToFirstChunk": 5.48733450549997, "medianTimeToFirstAnswerToken": 5.48733450549997, "medianEndToEndResponseTime": 9.360916970778053}, "mediumParallel": {"medianOutputSpeed": 152.959497274793, "medianTimeToFirstChunk": 0.552814537000017, "medianTimeToFirstAnswerToken": 0.552814537000017, "medianEndToEndResponseTime": 3.821653732396599}}, "endToEndResponseTime": {"input": 0.751727317000075, "reasoning": 0, "answer": 3.0313555173904323, "total": 3.783082834390507}, "timeToFirstAnswerToken": {"input": 0.751727317000075, "reasoning": 0, "total": 0.751727317000075}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1305c921-7aaa-4d6d-99b5-99b3acf15e19", "slug": "claude-opus-5-xhigh", "name": "Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)", "shortName": "Claude Opus 5 (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "claude-opus-5", "name": "Claude Opus 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 49.6514552926939, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 54.33697891422929, "strategyAndOps": 54.390383171252545, "legal": 55.994290225410204, "healthcareAndMedical": 52.95267186967661, "engineering": 52.79937086389077, "economics": 60.246820165276496}, "omniscience": 35.3833333333333, "omniscienceBreakdown": {"accuracy": 0.595, "hallucinationRate": 0.5954732510288065}, "mlcrOverall": 0.583333333333333, "gdpPdfAllPass": 0.21, "gdpval": 1708.14, "gdpvalNormalized": 0.60407, "itBenchSre": null, "tau2": null, "tauBanking": 0.43298969072165, "terminalbenchHard": null, "terminalBench21": 0.880149812734082, "terminalBench40": 0.464646464646465, "scicode": 0.556712962962963, "lcr": 0.803333333333333, "ifbench": null, "hle": 0.544022242817424, "gpqa": 0.937373737373737, "critpt": 0.277142857142857, "apexAgents": null, "mmmuPro": 0.839884393063584, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5321919210948297, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.86, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "intelligenceIndexTimePerTask": 695.9400855951081, "intelligenceIndexCost": {"total": 5867.757860182575, "input": 3105.055560182575, "nonCacheInput": 177.23678, "cacheRead": 2137.866968027602, "cacheWrite": 789.9518121549726, "output": 2762.7023, "reasoning": 1900.809825, "answer": 861.892475}, "intelligenceIndexCostPerTask": {"cost": {"total": 4.877843772646787, "input": 3.361467828679532, "nonCacheInput": 0.1290896598110611, "cacheRead": 2.575722571246833, "cacheWrite": 0.6566555976216382, "output": 1.516375943967254, "reasoning": 0.8748764525062369, "answer": 0.6414994914610175}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 2.139188016204884}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.4962976604298486}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.05770875558019151}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.7353943799225686}, {"slug": "scicode", "weightedCostPerTask": 0.007227737847222222}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.05170749003707137}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.10471828999999999}, {"slug": "critpt", "weightedCostPerTask": 0.24581399999999998}, {"slug": "omniscience", "weightedCostPerTask": 0.0021433976249999997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.037644045}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4437573582, "output": 110508092, "answer": 34475699, "reasoning": 76032393}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 34995.05810024947, "answer": 25659.979658440694, "output": 60655.03775869017}, "briefcaseBreakdown": {"overall": {"elo": 1624.56, "lower95ci": 1617.98, "upper95ci": 1632.06}, "rubricPassRate": 0.5797979797979798, "analyticalQuality": {"elo": 1899.55, "lower95ci": 1886.69, "upper95ci": 1913.11}, "presentation": {"elo": 1474, "lower95ci": 1463.3, "upper95ci": 1485.98}}, "briefcaseTotalCost": 1297.7740631642962, "timescaleData": {"medianOutputSpeed": 53.7986830311558, "medianTimeToFirstChunk": 22.2709949235}, "outputSpeedVariance": {"p05": 41.3779758252566, "q25": 44.4570375582914, "median": 53.7986830311558, "q75": 64.1476029006394, "p95": 70.0765005470594}, "timeToFirstChunkVariance": {"p05": 4.37211405740001, "q25": 11.10346134775, "median": 22.2709949235, "q75": 47.17290737625, "p95": 94.3926552075499}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 56.0069152119315, "medianTimeToFirstChunk": 23.079911135, "medianTimeToFirstAnswerToken": 23.079911135, "medianEndToEndResponseTime": 32.007380146781635}, "long": {"medianOutputSpeed": 53.7986830311558, "medianTimeToFirstChunk": 22.2709949235, "medianTimeToFirstAnswerToken": 22.2709949235, "medianEndToEndResponseTime": 31.56490272623266}, "hundredK": {"medianOutputSpeed": 62.5795206064762, "medianTimeToFirstChunk": 18.956082752, "medianTimeToFirstAnswerToken": 18.956082752, "medianEndToEndResponseTime": 26.94591704849757}, "mediumParallel": {"medianOutputSpeed": 51.6739868696944, "medianTimeToFirstChunk": 35.4280487375, "medianTimeToFirstAnswerToken": 35.4280487375, "medianEndToEndResponseTime": 45.104097176743586}}, "endToEndResponseTime": {"input": 22.2709949235, "reasoning": 0, "answer": 9.29390780273266, "total": 31.56490272623266}, "timeToFirstAnswerToken": {"input": 22.2709949235, "reasoning": 0, "total": 22.2709949235}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 3, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "13358187-4584-479c-ab43-5bcdf8f297a4", "slug": "claude-3-7-sonnet-thinking", "name": "Claude 3.7 Sonnet (Reasoning)", "shortName": "Claude 3.7 Sonnet", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-24", "knowledgeCutoffDate": "2024-10-01", "isReasoning": true, "reasoningTokens": 1105, "release": {"slug": "claude-3-7-sonnet", "name": "Claude 3.7 Sonnet"}, "deprecated": true, "deprecatedTo": "claude-4-sonnet-thinking", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 17.7114460194322, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -0.733333333333333, "omniscienceBreakdown": {"accuracy": 0.2803333333333333, "hallucinationRate": 0.3997220935618342}, "gdpval": null, "itBenchSre": null, "tau2": 0.546783625730994, "tauBanking": null, "terminalbenchHard": 0.212121212121212, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.482993197278912, "hle": 0.0967, "gpqa": 0.771717171717172, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.473015873015873, "aime25": 0.563333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "142b93bf-09c4-42dc-9c3a-50b1a222cbd4", "slug": "claude-sonnet-5-low", "name": "Claude Sonnet 5 (Adaptive Reasoning, Low Effort)", "shortName": "Claude Sonnet 5 (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "claude-sonnet-5", "name": "Claude Sonnet 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 24.7426143579597, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 26.821876265615508, "strategyAndOps": 27.09660578053455, "legal": 28.888210279195263, "engineering": 25.762018614919228, "economics": 33.6484342176398}, "omniscience": -8.23333333333333, "omniscienceBreakdown": {"accuracy": 0.3735, "hallucinationRate": 0.7275871242351689}, "gdpPdfAllPass": 0.094, "gdpval": 1145.04, "gdpvalNormalized": 0.32252, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": 0.0252525252525253, "scicode": 0.501157407407407, "lcr": 0.673333333333333, "ifbench": null, "hle": 0.219184430027804, "gpqa": null, "critpt": 0.0457142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.19901936568973871, "price1mInputTokens": 2, "price1mOutputTokens": 10, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": 4.116, "price1mBlended0To3To1": 4, "price1mBlended7To2To1": 1.54, "price1mBlended0To1To1": 6, "price1mBlended100To1To1": 0.3137254901960784, "price1mBlended0To100To1": 2.0792079207920793, "intelligenceIndexTimePerTask": 145.61208471436746, "intelligenceIndexCost": {"total": 652.6980686022611, "input": 399.54038860226103, "nonCacheInput": 69.19011, "cacheRead": 194.70410055632513, "cacheWrite": 135.64617804593595, "output": 253.15768, "reasoning": 122.34334000000001, "answer": 130.81434}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.5087545600633299, "input": 0.35707077919297353, "nonCacheInput": 0.04999636363270444, "cacheRead": 0.2152718829408736, "cacheWrite": 0.09180253261939542, "output": 0.15168378087035633, "reasoning": 0.07100177147120433, "answer": 0.08068200939915204}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.12262041666580274}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0260014572897742}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.015233765062276496}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.2664186366704915}, {"slug": "scicode", "weightedCostPerTask": 0.0013203243055555556}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002559419555143652}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.036668110000000004}, {"slug": "critpt", "weightedCostPerTask": 0.02324640571428572}, {"slug": "omniscience", "weightedCostPerTask": 9.867679999999999e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.014587348}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1062374029, "output": 25315768, "answer": 13081434, "reasoning": 12234334}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 7100.177147120431, "answer": 8068.200939915205, "output": 15168.378087035635}, "briefcaseBreakdown": {"overall": {"elo": 927.41, "lower95ci": 920.69, "upper95ci": 934.5}, "rubricPassRate": 0.24646464646464647, "analyticalQuality": {"elo": 876.82, "lower95ci": 863.91, "upper95ci": 890.9}, "presentation": {"elo": 951.75, "lower95ci": 940.23, "upper95ci": 964.61}}, "briefcaseTotalCost": 74.38971944392033, "timescaleData": {"medianOutputSpeed": 65.2053346992785, "medianTimeToFirstChunk": 1.81553827400006}, "outputSpeedVariance": {"p05": 46.6095787876083, "q25": 53.635661816064, "median": 65.2053346992785, "q75": 81.1041156295049, "p95": 91.5917044329232}, "timeToFirstChunkVariance": {"p05": 0.555614547700017, "q25": 1.15756397574995, "median": 1.81553827400006, "q75": 2.05351552625006, "p95": 3.10968055965001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 68.8328248338977, "medianTimeToFirstChunk": 1.29296445550001, "medianTimeToFirstAnswerToken": 1.29296445550001, "medianEndToEndResponseTime": 8.556940635564727}, "long": {"medianOutputSpeed": 65.2053346992785, "medianTimeToFirstChunk": 1.81553827400006, "medianTimeToFirstAnswerToken": 1.81553827400006, "medianEndToEndResponseTime": 9.483622523639415}, "hundredK": {"medianOutputSpeed": 62.7090738093433, "medianTimeToFirstChunk": 3.0097443225, "medianTimeToFirstAnswerToken": 3.0097443225, "medianEndToEndResponseTime": 10.983072098320264}, "mediumParallel": {"medianOutputSpeed": 62.8086505818516, "medianTimeToFirstChunk": 1.31915546900006, "medianTimeToFirstAnswerToken": 1.31915546900006, "medianEndToEndResponseTime": 9.279842338850974}}, "endToEndResponseTime": {"input": 1.81553827400006, "reasoning": 0, "answer": 7.668084249639356, "total": 9.483622523639415}, "timeToFirstAnswerToken": {"input": 1.81553827400006, "reasoning": 0, "total": 1.81553827400006}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1479f50b-d37f-4b55-bb8b-4212a15042eb", "slug": "mimo-v2-0206", "name": "MiMo-V2-Flash (Feb 2026)", "shortName": "MiMo-V2-Flash (Feb 2026)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "mimo-v2-0206", "name": "MiMo-V2-Flash (Feb 2026)"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 309, "inferenceParametersActiveBillions": 15, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "MIT", "licenseUrl": "https://choosealicense.com/licenses/mit/", "modelWeightsSourceUrl": "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash", "microevalsEnabled": true, "intelligenceIndex": 22.4406462861731, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -19.05, "omniscienceBreakdown": {"accuracy": 0.19783333333333333, "hallucinationRate": 0.48410554747558693}, "gdpval": null, "itBenchSre": null, "tau2": 0.932748538011696, "tauBanking": null, "terminalbenchHard": 0.310606060606061, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.713333333333333, "ifbench": 0.718367346938776, "hle": 0.221037998146432, "gpqa": 0.835353535353535, "critpt": 0.0285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5147c8b4-61d5-4070-9324-8adf8aa144c2", "slug": "xiaomi", "name": "Xiaomi", "logo": "/img/logos/xiaomi_small.svg", "color": "#ff6900", "country": "cn", "url": "https://huggingface.co/XiaomiMiMo"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "149096f3-57b7-4413-80c2-a2c010a2995a", "slug": "glm-5-turbo", "name": "GLM-5-Turbo", "shortName": "GLM-5-Turbo", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-15", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2417, "release": {"slug": "glm-5-turbo", "name": "GLM-5-Turbo"}, "deprecated": true, "deprecatedTo": "glm-5-1-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 26.5965803042835, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -16.3666666666667, "omniscienceBreakdown": {"accuracy": 0.2845, "hallucinationRate": 0.6263685068716516}, "gdpval": null, "itBenchSre": null, "tau2": 0.985380116959064, "tauBanking": null, "terminalbenchHard": 0.333333333333333, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.716666666666667, "ifbench": 0.731972789115646, "hle": 0.277571825764597, "gpqa": 0.847474747474747, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "15b56b8e-7b93-4ed9-ac06-75c922e3b86e", "slug": "ling-1t", "name": "Ling-1T", "shortName": "Ling-1T", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-08", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "ling-1t", "name": "Ling-1T"}, "deprecated": true, "deprecatedTo": "ling-2-6-1t", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1000, "inferenceParametersActiveBillions": 50, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ling-1T", "microevalsEnabled": false, "intelligenceIndex": 9.17207010042254, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -55.1333333333333, "omniscienceBreakdown": {"accuracy": 0.20333333333333334, "hallucinationRate": 0.9472803347280335}, "gdpval": null, "itBenchSre": null, "tau2": 0.327485380116959, "tauBanking": null, "terminalbenchHard": 0.106060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.366666666666667, "ifbench": 0.347619047619048, "hle": 0.0732159406858202, "gpqa": 0.719191919191919, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.677248677248677, "aime25": 0.713333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "16149b9c-a1e9-4669-a5cb-ff3c00d78f89", "slug": "gpt-oss-20b-low", "name": "gpt-oss-20b (low)", "shortName": "gpt-oss-20b (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-05", "knowledgeCutoffDate": "2025-05-31", "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gpt-oss-20b", "name": "gpt-oss-20b"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 21, "inferenceParametersActiveBillions": 3.6, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/openai/gpt-oss-20b", "microevalsEnabled": false, "intelligenceIndex": 9.95295342568922, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -58.55, "omniscienceBreakdown": {"accuracy": 0.15083333333333335, "hallucinationRate": 0.8671246319921492}, "gdpval": null, "itBenchSre": null, "tau2": 0.502923976608187, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.31, "ifbench": 0.578231292517007, "hle": 0.0528266913809083, "gpqa": 0.611111111111111, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.651851851851852, "aime25": 0.623333333333333, "analystAgent": null, "price1mInputTokens": 0.07, "price1mOutputTokens": 0.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.10250000000000001, "price1mBlended7To2To1": 0.083, "price1mBlended0To1To1": 0.135, "price1mBlended100To1To1": 0.07127450980392158, "price1mBlended0To100To1": 0.0712871287128713, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 249.942564526874, "medianTimeToFirstChunk": 0.838273553999898}, "outputSpeedVariance": {"p05": 58.9312111300768, "q25": 148.206550066284, "median": 249.942564526874, "q75": 392.356068988192, "p95": 969.370629123215}, "timeToFirstChunkVariance": {"p05": 0.286596892900014, "q25": 0.601070183499985, "median": 0.838273553999898, "q75": 1.31975755049996, "p95": 24.9248435822}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 240.462130068889, "medianTimeToFirstChunk": 0.483330275000071, "medianTimeToFirstAnswerToken": 8.80064826360405, "medianEndToEndResponseTime": 10.879977760755043}, "long": {"medianOutputSpeed": 249.942564526874, "medianTimeToFirstChunk": 0.838273553999898, "medianTimeToFirstAnswerToken": 8.840111911487657, "medianEndToEndResponseTime": 10.840571500859598}, "hundredK": {"medianOutputSpeed": 180.648122371298, "medianTimeToFirstChunk": 5.857361938, "medianTimeToFirstAnswerToken": 16.928609032886868, "medianEndToEndResponseTime": 19.696420806608582}, "mediumParallel": {"medianOutputSpeed": 180.493799196378, "medianTimeToFirstChunk": 0.488545361499974, "medianTimeToFirstAnswerToken": 11.569258432556733, "medianEndToEndResponseTime": 14.339436700320924}}, "endToEndResponseTime": {"input": 0.838273553999898, "reasoning": 8.00183835748776, "answer": 2.00045958937194, "total": 10.840571500859598}, "timeToFirstAnswerToken": {"input": 0.838273553999898, "reasoning": 8.00183835748776, "total": 8.840111911487657}, "performanceDataSource": {"type": "median"}, "hostModelCount": 9, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "169e47f5-3d4d-4ad4-8f8b-ab46f0c73f67", "slug": "qwen3-5-27b", "name": "Qwen3.5 27B (Reasoning)", "shortName": "Qwen3.5 27B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-5-27b", "name": "Qwen3.5 27B"}, "deprecated": true, "deprecatedTo": "qwen3-6-27b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 27.8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-27B", "microevalsEnabled": false, "intelligenceIndex": 22.8992942688298, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -43.9833333333333, "omniscienceBreakdown": {"accuracy": 0.20666666666666667, "hallucinationRate": 0.8149159663865546}, "gdpval": null, "itBenchSre": 0.354990583804143, "tau2": 0.93859649122807, "tauBanking": null, "terminalbenchHard": 0.325757575757576, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.776666666666667, "ifbench": 0.75578231292517, "hle": 0.239110287303058, "gpqa": 0.857575757575758, "critpt": 0.00853061224489796, "apexAgents": null, "mmmuPro": 0.75028901734104, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.307, "price1mBlended0To3To1": 0.825, "price1mBlended7To2To1": 0.51, "price1mBlended0To1To1": 1.3499999999999999, "price1mBlended100To1To1": 0.3205882352941177, "price1mBlended0To100To1": 0.3207920792079208, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 77.5582582115256, "medianTimeToFirstChunk": 5.65613527199998}, "outputSpeedVariance": {"p05": 64.6248214038502, "q25": 75.1101412771223, "median": 77.5582582115256, "q75": 79.9334847824075, "p95": 85.2632645849303}, "timeToFirstChunkVariance": {"p05": 5.4927370403, "q25": 5.55665368900003, "median": 5.65613527199998, "q75": 6.38840302924999, "p95": 8.19415800365001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 77.5582582115256, "medianTimeToFirstChunk": 5.65613527199998, "medianTimeToFirstAnswerToken": 31.443202260345377, "medianEndToEndResponseTime": 37.88996900743172}}, "endToEndResponseTime": {"input": 5.65613527199998, "reasoning": 25.787066988345398, "answer": 6.4467667470863494, "total": 37.88996900743172}, "timeToFirstAnswerToken": {"input": 5.65613527199998, "reasoning": 25.787066988345398, "total": 31.443202260345377}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 5, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "16c5b637-8bce-4252-81f2-1b87a36a4e4c", "slug": "o3", "name": "o3", "shortName": "o3", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-16", "knowledgeCutoffDate": "2024-05-31", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "o3", "name": "o3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 20.200754789201, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -15.55, "omniscienceBreakdown": {"accuracy": 0.38566666666666666, "hallucinationRate": 0.8809007053716766}, "gdpval": null, "itBenchSre": null, "tau2": 0.807017543859649, "tauBanking": null, "terminalbenchHard": 0.371212121212121, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.746666666666667, "ifbench": 0.714285714285714, "hle": 0.2005, "gpqa": 0.827272727272727, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": 0.700578034682081, "livecodebench": 0.808465608465608, "aime25": 0.883333333333333, "analystAgent": null, "price1mInputTokens": 2, "price1mOutputTokens": 8, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": 6.75, "price1mBlended0To3To1": 3.5, "price1mBlended7To2To1": 1.55, "price1mBlended0To1To1": 5, "price1mBlended100To1To1": 0.5882352941176471, "price1mBlended0To100To1": 2.0594059405940595, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 132.971863067058, "medianTimeToFirstChunk": 7.13368453549992}, "outputSpeedVariance": {"p05": 76.2111851228353, "q25": 101.095802703957, "median": 132.971863067058, "q75": 149.213919975188, "p95": 182.585696144513}, "timeToFirstChunkVariance": {"p05": 3.81063291419997, "q25": 4.79981864800004, "median": 7.13368453549992, "q75": 11.62188145325, "p95": 16.18693783745}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 125.996765925103, "medianTimeToFirstChunk": 6.75219627399997, "medianTimeToFirstAnswerToken": 6.75219627399997, "medianEndToEndResponseTime": 10.720552099078988}, "long": {"medianOutputSpeed": 132.971863067058, "medianTimeToFirstChunk": 7.13368453549992, "medianTimeToFirstAnswerToken": 7.13368453549992, "medianEndToEndResponseTime": 10.893878522914001}, "hundredK": {"medianOutputSpeed": 97.3772758142164, "medianTimeToFirstChunk": 5.818883666, "medianTimeToFirstAnswerToken": 5.818883666, "medianEndToEndResponseTime": 10.953551850330161}, "mediumParallel": {"medianOutputSpeed": 136.758729800965, "medianTimeToFirstChunk": 5.56683226649995, "medianTimeToFirstAnswerToken": 5.56683226649995, "medianEndToEndResponseTime": 9.222906001081183}}, "endToEndResponseTime": {"input": 7.13368453549992, "reasoning": 0, "answer": 3.7601939874140813, "total": 10.893878522914001}, "timeToFirstAnswerToken": {"input": 7.13368453549992, "reasoning": 0, "total": 7.13368453549992}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 3, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "16f2578b-1b28-4be3-b371-700c2677bcd6", "slug": "gemini-1-5-pro-may-2024", "name": "Gemini 1.5 Pro (May '24)", "shortName": "Gemini 1.5 Pro (May)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-05-15", "knowledgeCutoffDate": "2023-11-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-1-5-pro-may-24", "name": "Gemini 1.5 Pro (May '24)"}, "deprecated": true, "deprecatedTo": "gemini-2-0-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.4407131644479, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0348, "gpqa": 0.370707070707071, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.244444444444444, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "18721247-4e56-4cf7-9a9d-c71cc60c0961", "slug": "k-exaone-2-0-0803", "name": "K-EXAONE 2.0 0803", "shortName": "K-EXAONE 2.0", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "k-exaone-2-0-0803", "name": "K-EXAONE 2.0 0803"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 750, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "apache-2.0", "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 19.6904943371003, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -6.6, "omniscienceBreakdown": {"accuracy": 0.1305, "hallucinationRate": 0.2259919493962047}, "gdpval": 918, "gdpvalNormalized": 0.209, "itBenchSre": null, "tau2": null, "tauBanking": 0.115463917525773, "terminalbenchHard": null, "terminalBench21": 0.404494382022472, "terminalBench40": null, "scicode": 0.420138888888889, "lcr": 0.6, "ifbench": null, "hle": 0.185820203892493, "gpqa": 0.829292929292929, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "45157c16-fcbb-4110-b20f-7bca754b6554", "slug": "lg", "name": "LG AI Research", "logo": "/img/logos/lg_small.png", "color": "#df3b8a", "country": "kr", "url": "https://www.lgresearch.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "191a2097-cce3-49cf-881e-0c790892059f", "slug": "qwen3-4b-instruct-reasoning", "name": "Qwen3 4B (Reasoning)", "shortName": "Qwen3 4B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-4b-instruct", "name": "Qwen3 4B"}, "deprecated": true, "deprecatedTo": "qwen3-4b-2507-instruct-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 4.02, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-4B", "microevalsEnabled": false, "intelligenceIndex": 7.22847163984467, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.190058479532164, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.325170068027211, "hle": 0.0442, "gpqa": 0.522222222222222, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.464550264550264, "aime25": 0.223333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "19496b81-9f41-4214-a77a-1df803b3c5ae", "slug": "glm-5-3-flash", "name": "GLM 5.3 Flash", "shortName": "GLM-5.3-Flash", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-08-26", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "glm-5-3-flash", "name": "GLM 5.3 Flash"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 320, "inferenceParametersActiveBillions": 18, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-5.3-Flash", "microevalsEnabled": true, "intelligenceIndex": 41.907366113455, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 41.9817401866044, "strategyAndOps": 45.16018300140284, "legal": 39.922315233599434, "healthcareAndMedical": 44.859244252149146, "engineering": 43.843285321104595, "economics": 48.89497509267839}, "omniscience": 7.46666666666667, "omniscienceBreakdown": {"accuracy": 0.275, "hallucinationRate": 0.27632183908045976}, "mlcrOverall": 0.511111111111111, "gdpPdfAllPass": 0.154, "gdpval": 1654.95, "gdpvalNormalized": 0.5774750000000001, "itBenchSre": null, "tau2": null, "tauBanking": 0.472164948453608, "terminalbenchHard": null, "terminalBench21": 0.842696629213483, "terminalBench40": 0.328282828282828, "scicode": 0.516203703703704, "lcr": 0.8, "ifbench": null, "hle": 0.398517145505097, "gpqa": 0.912121212121212, "critpt": 0.154285714285714, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.6036862782167782, "enterpriseOpsGym": 0.3321396598030439, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.5, "cacheHitPrice": 0.026, "cacheHitDiscountPercent": 0.8266666666666667, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.2375, "price1mBlended7To2To1": 0.0982, "price1mBlended0To1To1": 0.325, "price1mBlended100To1To1": 0.031862745098039214, "price1mBlended0To100To1": 0.15346534653465346, "intelligenceIndexTimePerTask": 491.5178396978873, "intelligenceIndexCost": {"total": 280.28213741916164, "input": 189.94139941916163, "nonCacheInput": 4.2896787, "cacheRead": 164.02214144840158, "cacheWrite": 21.629579270760043, "output": 90.340738, "reasoning": 75.7282435, "answer": 14.6124945}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.2532595604307378, "input": 0.21892298440247968, "nonCacheInput": 0.003296984324158392, "cacheRead": 0.19717920806761985, "cacheWrite": 0.01844679201070141, "output": 0.034336576028258216, "reasoning": 0.023324742592247094, "answer": 0.01101183343601111}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.1304647215981877}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.03039125344423236}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0015198492269076409}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.0789998985313891}, {"slug": "scicode", "weightedCostPerTask": 0.0013985710069444445}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002165517108433735}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0031873035500000002}, {"slug": "critpt", "weightedCostPerTask": 0.004199942857142857}, {"slug": "omniscience", "weightedCostPerTask": 8.973728249999998e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0008427658249999999}]}, "canonicalIntelligenceIndexTokenCount": {"input": 6481338955, "output": 180681476, "answer": 29224989, "reasoning": 151456487}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 46649.4851844942, "answer": 22023.666872022226, "output": 68673.15205651642}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1448.95, "lower95ci": 1440.3, "upper95ci": 1457.86}, "rubricPassRate": 0.4635897435897436, "analyticalQuality": {"elo": 1634.74, "lower95ci": 1618.4, "upper95ci": 1651.74}, "presentation": {"elo": 1397.98, "lower95ci": 1385.86, "upper95ci": 1410.97}}, "briefcaseTotalCost": 79.1485977695672, "timescaleData": {"medianOutputSpeed": 117.247636125543, "medianTimeToFirstChunk": 2.29993430850004}, "outputSpeedVariance": {"p05": 80.7012498495087, "q25": 100.724365929777, "median": 117.247636125543, "q75": 126.027392324443, "p95": 140.8869456207}, "timeToFirstChunkVariance": {"p05": 2.01323691875, "q25": 2.1573642235, "median": 2.29993430850004, "q75": 2.53767521500006, "p95": 2.73701234079991}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 109.77779976955, "medianTimeToFirstChunk": 2.0601702705, "medianTimeToFirstAnswerToken": 20.278790102546925, "medianEndToEndResponseTime": 24.833445060558656}, "long": {"medianOutputSpeed": 117.247636125543, "medianTimeToFirstChunk": 2.29993430850004, "medianTimeToFirstAnswerToken": 19.35784750905701, "medianEndToEndResponseTime": 23.622325809196248}, "hundredK": {"medianOutputSpeed": 104.659760453009, "medianTimeToFirstChunk": 7.59260786850004, "medianTimeToFirstAnswerToken": 26.70214902685169, "medianEndToEndResponseTime": 31.479534316439604}, "mediumParallel": {"medianOutputSpeed": 89.7613903249698, "medianTimeToFirstChunk": 2.15347999650001, "medianTimeToFirstAnswerToken": 24.43477480219823, "medianEndToEndResponseTime": 30.005098503622786}}, "endToEndResponseTime": {"input": 2.29993430850004, "reasoning": 17.057913200556968, "answer": 4.264478300139242, "total": 23.622325809196248}, "timeToFirstAnswerToken": {"input": 2.29993430850004, "reasoning": 17.057913200556968, "total": 19.35784750905701}, "performanceDataSource": {"type": "firstParty", "providerName": "Z AI"}, "hostModelCount": 18, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "198b717f-42c8-4ab7-a699-ae9373d669d3", "slug": "deepseek-v3-1-reasoning", "name": "DeepSeek V3.1 (Reasoning)", "shortName": "DeepSeek V3.1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-21", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-v3-1", "name": "DeepSeek V3.1"}, "deprecated": true, "deprecatedTo": "deepseek-v3-1-terminus-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "microevalsEnabled": false, "intelligenceIndex": 13.4758123489932, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -29.5833333333333, "omniscienceBreakdown": {"accuracy": 0.29, "hallucinationRate": 0.8251173708920188}, "gdpval": null, "itBenchSre": null, "tau2": 0.374269005847953, "tauBanking": null, "terminalbenchHard": 0.25, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.566666666666667, "ifbench": 0.414965986394558, "hle": 0.142724745134384, "gpqa": 0.778787878787879, "critpt": 0.02, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.784126984126984, "aime25": 0.896666666666667, "analystAgent": null, "price1mInputTokens": 0.59, "price1mOutputTokens": 1.69, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.865, "price1mBlended7To2To1": 0.7, "price1mBlended0To1To1": 1.14, "price1mBlended100To1To1": 0.6007843137254902, "price1mBlended0To100To1": 0.6008910891089109, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 4, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1a8ba535-df18-459b-ad40-3199191296d7", "slug": "llama-3-3-nemotron-super-49b-reasoning", "name": "Llama 3.3 Nemotron Super 49B v1 (Reasoning)", "shortName": "Llama 3.3 Nemotron Super 49B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-18", "knowledgeCutoffDate": "2023-12-01", "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "llama-3-3-nemotron-super-49b", "name": "Llama 3.3 Nemotron Super 49B v1"}, "deprecated": true, "deprecatedTo": "llama-nemotron-super-49b-v1-5-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 49, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "NVIDIA Open Model License Agreement", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1", "microevalsEnabled": false, "intelligenceIndex": 8.93313646948331, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -58.3, "omniscienceBreakdown": {"accuracy": 0.171, "hallucinationRate": 0.9095295536791315}, "gdpval": null, "itBenchSre": null, "tau2": 0.269005847953216, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.183333333333333, "ifbench": 0.380952380952381, "hle": 0.0562, "gpqa": 0.643434343434343, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.277248677248677, "aime25": 0.546666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 52.77777777777778, "modelAvailability": 4, "transparencyMethodology": 4, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1aa3694e-b656-4dbe-8f84-0c65d8897abb", "slug": "step-3-5-flash", "name": "Step 3.5 Flash 2603", "shortName": "Step 3.5 Flash 2603", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "step-3-5-flash", "name": "Step 3.5 Flash 2603"}, "deprecated": true, "deprecatedTo": "step-3-7-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 16.964120603515, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -44.2166666666667, "omniscienceBreakdown": {"accuracy": 0.24616666666666667, "hallucinationRate": 0.9131107671899182}, "gdpval": null, "itBenchSre": null, "tau2": 0.874269005847953, "tauBanking": null, "terminalbenchHard": 0.325757575757576, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.63, "ifbench": 0.66530612244898, "hle": 0.244670991658943, "gpqa": 0.826262626262626, "critpt": 0.0228571428571429, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.3, "cacheHitPrice": 0.02, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15000000000000002, "price1mBlended7To2To1": 0.064, "price1mBlended0To1To1": 0.2, "price1mBlended100To1To1": 0.023529411764705882, "price1mBlended0To100To1": 0.10198019801980199, "timescaleData": {"medianOutputSpeed": 122.782566635924, "medianTimeToFirstChunk": 3.41110853349997}, "outputSpeedVariance": {"p05": 82.871318840227, "q25": 112.597588227994, "median": 122.782566635924, "q75": 148.172427025057, "p95": 194.910268836717}, "timeToFirstChunkVariance": {"p05": 2.92367919269998, "q25": 3.23505295850001, "median": 3.41110853349997, "q75": 3.58958214524995, "p95": 7.20456443379996}, "performanceByPromptType": {"long": {"medianOutputSpeed": 122.782566635924, "medianTimeToFirstChunk": 3.41110853349997, "medianTimeToFirstAnswerToken": 19.700065954714486, "medianEndToEndResponseTime": 23.772305310018115}}, "endToEndResponseTime": {"input": 3.41110853349997, "reasoning": 16.288957421214516, "answer": 4.072239355303629, "total": 23.772305310018115}, "timeToFirstAnswerToken": {"input": 3.41110853349997, "reasoning": 16.288957421214516, "total": 19.700065954714486}, "performanceDataSource": {"type": "firstParty", "providerName": "StepFun"}, "hostModelCount": 1, "creator": {"id": "ce2e2e8b-7a22-4020-98ec-8ef71000dd42", "slug": "stepfun", "name": "StepFun", "logo": "/img/logos/stepfun_small.svg", "color": "#017AFF", "country": "cn", "url": "https://www.stepfun.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1b05e346-e86a-4a20-8feb-7da8c65a99aa", "slug": "mistral-large-2407", "name": "Mistral Large 2 (Jul '24)", "shortName": "Mistral Large 2 (Jul)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-07-24", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-large-2407", "name": "Mistral Large 2 (Jul '24)"}, "deprecated": true, "deprecatedTo": "mistral-large-2", "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 123, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "Mistral Research License", "licenseUrl": "https://mistral.ai/licenses/MRL-0.1.md", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-Large-Instruct-2407", "microevalsEnabled": false, "intelligenceIndex": 6.7994617527877, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.330409356725146, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.02, "ifbench": 0.316326530612245, "hle": 0.0295, "gpqa": 0.471717171717172, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.266666666666667, "aime25": 0, "analystAgent": null, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 2.4, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 2.0392156862745097, "price1mBlended0To100To1": 2.0396039603960396, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1b64aa81-c223-4b8f-909b-82185a234765", "slug": "solar-pro4", "name": "Solar Pro 4", "shortName": "Solar Pro 4", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-06", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "solar-pro4", "name": "Solar Pro 4"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 512000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 28.1541333537469, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -0.85, "omniscienceBreakdown": {"accuracy": 0.18933333333333333, "hallucinationRate": 0.24403782894736842}, "gdpPdfAllPass": 0.056, "gdpval": 1172.77, "gdpvalNormalized": 0.336385, "itBenchSre": null, "tau2": null, "tauBanking": 0.232989690721649, "terminalbenchHard": null, "terminalBench21": 0.573033707865168, "terminalBench40": 0.00505050505050505, "scicode": 0.445601851851852, "lcr": 0.74, "ifbench": null, "hle": 0.292400370713624, "gpqa": 0.890909090909091, "critpt": 0.0542857142857143, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.09082506839361529, "price1mInputTokens": 0.3, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.06, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5249999999999999, "price1mBlended7To2To1": 0.22199999999999998, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.07352941176470588, "price1mBlended0To100To1": 0.3089108910891089, "timescaleData": {"medianOutputSpeed": 71.3222331486767, "medianTimeToFirstChunk": 2.00354607849982}, "outputSpeedVariance": {"p05": 38.9400717329457, "q25": 56.9447376898162, "median": 71.3222331486767, "q75": 84.6421393630909, "p95": 96.6172494663976}, "timeToFirstChunkVariance": {"p05": 1.7011964272499, "q25": 1.82225028524999, "median": 2.00354607849982, "q75": 2.33544252850004, "p95": 11.6962251507999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 59.1091640980035, "medianTimeToFirstChunk": 1.18317522050001, "medianTimeToFirstAnswerToken": 35.018876173468705, "medianEndToEndResponseTime": 43.477801411710885}, "long": {"medianOutputSpeed": 71.3222331486767, "medianTimeToFirstChunk": 2.00354607849982, "medianTimeToFirstAnswerToken": 30.045292834113116, "medianEndToEndResponseTime": 37.05572952301644}, "hundredK": {"medianOutputSpeed": 58.7569880218457, "medianTimeToFirstChunk": 6.27503530850001, "medianTimeToFirstAnswerToken": 40.31353978828044, "medianEndToEndResponseTime": 48.82316590822555}, "mediumParallel": {"medianOutputSpeed": 76.4809372651185, "medianTimeToFirstChunk": 1.10856591800018, "medianTimeToFirstAnswerToken": 27.2588730601194, "medianEndToEndResponseTime": 33.7964498456492}}, "endToEndResponseTime": {"input": 2.00354607849982, "reasoning": 28.041746755613296, "answer": 7.010436688903324, "total": 37.05572952301644}, "timeToFirstAnswerToken": {"input": 2.00354607849982, "reasoning": 28.041746755613296, "total": 30.045292834113116}, "performanceDataSource": {"type": "firstParty", "providerName": "Upstage"}, "hostModelCount": 1, "creator": {"id": "64ff7f06-c6fb-42ea-ba24-9cd103ab2d61", "slug": "upstage", "name": "Upstage", "logo": "/img/logos/upstage_small.svg", "color": "#7c59f5", "country": "kr", "url": "https://www.upstage.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1cb96708-f6c1-4668-9804-5db6ecac01ed", "slug": "dbrx", "name": "DBRX Instruct", "shortName": "DBRX", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-03-27", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "dbrx", "name": "DBRX Instruct"}, "deprecated": true, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 132, "inferenceParametersActiveBillions": 36, "sizeClass": "medium", "contextWindowTokens": 32768, "licenseName": "Databricks Open Model License", "licenseUrl": "https://www.databricks.com/legal/open-model-license", "modelWeightsSourceUrl": "https://huggingface.co/databricks/dbrx-instruct", "microevalsEnabled": false, "intelligenceIndex": 5.28869837981177, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0292, "gpqa": 0.331313131313131, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0931216931216931, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "650e5ce8-a549-4207-bbd4-9c4815bc2d49", "slug": "databricks", "name": "Databricks", "logo": "/img/logos/databricks_small.png", "color": "#e4462f", "country": "us", "url": "https://www.databricks.com/product/machine-learning"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1cf439b8-0cfd-47b2-9de2-9a2157e6762b", "slug": "glm-4.5", "name": "GLM-4.5 (Reasoning)", "shortName": "GLM-4.5", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "glm-4-5", "name": "GLM-4.5"}, "deprecated": true, "deprecatedTo": "glm-4-6-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 355, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://huggingface.co/zai-org/GLM-4.5", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-4.5", "microevalsEnabled": false, "intelligenceIndex": 12.7680269610265, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -27.3833333333333, "omniscienceBreakdown": {"accuracy": 0.25133333333333335, "hallucinationRate": 0.7014692787177204}, "gdpval": null, "itBenchSre": null, "tau2": 0.429824561403509, "tauBanking": null, "terminalbenchHard": 0.21969696969697, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.526666666666667, "ifbench": 0.440816326530612, "hle": 0.129749768303985, "gpqa": 0.781818181818182, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.737566137566138, "aime25": 0.736666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 55.55555555555556, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1d0db5a3-3132-4213-a94b-c2e395d08283", "slug": "qwen2.5-32b-instruct", "name": "Qwen2.5 Instruct 32B", "shortName": "Qwen2.5 Instruct 32B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-19", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen2.5-32b-instruct", "name": "Qwen2.5 Instruct 32B"}, "deprecated": true, "deprecatedTo": "qwen3-32b-instruct", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen2.5-32B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 6.87156485936671, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0399, "gpqa": 0.465656565656566, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.247619047619048, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1d81aa1c-64c8-442a-9c41-81b37e407b91", "slug": "gemini-2-5-flash-lite", "name": "Gemini 2.5 Flash-Lite (Non-reasoning)", "shortName": "Gemini 2.5 Flash-Lite (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-17", "knowledgeCutoffDate": "2025-01-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-flash-lite", "name": "Gemini 2.5 Flash-Lite"}, "deprecated": true, "deprecatedTo": "gemini-2-5-flash-lite-preview-09-2025", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.66853092464521, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -58.7833333333333, "omniscienceBreakdown": {"accuracy": 0.15433333333333332, "hallucinationRate": 0.87761135199054}, "gdpval": null, "itBenchSre": null, "tau2": 0.190058479532164, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.32, "ifbench": 0.314965986394558, "hle": 0.0366079703429101, "gpqa": 0.473737373737374, "critpt": 0, "apexAgents": null, "mmmuPro": 0.539884393063584, "livecodebench": 0.4, "aime25": 0.353333333333333, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.01, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.1032, "price1mBlended0To3To1": 0.17500000000000002, "price1mBlended7To2To1": 0.067, "price1mBlended0To1To1": 0.25, "price1mBlended100To1To1": 0.014705882352941176, "price1mBlended0To100To1": 0.10297029702970298, "timescaleData": {"medianOutputSpeed": 327.764342659023, "medianTimeToFirstChunk": 0.310349673999994}, "outputSpeedVariance": {"p05": 230.451627407341, "q25": 265.508104345387, "median": 327.764342659023, "q75": 358.625654435231, "p95": 399.848497718559}, "timeToFirstChunkVariance": {"p05": 0.256304068349982, "q25": 0.271444247750004, "median": 0.310349673999994, "q75": 0.349082349750017, "p95": 1.20226697420001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 327.764342659023, "medianTimeToFirstChunk": 0.310349673999994, "medianTimeToFirstAnswerToken": 0.310349673999994, "medianEndToEndResponseTime": 1.8358359302037561}}, "endToEndResponseTime": {"input": 0.310349673999994, "reasoning": 0, "answer": 1.525486256203762, "total": 1.8358359302037561}, "timeToFirstAnswerToken": {"input": 0.310349673999994, "reasoning": 0, "total": 0.310349673999994}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1dcea4f7-7e8b-49f8-abe2-5860ff9f349e", "slug": "hermes-3-llama-3-1-70b", "name": "Hermes 3 - Llama-3.1 70B", "shortName": "Hermes 3 - Llama-3.1 70B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-08-15", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "hermes-3-llama-3-1-70b", "name": "Hermes 3 - Llama-3.1 70B"}, "deprecated": true, "deprecatedTo": "hermes-4-llama-3-1-70b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 70.6, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.1 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B", "microevalsEnabled": false, "intelligenceIndex": 5.99680149700574, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0399, "gpqa": 0.401010101010101, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.188359788359788, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.7, "price1mOutputTokens": 0.7, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.7, "price1mBlended7To2To1": 0.7, "price1mBlended0To1To1": 0.7, "price1mBlended100To1To1": 0.7000000000000001, "price1mBlended0To100To1": 0.7000000000000001, "timescaleData": {"medianOutputSpeed": 30.236622747792, "medianTimeToFirstChunk": 2.10487121149998}, "outputSpeedVariance": {"p05": 19.1474691274222, "q25": 28.8115901998521, "median": 30.236622747792, "q75": 32.840277544127, "p95": 34.0440027800855}, "timeToFirstChunkVariance": {"p05": 1.86013365634997, "q25": 1.94649683225003, "median": 2.10487121149998, "q75": 2.51000776675001, "p95": 3.46715083049979}, "performanceByPromptType": {"long": {"medianOutputSpeed": 30.236622747792, "medianTimeToFirstChunk": 2.10487121149998, "medianTimeToFirstAnswerToken": 2.10487121149998, "medianEndToEndResponseTime": 18.641109539787223}}, "endToEndResponseTime": {"input": 2.10487121149998, "reasoning": 0, "answer": 16.536238328287244, "total": 18.641109539787223}, "timeToFirstAnswerToken": {"input": 2.10487121149998, "reasoning": 0, "total": 2.10487121149998}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0a2f41cc-2cbc-4949-be54-9fef1319d4a9", "slug": "nous-research", "name": "Nous Research", "logo": "/img/logos/nousresearch_small.jpg", "color": "#006fa8", "country": "us", "url": "https://nousresearch.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1e9907e0-ffac-4595-b006-962e4f1da7cf", "slug": "north-mini-code", "name": "North Mini Code", "shortName": "North Mini Code", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "north-mini-code", "name": "North Mini Code"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/CohereLabs/North-Mini-Code-1.0", "microevalsEnabled": true, "intelligenceIndex": 9.91462776590372, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 9.140184243651095, "strategyAndOps": 5.920013653477286, "legal": 9.931675820153792, "engineering": 13.924875144935381, "economics": 14.79949755130476}, "omniscience": -48.5833333333333, "omniscienceBreakdown": {"accuracy": 0.189, "hallucinationRate": 0.8321002877106453}, "gdpPdfAllPass": 0.018, "gdpval": 471.64, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.374269005847953, "tauBanking": 0.0639175257731959, "terminalbenchHard": 0.310606060606061, "terminalBench21": 0.355805243445693, "terminalBench40": 0.00505050505050505, "scicode": 0.387731481481481, "lcr": 0.373333333333333, "ifbench": 0.575510204081633, "hle": 0.110750695088044, "gpqa": 0.756565656565657, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.014912858603711226, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "intelligenceIndexTimePerTask": 262.347970942596, "intelligenceIndexCost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "intelligenceIndexCostPerTask": {"cost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0}, {"slug": "gdpval-aa", "weightedCostPerTask": 0}, {"slug": "automationbench-aa", "weightedCostPerTask": 0}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0}, {"slug": "scicode", "weightedCostPerTask": 0}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0}, {"slug": "gdp-pdf", "weightedCostPerTask": 0}, {"slug": "critpt", "weightedCostPerTask": 0}, {"slug": "omniscience", "weightedCostPerTask": 0}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0}]}, "canonicalIntelligenceIndexTokenCount": {"input": 903747242, "output": 81537442, "answer": 9967973, "reasoning": 71569469}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 10552.932382862688, "answer": 7802.356050504403, "output": 18355.28843336709}, "openness": {"opennessIndex": 41.666666666666664, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 234.19, "lower95ci": 224.51, "upper95ci": 242.14}, "rubricPassRate": 0.06230847803881512, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 142.93, "lower95ci": 125.98, "upper95ci": 159.55}}, "briefcaseTotalCost": 0, "timescaleData": {"medianOutputSpeed": 76.1061007083298, "medianTimeToFirstChunk": 0.385678121999945}, "outputSpeedVariance": {"p05": 37.4721148775935, "q25": 60.1657457427118, "median": 76.1061007083298, "q75": 85.8852684985193, "p95": 133.927061497293}, "timeToFirstChunkVariance": {"p05": 0.26110724450009, "q25": 0.312109961249917, "median": 0.385678121999945, "q75": 0.490478128999981, "p95": 0.728332054399988}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 71.6639719945584, "medianTimeToFirstChunk": 0.207070783999996, "medianTimeToFirstAnswerToken": 28.115096872085992, "medianEndToEndResponseTime": 35.09210339410749}, "long": {"medianOutputSpeed": 76.1061007083298, "medianTimeToFirstChunk": 0.385678121999945, "medianTimeToFirstAnswerToken": 26.664780340951232, "medianEndToEndResponseTime": 33.234555895689056}, "hundredK": {"medianOutputSpeed": 124.868430545686, "medianTimeToFirstChunk": 2.08255348900002, "medianTimeToFirstAnswerToken": 18.099412123803265, "medianEndToEndResponseTime": 22.103626782504076}, "mediumParallel": {"medianOutputSpeed": 96.818878517052, "medianTimeToFirstChunk": 0.255472007999969, "medianTimeToFirstAnswerToken": 20.912600355626456, "medianEndToEndResponseTime": 26.07688244253308}}, "endToEndResponseTime": {"input": 0.385678121999945, "reasoning": 26.279102218951287, "answer": 6.569775554737822, "total": 33.234555895689056}, "timeToFirstAnswerToken": {"input": 0.385678121999945, "reasoning": 26.279102218951287, "total": 26.664780340951232}, "performanceDataSource": {"type": "firstParty", "providerName": "Cohere"}, "hostModelCount": 1, "creator": {"id": "671d3708-c407-4b8f-b350-f728e4689d26", "slug": "cohere", "name": "Cohere", "logo": "/img/logos/cohere_small.svg", "color": "#D18EE2", "country": "ca", "url": "https://cohere.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1edc272c-d799-44d6-909a-bf3c1909a3a0", "slug": "sonar-reasoning-pro", "name": "Sonar Reasoning Pro", "shortName": "Sonar Reasoning Pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "sonar-reasoning-pro", "name": "Sonar Reasoning Pro"}, "deprecated": true, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 127000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.8218357445928, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "941fc0f0-1d4e-405a-95b2-2d49494e0e6c", "slug": "perplexity", "name": "Perplexity", "logo": "/img/logos/perplexity.svg", "color": "#1B818E", "country": "us", "url": "https://perplexity.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1f054429-397e-4fdb-9e71-67bc92c1735e", "slug": "gpt-5-5", "name": "GPT-5.5 (xhigh)", "shortName": "GPT-5.5 (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-23", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-5", "name": "GPT-5.5"}, "deprecated": true, "deprecatedTo": "gpt-5-6-sol-xhigh", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 922000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 38.6291937590607, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 41.932765023079206, "strategyAndOps": 45.67846602784016, "legal": 45.02602199038892, "healthcareAndMedical": 38.81989442807871, "engineering": 40.14906814791633, "economics": 48.171013052208835}, "omniscience": 20.5166666666667, "omniscienceBreakdown": {"accuracy": 0.5795, "hallucinationRate": 0.890210067380103}, "mlcrOverall": 0.177777777777778, "harveyLab": 0.862787668258793, "gdpPdfAllPass": 0.212, "gdpval": 1395.85, "gdpvalNormalized": 0.44792499999999996, "itBenchSre": 0.458097928436911, "tau2": 0.93859649122807, "tauBanking": 0.389690721649485, "terminalbenchHard": 0.606060606060606, "terminalBench21": 0.842696629213483, "terminalBench40": 0.146464646464646, "scicode": 0.55787037037037, "lcr": 0.843333333333333, "ifbench": 0.758503401360544, "hle": 0.457831325301205, "gpqa": 0.935353535353535, "critpt": 0.271428571428571, "apexAgents": 0.376843657817109, "mmmuPro": 0.798843930635838, "livecodebench": null, "aime25": null, "analystAgent": 0.5, "automationBenchPartialScore": 0.4730056587293313, "enterpriseOpsGym": 0.4664279319606088, "price1mInputTokens": 5, "price1mOutputTokens": 30, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 5.12, "price1mBlended0To3To1": 11.25, "price1mBlended7To2To1": 4.35, "price1mBlended0To1To1": 17.5, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 5.247524752475248, "intelligenceIndexTimePerTask": 262.0929525974217, "intelligenceIndexCost": {"total": 5294.3643471784235, "input": 2666.196587178424, "nonCacheInput": 138.557445, "cacheRead": 657.3146980912862, "cacheWrite": 1870.324444087138, "output": 2628.16776, "reasoning": 2246.36784, "answer": 381.79992}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.6339796841243297, "input": 1.9242313294107678, "nonCacheInput": 0.10334944568237052, "cacheRead": 0.49675990906095996, "cacheWrite": 1.3241219746674369, "output": 0.7097483547135619, "reasoning": 0.46282767869968644, "answer": 0.24692067601387552}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.7720536328844316}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.2185277565229377}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.11669202114999608}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.1562489484350371}, {"slug": "scicode", "weightedCostPerTask": 0.016845909722222222}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.03801581533827618}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.10552215000000001}, {"slug": "critpt", "weightedCostPerTask": 0.1613401285714286}, {"slug": "omniscience", "weightedCostPerTask": 0.0227353215}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.025997999999999997}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1716405774, "output": 87605592, "answer": 12726664, "reasoning": 74878928}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 15427.589289989548, "answer": 8230.689200462515, "output": 23658.278490452063}, "briefcaseBreakdown": {"overall": {"elo": 1135.79, "lower95ci": 1129.47, "upper95ci": 1142.29}, "rubricPassRate": 0.33438818565400846, "analyticalQuality": {"elo": 1189.93, "lower95ci": 1178.61, "upper95ci": 1201.08}, "presentation": {"elo": 1102.64, "lower95ci": 1092.46, "upper95ci": 1114.53}}, "briefcaseTotalCost": 468.3792039498885, "timescaleData": {"medianOutputSpeed": 90.8089127551576, "medianTimeToFirstChunk": 37.9551744819999}, "outputSpeedVariance": {"p05": 62.0205592541308, "q25": 73.0798547380164, "median": 90.8089127551576, "q75": 107.680113159272, "p95": 133.640282903329}, "timeToFirstChunkVariance": {"p05": 15.7969528834501, "q25": 22.15553671725, "median": 37.9551744819999, "q75": 75.64361739025, "p95": 206.568434962}, "performanceByPromptType": {"long": {"medianOutputSpeed": 90.8089127551576, "medianTimeToFirstChunk": 37.9551744819999, "medianTimeToFirstAnswerToken": 37.9551744819999, "medianEndToEndResponseTime": 43.461241946414084}}, "endToEndResponseTime": {"input": 37.9551744819999, "reasoning": 0, "answer": 5.50606746441419, "total": 43.461241946414084}, "timeToFirstAnswerToken": {"input": 37.9551744819999, "reasoning": 0, "total": 37.9551744819999}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1f05af98-1ec6-4506-a0b8-57a8c9b63878", "slug": "mistral-medium", "name": "Mistral Medium", "shortName": "Mistral Medium", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-12-11", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-medium", "name": "Mistral Medium"}, "deprecated": true, "deprecatedTo": "mistral-medium-3", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 32768, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.49191510422431, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0351, "gpqa": 0.349494949494949, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0994708994708995, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.5, "price1mOutputTokens": 7.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 2.1, "price1mBlended0To1To1": 4.5, "price1mBlended100To1To1": 1.5588235294117647, "price1mBlended0To100To1": 1.5594059405940595, "timescaleData": {"medianOutputSpeed": 131.574767773454, "medianTimeToFirstChunk": 2.24821114699997}, "outputSpeedVariance": {"p05": 78.5141865132804, "q25": 102.283143813293, "median": 131.574767773454, "q75": 156.612429072452, "p95": 183.243343185056}, "timeToFirstChunkVariance": {"p05": 2.1352498266, "q25": 2.17133280700005, "median": 2.24821114699997, "q75": 2.31948920174994, "p95": 2.69863670579992}, "performanceByPromptType": {"long": {"medianOutputSpeed": 131.574767773454, "medianTimeToFirstChunk": 2.24821114699997, "medianTimeToFirstAnswerToken": 2.24821114699997, "medianEndToEndResponseTime": 6.048331857536979}}, "endToEndResponseTime": {"input": 2.24821114699997, "reasoning": 0, "answer": 3.8001207105370094, "total": 6.048331857536979}, "timeToFirstAnswerToken": {"input": 2.24821114699997, "reasoning": 0, "total": 2.24821114699997}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1f541ef3-913f-4eb2-9d07-0e93c7a9a5e3", "slug": "gpt-6-astra-xhigh", "name": "GPT-6 Astra (xhigh)", "shortName": "GPT-6 Astra (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-03", "knowledgeCutoffDate": "2026-04-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-6-astra", "name": "GPT-6 Astra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 52.5059027108782, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 54.62591612211527, "strategyAndOps": 56.98918866410171, "legal": 58.3753910131589, "engineering": 54.86161681772043, "economics": 59.64665338276181}, "omniscience": 43.4166666666667, "omniscienceBreakdown": {"accuracy": 0.6185, "hallucinationRate": 0.4831804281345566}, "gdpPdfAllPass": 0.322, "gdpval": 1555.23, "gdpvalNormalized": 0.5276150000000001, "itBenchSre": null, "tau2": null, "tauBanking": 0.430927835051546, "terminalbenchHard": null, "terminalBench21": 0.891385767790262, "terminalBench40": 0.595959595959596, "scicode": 0.556712962962963, "lcr": 0.8, "ifbench": null, "hle": 0.545875810936052, "gpqa": 0.962626262626263, "critpt": 0.314285714285714, "apexAgents": null, "mmmuPro": 0.86242774566474, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.6717778020215392, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 1, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 12.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.7, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 1.5686274509803921, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 316.1326270132107, "intelligenceIndexCost": {"total": 3802.9799452617394, "input": 1907.9228452617394, "nonCacheInput": 281.16663, "cacheRead": 843.6115214989791, "cacheWrite": 783.1446937627603, "output": 1895.0571, "reasoning": 1224.5635, "answer": 670.4936}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.308795912269076, "input": 1.4637368639744461, "nonCacheInput": 0.217051193301374, "cacheRead": 0.7237054006606568, "cacheWrite": 0.5229802700124153, "output": 0.8450590482946302, "reasoning": 0.42912435154993606, "answer": 0.41593469674469413}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.9845281987639405}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.30381411031489386}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.07031943574056776}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.5855482520522051}, {"slug": "scicode", "weightedCostPerTask": 0.012163322916666667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.025322250695088044}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.19127230999999997}, {"slug": "critpt", "weightedCostPerTask": 0.07980151428571428}, {"slug": "omniscience", "weightedCostPerTask": 0.007531007499999997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.048495510000000006}]}, "canonicalIntelligenceIndexTokenCount": {"input": 934379760, "output": 37901142, "answer": 13409872, "reasoning": 24491270}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 8582.48703099872, "answer": 8318.693934893881, "output": 16901.1809658926}, "briefcaseBreakdown": {"overall": {"elo": 1533.73, "lower95ci": 1524.83, "upper95ci": 1543.92}, "rubricPassRate": 0.5232323232323233, "analyticalQuality": {"elo": 1702.08, "lower95ci": 1685.93, "upper95ci": 1719.61}, "presentation": {"elo": 1491.7, "lower95ci": 1475.54, "upper95ci": 1508.83}}, "briefcaseTotalCost": 597.2804405834572, "timescaleData": {"medianOutputSpeed": 52.9243169963677, "medianTimeToFirstChunk": 117.7072868305}, "outputSpeedVariance": {"p05": 38.1922573876351, "q25": 48.2166540653184, "median": 52.9243169963677, "q75": 62.2637702878368, "p95": 74.0438769202534}, "timeToFirstChunkVariance": {"p05": 47.5505287831003, "q25": 82.2083590597503, "median": 117.7072868305, "q75": 167.82362739575, "p95": 292.5112876675}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 55.5315568317343, "medianTimeToFirstChunk": 76.143074066, "medianTimeToFirstAnswerToken": 76.143074066, "medianEndToEndResponseTime": 85.14696353942222}, "long": {"medianOutputSpeed": 52.9243169963677, "medianTimeToFirstChunk": 117.7072868305, "medianTimeToFirstAnswerToken": 117.7072868305, "medianEndToEndResponseTime": 127.15473987999927}, "hundredK": {"medianOutputSpeed": 60.3192998109834, "medianTimeToFirstChunk": 66.148180829, "medianTimeToFirstAnswerToken": 66.148180829, "medianEndToEndResponseTime": 74.43740171794931}, "mediumParallel": {"medianOutputSpeed": 57.0136394008204, "medianTimeToFirstChunk": 148.005023563, "medianTimeToFirstAnswerToken": 148.005023563, "medianEndToEndResponseTime": 156.77485487450204}}, "endToEndResponseTime": {"input": 117.7072868305, "reasoning": 0, "answer": 9.447453049499268, "total": 127.15473987999927}, "timeToFirstAnswerToken": {"input": 117.7072868305, "reasoning": 0, "total": 117.7072868305}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1f6478c9-3e22-4586-adbe-841782859677", "slug": "nova-2-0-omni", "name": "Nova 2.0 Omni (Non-reasoning)", "shortName": "Nova 2.0 Omni (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-26", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "nova-2-0-omni", "name": "Nova 2.0 Omni"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.15087501101863, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -64.2333333333333, "omniscienceBreakdown": {"accuracy": 0.13233333333333333, "hallucinationRate": 0.8928159815597387}, "gdpval": null, "itBenchSre": null, "tau2": 0.447368421052632, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.246666666666667, "ifbench": 0.410884353741497, "hle": 0.0384615384615385, "gpqa": 0.554545454545454, "critpt": 0, "apexAgents": null, "mmmuPro": 0.498843930635838, "livecodebench": 0.304761904761905, "aime25": 0.37, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.42, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.52, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.32156862745098036, "price1mBlended0To100To1": 0.3217821782178218, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1fc32894-1060-493b-af94-62bb1068555e", "slug": "granite-4-0-micro", "name": "Granite 4.0 Micro", "shortName": "Granite 4.0 Micro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-22", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "granite-4-0-micro", "name": "Granite 4.0 Micro"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.0-micro", "microevalsEnabled": false, "intelligenceIndex": 5.10657830942846, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -77.5333333333333, "omniscienceBreakdown": {"accuracy": 0.09316666666666666, "hallucinationRate": 0.9577283587575813}, "gdpval": null, "itBenchSre": null, "tau2": 0.125730994152047, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.07, "ifbench": 0.247619047619048, "hle": 0.0500463392029657, "gpqa": 0.336363636363636, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.17989417989418, "aime25": 0.06, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 55.55555555555556, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "1fc54cef-d179-48b1-a27d-046874e9b208", "slug": "claude-3-haiku", "name": "Claude 3 Haiku", "shortName": "Claude 3 Haiku", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-03-04", "knowledgeCutoffDate": "2023-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-3-haiku", "name": "Claude 3 Haiku"}, "deprecated": true, "deprecatedTo": "claude-3-5-haiku", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.57842403353134, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -48.6333333333333, "omniscienceBreakdown": {"accuracy": 0.17633333333333334, "hallucinationRate": 0.8045325779036827}, "gdpval": null, "itBenchSre": null, "tau2": 0.210526315789474, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.276666666666667, "ifbench": 0.361224489795918, "hle": 0.0407784986098239, "gpqa": 0.373737373737374, "critpt": 0, "apexAgents": null, "mmmuPro": 0.308092485549133, "livecodebench": 0.154497354497354, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.25, "price1mOutputTokens": 1.25, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.3335, "price1mBlended0To3To1": 0.5, "price1mBlended7To2To1": 0.35, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.25980392156862747, "price1mBlended0To100To1": 0.2599009900990099, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "20928ba9-3a3f-415f-9519-b84ff64ecf34", "slug": "claude-opus-5-low", "name": "Claude Opus 5 (Adaptive Reasoning, Low Effort)", "shortName": "Claude Opus 5 (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "claude-opus-5", "name": "Claude Opus 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 39.7883357992936, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 44.38761733390958, "strategyAndOps": 46.94862407514384, "legal": 48.29453458446238, "healthcareAndMedical": 45.27787802010612, "engineering": 42.8845965858493, "economics": 50.533920779270915}, "omniscience": 28.55, "omniscienceBreakdown": {"accuracy": 0.5595, "hallucinationRate": 0.6220204313280363}, "mlcrOverall": 0.538888888888889, "gdpPdfAllPass": 0.172, "gdpval": 1371.52, "gdpvalNormalized": 0.43576, "itBenchSre": null, "tau2": null, "tauBanking": 0.303092783505155, "terminalbenchHard": null, "terminalBench21": 0.764044943820225, "terminalBench40": 0.262626262626263, "scicode": 0.491898148148148, "lcr": 0.813333333333333, "ifbench": null, "hle": 0.434198331788693, "gpqa": 0.888888888888889, "critpt": 0.231428571428571, "apexAgents": null, "mmmuPro": 0.798265895953757, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5179066298700786, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.86, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "intelligenceIndexTimePerTask": 179.9838997575026, "intelligenceIndexCost": {"total": 1560.9147939199095, "input": 921.1058939199095, "nonCacheInput": 176.16386500000002, "cacheRead": 427.53790292000787, "cacheWrite": 317.40412599990157, "output": 639.8089, "reasoning": 274.126, "answer": 365.6829}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.098302324514437, "input": 0.7316021918097116, "nonCacheInput": 0.1284895550516296, "cacheRead": 0.42549678019648396, "cacheWrite": 0.17761585656159834, "output": 0.36670013270472546, "reasoning": 0.16359625413197068, "answer": 0.20310387857275466}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.26716822411121277}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.058172795113107884}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.041336097685571616}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.5179420456391798}, {"slug": "scicode", "weightedCostPerTask": 0.002870795138888889}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.006251423308619091}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.095397535}, {"slug": "critpt", "weightedCostPerTask": 0.07203800714285713}, {"slug": "omniscience", "weightedCostPerTask": 0.000594893875}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.036530507499999997}]}, "canonicalIntelligenceIndexTokenCount": {"input": 941093239, "output": 25592356, "answer": 14627316, "reasoning": 10965040}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 6543.850165278829, "answer": 8124.155142910187, "output": 14668.005308189016}, "briefcaseBreakdown": {"overall": {"elo": 1215.73, "lower95ci": 1209.67, "upper95ci": 1222.69}, "rubricPassRate": 0.38181818181818183, "analyticalQuality": {"elo": 1327.84, "lower95ci": 1315.78, "upper95ci": 1340.52}, "presentation": {"elo": 1121.73, "lower95ci": 1109.85, "upper95ci": 1133.98}}, "briefcaseTotalCost": 162.08205596080242, "timescaleData": {"medianOutputSpeed": 52.0543310215564, "medianTimeToFirstChunk": 2.88493505999995}, "outputSpeedVariance": {"p05": 40.4561292908067, "q25": 44.175837775004, "median": 52.0543310215564, "q75": 63.1695639105689, "p95": 71.4405669748178}, "timeToFirstChunkVariance": {"p05": 1.11493106860003, "q25": 2.06058826674999, "median": 2.88493505999995, "q75": 4.13581294149981, "p95": 5.66881503405003}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 55.9656723564837, "medianTimeToFirstChunk": 2.24333703849998, "medianTimeToFirstAnswerToken": 2.24333703849998, "medianEndToEndResponseTime": 11.177384981588336}, "long": {"medianOutputSpeed": 52.0543310215564, "medianTimeToFirstChunk": 2.88493505999995, "medianTimeToFirstAnswerToken": 2.88493505999995, "medianEndToEndResponseTime": 12.490283744491608}, "hundredK": {"medianOutputSpeed": 59.8722185937238, "medianTimeToFirstChunk": 6.50960051200004, "medianTimeToFirstAnswerToken": 6.50960051200004, "medianEndToEndResponseTime": 14.860719140037876}, "mediumParallel": {"medianOutputSpeed": 47.1962237893225, "medianTimeToFirstChunk": 2.45951158949993, "medianTimeToFirstAnswerToken": 2.45951158949993, "medianEndToEndResponseTime": 13.053579501202607}}, "endToEndResponseTime": {"input": 2.88493505999995, "reasoning": 0, "answer": 9.605348684491657, "total": 12.490283744491608}, "timeToFirstAnswerToken": {"input": 2.88493505999995, "reasoning": 0, "total": 2.88493505999995}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 3, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "20da3b31-fc0a-4359-abec-d59367bf1d9f", "slug": "qwen3-5-9b-non-reasoning", "name": "Qwen3.5 9B (Non-reasoning)", "shortName": "Qwen3.5 9B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-5-9b", "name": "Qwen3.5 9B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 9.65, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-9B", "microevalsEnabled": false, "intelligenceIndex": 13.2659955355465, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -70.7, "omniscienceBreakdown": {"accuracy": 0.13983333333333334, "hallucinationRate": 0.9844991280759543}, "gdpval": null, "itBenchSre": null, "tau2": 0.850877192982456, "tauBanking": null, "terminalbenchHard": 0.181818181818182, "terminalBench21": 0.213483146067416, "terminalBench40": null, "scicode": null, "lcr": 0.46, "ifbench": 0.378231292517007, "hle": 0.0936051899907322, "gpqa": 0.785858585858586, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": 0.667630057803468, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.17, "price1mOutputTokens": 0.25, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.19, "price1mBlended7To2To1": 0.17800000000000002, "price1mBlended0To1To1": 0.21000000000000002, "price1mBlended100To1To1": 0.17078431372549022, "price1mBlended0To100To1": 0.1707920792079208, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 86.2466222746225, "medianTimeToFirstChunk": 0.758162765999998}, "outputSpeedVariance": {"p05": 58.8090906431323, "q25": 70.2088775536332, "median": 86.2466222746225, "q75": 94.8962085869501, "p95": 106.988030502787}, "timeToFirstChunkVariance": {"p05": 0.655650019199988, "q25": 0.70009706175, "median": 0.758162765999998, "q75": 0.860152394750116, "p95": 1.36018650929997}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 87.1243276499443, "medianTimeToFirstChunk": 0.421689710999999, "medianTimeToFirstAnswerToken": 0.421689710999999, "medianEndToEndResponseTime": 6.16061491693035}, "long": {"medianOutputSpeed": 86.2466222746225, "medianTimeToFirstChunk": 0.758162765999998, "medianTimeToFirstAnswerToken": 0.758162765999998, "medianEndToEndResponseTime": 6.555491250446881}, "hundredK": {"medianOutputSpeed": 98.1481724656871, "medianTimeToFirstChunk": 5.80372238299998, "medianTimeToFirstAnswerToken": 5.80372238299998, "medianEndToEndResponseTime": 10.898060743449854}, "mediumParallel": {"medianOutputSpeed": 99.4199128074268, "medianTimeToFirstChunk": 0.452582111999845, "medianTimeToFirstAnswerToken": 0.452582111999845, "medianEndToEndResponseTime": 5.481755703898724}}, "endToEndResponseTime": {"input": 0.758162765999998, "reasoning": 0, "answer": 5.797328484446883, "total": 6.555491250446881}, "timeToFirstAnswerToken": {"input": 0.758162765999998, "reasoning": 0, "total": 0.758162765999998}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "217b34ec-5920-4fc1-8886-6a70a324837d", "slug": "mistral-7b-instruct", "name": "Mistral 7B Instruct", "shortName": "Mistral 7B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-09-27", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-7b-instruct", "name": "Mistral 7B Instruct"}, "deprecated": true, "deprecatedTo": "ministral-3-8b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 8192, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1", "microevalsEnabled": false, "intelligenceIndex": 5.03498213171439, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -64.9166666666667, "omniscienceBreakdown": {"accuracy": 0.09016666666666667, "hallucinationRate": 0.8126030408499725}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.199319727891156, "hle": 0.0455, "gpqa": 0.176767676767677, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0455026455026455, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.25, "price1mOutputTokens": 0.25, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.25, "price1mBlended7To2To1": 0.25, "price1mBlended0To1To1": 0.25, "price1mBlended100To1To1": 0.25, "price1mBlended0To100To1": 0.25, "timescaleData": {"medianOutputSpeed": 93.3438099801317, "medianTimeToFirstChunk": 0.763805775000094}, "outputSpeedVariance": {"p05": 54.5001319288712, "q25": 78.6018744607692, "median": 93.3438099801317, "q75": 105.655518762312, "p95": 125.689604464381}, "timeToFirstChunkVariance": {"p05": 0.695094485999993, "q25": 0.728314042250019, "median": 0.763805775000094, "q75": 0.984912924250008, "p95": 1.28689868064998}, "performanceByPromptType": {"long": {"medianOutputSpeed": 93.3438099801317, "medianTimeToFirstChunk": 0.763805775000094, "medianTimeToFirstAnswerToken": 0.763805775000094, "medianEndToEndResponseTime": 6.12034736149014}}, "endToEndResponseTime": {"input": 0.763805775000094, "reasoning": 0, "answer": 5.356541586490046, "total": 6.12034736149014}, "timeToFirstAnswerToken": {"input": 0.763805775000094, "reasoning": 0, "total": 0.763805775000094}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 2, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "219ed587-60c5-4a48-9517-8480e08d0ca1", "slug": "gemini-2-5-flash-reasoning", "name": "Gemini 2.5 Flash (Reasoning)", "shortName": "Gemini 2.5 Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-20", "knowledgeCutoffDate": "2025-01-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-flash", "name": "Gemini 2.5 Flash"}, "deprecated": true, "deprecatedTo": "gemini-2-5-flash-preview-09-2025-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 13.1060438652288, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -29.8, "omniscienceBreakdown": {"accuracy": 0.2595, "hallucinationRate": 0.7528696826468603}, "mlcrOverall": 0.0888888888888889, "gdpval": null, "itBenchSre": null, "tau2": 0.315789473684211, "tauBanking": null, "terminalbenchHard": 0.136363636363636, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.653333333333333, "ifbench": 0.502721088435374, "hle": 0.121408711770158, "gpqa": 0.78989898989899, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": 0.690751445086705, "livecodebench": 0.695238095238095, "aime25": 0.733333333333333, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": 0.03, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.1935, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.331, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.056862745098039215, "price1mBlended0To100To1": 0.3217821782178218, "timescaleData": {"medianOutputSpeed": 226.51320166426, "medianTimeToFirstChunk": 24.589884812}, "outputSpeedVariance": {"p05": 178.551805394942, "q25": 207.433699736471, "median": 226.51320166426, "q75": 242.561713095965, "p95": 270.864159374647}, "timeToFirstChunkVariance": {"p05": 7.95215161140001, "q25": 13.2624477155, "median": 24.589884812, "q75": 35.7139249019999, "p95": 54.0096852991999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 226.51320166426, "medianTimeToFirstChunk": 24.589884812, "medianTimeToFirstAnswerToken": 24.589884812, "medianEndToEndResponseTime": 26.797261672714303}}, "endToEndResponseTime": {"input": 24.589884812, "reasoning": 0, "answer": 2.2073768607143025, "total": 26.797261672714303}, "timeToFirstAnswerToken": {"input": 24.589884812, "reasoning": 0, "total": 24.589884812}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 2, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "222fb320-6e55-4672-846a-b6d5a24a45f4", "slug": "gemma-3-4b", "name": "Gemma 3 4B Instruct", "shortName": "Gemma 3 4B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-12", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-3-4b-instruct", "name": "Gemma 3 4B Instruct"}, "deprecated": true, "deprecatedTo": "gemma-4-e4b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 4.3, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "Gemma license", "licenseUrl": "https://ai.google.dev/gemma/terms", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-3-12b-it", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -82.8833333333333, "omniscienceBreakdown": {"accuracy": 0.07733333333333334, "hallucinationRate": 0.9821170520231214}, "gdpval": null, "itBenchSre": null, "tau2": 0.0497076023391813, "tauBanking": 0.00412371134020619, "terminalbenchHard": 0.00757575757575758, "terminalBench21": 0.00374531835205993, "terminalBench40": null, "scicode": null, "lcr": 0.0666666666666667, "ifbench": 0.282993197278912, "hle": 0.0529, "gpqa": 0.290909090909091, "critpt": 0, "apexAgents": null, "mmmuPro": 0.299421965317919, "livecodebench": 0.112169312169312, "aime25": 0.126666666666667, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 4, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2236df45-0699-40d1-b5cc-69ee345d2257", "slug": "qwen3-5-122b-a10b", "name": "Qwen3.5 122B A10B (Reasoning)", "shortName": "Qwen3.5 122B A10B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-5-122b-a10b", "name": "Qwen3.5 122B A10B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 125, "inferenceParametersActiveBillions": 10, "sizeClass": "medium", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B", "microevalsEnabled": true, "intelligenceIndex": 16.1869509312969, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 17.52419343048574, "strategyAndOps": 13.639240616276552, "legal": 17.969679014098332, "engineering": 19.32548567960313, "economics": 24.86028222446897}, "omniscience": -41.5, "omniscienceBreakdown": {"accuracy": 0.24366666666666667, "hallucinationRate": 0.870868223887175}, "gdpPdfAllPass": 0.034, "gdpval": 925.2, "gdpvalNormalized": 0.2126, "itBenchSre": null, "tau2": 0.935672514619883, "tauBanking": 0.152577319587629, "terminalbenchHard": 0.310606060606061, "terminalBench21": 0.47565543071161, "terminalBench40": 0, "scicode": 0.396990740740741, "lcr": 0.763333333333333, "ifbench": 0.757142857142857, "hle": 0.252085264133457, "gpqa": 0.856565656565657, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": 0.74971098265896, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.054811162302925646, "price1mInputTokens": 0.4, "price1mOutputTokens": 3.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.41, "price1mBlended0To3To1": 1.1, "price1mBlended7To2To1": 0.68, "price1mBlended0To1To1": 1.8, "price1mBlended100To1To1": 0.4274509803921569, "price1mBlended0To100To1": 0.42772277227722777, "intelligenceIndexTimePerTask": 125.64597481491914, "intelligenceIndexCost": {"total": 661.2875196000001, "input": 338.9178972000001, "nonCacheInput": 8.109526800000001, "cacheRead": 0, "cacheWrite": 330.80837040000006, "output": 322.3696224, "reasoning": 263.2474528, "answer": 59.1221696}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.3247468637357143, "input": 0.26998059225447935, "nonCacheInput": 0.005486607720027509, "cacheRead": 0, "cacheWrite": 0.2644939845344519, "output": 0.05476627148123493, "reasoning": 0.023265768737462094, "answer": 0.03150050274377285}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.07951872395604397}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.023991564181818182}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.011919114216133942}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.17832505636363635}, {"slug": "scicode", "weightedCostPerTask": 0.0015884111111111108}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00841899638554217}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0039675216}, {"slug": "critpt", "weightedCostPerTask": 0.01231674457142857}, {"slug": "omniscience", "weightedCostPerTask": 0.00204488815}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0026558432}]}, "canonicalIntelligenceIndexTokenCount": {"input": 847294743, "output": 100740507, "answer": 18475678, "reasoning": 82264829}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 7270.552730456905, "answer": 9843.907107429015, "output": 17114.45983788592}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 498.94, "lower95ci": 490.07, "upper95ci": 507.84}, "rubricPassRate": 0.10606060606060606, "analyticalQuality": {"elo": 310.59, "lower95ci": 293.7, "upper95ci": 328.97}, "presentation": {"elo": 478.63, "lower95ci": 460.89, "upper95ci": 494.78}}, "briefcaseTotalCost": 48.241359200000005, "timescaleData": {"medianOutputSpeed": 127.781323312914, "medianTimeToFirstChunk": 2.37777444049997}, "outputSpeedVariance": {"p05": 95.3866375872409, "q25": 122.580590158196, "median": 127.781323312914, "q75": 134.612253517752, "p95": 151.433045527059}, "timeToFirstChunkVariance": {"p05": 2.2619857839, "q25": 2.28455005524995, "median": 2.37777444049997, "q75": 2.64565257125007, "p95": 4.3849309891}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 135.787223586527, "medianTimeToFirstChunk": 1.00086312099995, "medianTimeToFirstAnswerToken": 15.729789357020604, "medianEndToEndResponseTime": 19.412020916025764}, "long": {"medianOutputSpeed": 127.781323312914, "medianTimeToFirstChunk": 2.37777444049997, "medianTimeToFirstAnswerToken": 18.02951405429589, "medianEndToEndResponseTime": 21.94244895774487}, "hundredK": {"medianOutputSpeed": 106.744021143513, "medianTimeToFirstChunk": 19.5774766115, "medianTimeToFirstAnswerToken": 38.313888998579564, "medianEndToEndResponseTime": 42.99799209534946}, "mediumParallel": {"medianOutputSpeed": 125.688087180848, "medianTimeToFirstChunk": 1.13862748799999, "medianTimeToFirstAnswerToken": 17.05103450173927, "medianEndToEndResponseTime": 21.02913625517409}}, "endToEndResponseTime": {"input": 2.37777444049997, "reasoning": 15.65173961379592, "answer": 3.91293490344898, "total": 21.94244895774487}, "timeToFirstAnswerToken": {"input": 2.37777444049997, "reasoning": 15.65173961379592, "total": 18.02951405429589}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 5, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "22d09131-343b-4adf-8760-533e20a2155f", "slug": "mimo-v2-5-0424", "name": "MiMo-V2.5", "shortName": "MiMo-V2.5", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-22", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "mimo-v2-5-0424", "name": "MiMo-V2.5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 310, "inferenceParametersActiveBillions": 15, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/XiaomiMiMo/MiMo-V2.5", "microevalsEnabled": true, "intelligenceIndex": 22.3038928794953, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 22.9037996054785, "strategyAndOps": 19.752373549813615, "legal": 25.01481848224228, "engineering": 25.09087657968199, "economics": 34.52482474328686}, "omniscience": -9.83333333333333, "omniscienceBreakdown": {"accuracy": 0.1675, "hallucinationRate": 0.31931931931931934}, "gdpPdfAllPass": 0.04, "gdpval": 1079.43, "gdpvalNormalized": 0.28971500000000006, "itBenchSre": null, "tau2": 0.906432748538012, "tauBanking": 0.0865979381443299, "terminalbenchHard": 0.416666666666667, "terminalBench21": 0.636704119850187, "terminalBench40": 0, "scicode": 0.438657407407407, "lcr": 0.73, "ifbench": 0.671428571428571, "hle": 0.272011121408712, "gpqa": 0.84949494949495, "critpt": 0.0371428571428571, "apexAgents": null, "mmmuPro": 0.754335260115607, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.1842951233004315, "price1mInputTokens": 0.14, "price1mOutputTokens": 0.28, "cacheHitPrice": 0.0028, "cacheHitDiscountPercent": 0.98, "cacheWritePrice": null, "pricePer1k1mpImages": 1.026, "price1mBlended0To3To1": 0.17500000000000002, "price1mBlended7To2To1": 0.05796000000000001, "price1mBlended0To1To1": 0.21000000000000002, "price1mBlended100To1To1": 0.006862745098039216, "price1mBlended0To100To1": 0.1413861386138614, "intelligenceIndexTimePerTask": 552.7490504556542, "intelligenceIndexCost": {"total": 42.61208501909787, "input": 16.055258219097865, "nonCacheInput": 2.55097752, "cacheRead": 3.637024234712288, "cacheWrite": 9.867256464385578, "output": 26.556826800000003, "reasoning": 21.28677404, "answer": 5.2700527600000004}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.019069773544356065, "input": 0.010410232216692858, "nonCacheInput": 0.001457686833467357, "cacheRead": 0.0033684338231462128, "cacheWrite": 0.005584111560079288, "output": 0.008659541327663205, "reasoning": 0.005601197693515617, "answer": 0.0030583436341475906}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.002332878181735218}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0009495881876972424}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0009182948904094361}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.01123804569080492}, {"slug": "scicode", "weightedCostPerTask": 0.0003527983472222223}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0005749102659870251}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0006119204000000001}, {"slug": "critpt", "weightedCostPerTask": 0.0012249202}, {"slug": "omniscience", "weightedCostPerTask": 7.89311705e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0007874862100000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1387638898, "output": 94845810, "answer": 18821617, "reasoning": 76024193}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 20004.277476841482, "answer": 10922.655836241394, "output": 30926.933313082875}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 750.72, "lower95ci": 741.36, "upper95ci": 759.68}, "rubricPassRate": 0.13871635610766045, "analyticalQuality": {"elo": 593.53, "lower95ci": 576.11, "upper95ci": 610.34}, "presentation": {"elo": 883.11, "lower95ci": 865.07, "upper95ci": 898.89}}, "briefcaseTotalCost": 1.415279430252699, "timescaleData": {"medianOutputSpeed": 51.2628765223709, "medianTimeToFirstChunk": 6.44260197449995}, "outputSpeedVariance": {"p05": 29.076838317389, "q25": 40.5413292251264, "median": 51.2628765223709, "q75": 73.1690004198012, "p95": 85.2536893120225}, "timeToFirstChunkVariance": {"p05": 2.38125593215017, "q25": 4.23736949625005, "median": 6.44260197449995, "q75": 18.1673432737499, "p95": 38.4195522370001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 50.497284596808, "medianTimeToFirstChunk": 9.98497008950001, "medianTimeToFirstAnswerToken": 49.591060119268114, "medianEndToEndResponseTime": 59.492582626710146}, "long": {"medianOutputSpeed": 51.2628765223709, "medianTimeToFirstChunk": 6.44260197449995, "medianTimeToFirstAnswerToken": 45.45718983375144, "medianEndToEndResponseTime": 55.21083679856431}, "hundredK": {"medianOutputSpeed": 88.9139872364381, "medianTimeToFirstChunk": 54.291671479, "medianTimeToFirstAnswerToken": 76.78532025308596, "medianEndToEndResponseTime": 82.40873244660744}, "mediumParallel": {"medianOutputSpeed": 44.2361505918606, "medianTimeToFirstChunk": 7.14888958949999, "medianTimeToFirstAnswerToken": 52.36078016408352, "medianEndToEndResponseTime": 63.6637528077294}}, "endToEndResponseTime": {"input": 6.44260197449995, "reasoning": 39.01458785925149, "answer": 9.753646964812873, "total": 55.21083679856431}, "timeToFirstAnswerToken": {"input": 6.44260197449995, "reasoning": 39.01458785925149, "total": 45.45718983375144}, "performanceDataSource": {"type": "firstParty", "providerName": "Xiaomi"}, "hostModelCount": 4, "creator": {"id": "5147c8b4-61d5-4070-9324-8adf8aa144c2", "slug": "xiaomi", "name": "Xiaomi", "logo": "/img/logos/xiaomi_small.svg", "color": "#ff6900", "country": "cn", "url": "https://huggingface.co/XiaomiMiMo"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "23149f9b-c904-43e2-9ec4-afa2bf843941", "slug": "grok-4-1-fast-reasoning", "name": "Grok 4.1 Fast (Reasoning)", "shortName": "Grok 4.1 Fast", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "grok-4-1-fast", "name": "Grok 4.1 Fast"}, "deprecated": true, "deprecatedTo": "grok-4-3", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 20.3701852131578, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -29.9166666666667, "omniscienceBreakdown": {"accuracy": 0.25083333333333335, "hallucinationRate": 0.7341490545050056}, "gdpval": null, "itBenchSre": null, "tau2": 0.932748538011696, "tauBanking": null, "terminalbenchHard": 0.242424242424242, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.74, "ifbench": 0.527210884353742, "hle": 0.193234476367006, "gpqa": 0.852525252525253, "critpt": 0.0285714285714286, "apexAgents": null, "mmmuPro": 0.632947976878613, "livecodebench": 0.822222222222222, "aime25": 0.893333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "235060f4-057d-4bd1-8b8e-4a92908c770e", "slug": "hermes-4-llama-3-1-70b", "name": "Hermes 4 - Llama-3.1 70B (Non-reasoning)", "shortName": "Hermes 4 70B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-27", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "hermes-4-llama-3-1-70b", "name": "Hermes 4 - Llama-3.1 70B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 70.6, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "META LLAMA 3 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://llama.meta.com/llama3/license/", "modelWeightsSourceUrl": "https://huggingface.co/NousResearch/Hermes-4-70B", "microevalsEnabled": false, "intelligenceIndex": 6.65822068462287, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -48.5833333333333, "omniscienceBreakdown": {"accuracy": 0.18666666666666668, "hallucinationRate": 0.826844262295082}, "gdpval": null, "itBenchSre": null, "tau2": 0.216374269005848, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.0466666666666667, "ifbench": 0.289795918367347, "hle": 0.0356811862835959, "gpqa": 0.490909090909091, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.268783068783069, "aime25": 0.113333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 47.22222222222222, "modelAvailability": 4, "transparencyMethodology": 3, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0a2f41cc-2cbc-4949-be54-9fef1319d4a9", "slug": "nous-research", "name": "Nous Research", "logo": "/img/logos/nousresearch_small.jpg", "color": "#006fa8", "country": "us", "url": "https://nousresearch.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "23b379f7-18df-492a-9fc1-a56c5a5b9cfc", "slug": "nvidia-nemotron-3-nano-30b-a3b", "name": "NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)", "shortName": "Nemotron 3 Nano (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-15", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "nvidia-nemotron-3-nano-30b-a3b", "name": "NVIDIA Nemotron 3 Nano 30B A3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 31.6, "inferenceParametersActiveBillions": 3.6, "sizeClass": "small", "contextWindowTokens": 1000000, "licenseName": "Nvidia Nemotron Open Model License", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "microevalsEnabled": false, "intelligenceIndex": 6.8478519055181, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -69.3, "omniscienceBreakdown": {"accuracy": 0.11366666666666667, "hallucinationRate": 0.9101165851823994}, "gdpval": -121.8, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.254385964912281, "tauBanking": null, "terminalbenchHard": 0.121212121212121, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.106666666666667, "ifbench": 0.374829931972789, "hle": 0.0458758109360519, "gpqa": 0.398989898989899, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.35978835978836, "aime25": 0.133333333333333, "analystAgent": null, "price1mInputTokens": 0.05, "price1mOutputTokens": 0.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.08750000000000001, "price1mBlended7To2To1": 0.06500000000000002, "price1mBlended0To1To1": 0.125, "price1mBlended100To1To1": 0.051470588235294115, "price1mBlended0To100To1": 0.05148514851485149, "openness": {"opennessIndex": 83.33333333333333, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {"medianOutputSpeed": 143.257604202979, "medianTimeToFirstChunk": 0.971365746999936}, "outputSpeedVariance": {"p05": 53.6167022011015, "q25": 98.5406435778046, "median": 143.257604202979, "q75": 272.323248620825, "p95": 338.151067307597}, "timeToFirstChunkVariance": {"p05": 0.562446775850037, "q25": 0.674976977749992, "median": 0.971365746999936, "q75": 1.05425043125, "p95": 3.30134912794985}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 129.391172628297, "medianTimeToFirstChunk": 0.472120585000013, "medianTimeToFirstAnswerToken": 0.472120585000013, "medianEndToEndResponseTime": 4.336371830611286}, "long": {"medianOutputSpeed": 143.257604202979, "medianTimeToFirstChunk": 0.971365746999936, "medianTimeToFirstAnswerToken": 0.971365746999936, "medianEndToEndResponseTime": 4.461581870477469}, "hundredK": {"medianOutputSpeed": 228.199884217855, "medianTimeToFirstChunk": 5.15149205850008, "medianTimeToFirstAnswerToken": 5.15149205850008, "medianEndToEndResponseTime": 7.342553643451044}, "mediumParallel": {"medianOutputSpeed": 124.131649548586, "medianTimeToFirstChunk": 0.666052981999997, "medianTimeToFirstAnswerToken": 0.666052981999997, "medianEndToEndResponseTime": 4.694034579105065}}, "endToEndResponseTime": {"input": 0.971365746999936, "reasoning": 0, "answer": 3.4902161234775324, "total": 4.461581870477469}, "timeToFirstAnswerToken": {"input": 0.971365746999936, "reasoning": 0, "total": 0.971365746999936}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "23c86e4a-c769-43c0-a056-79e3cd15834f", "slug": "claude-sonnet-5", "name": "Claude Sonnet 5 (Adaptive Reasoning, Max Effort)", "shortName": "Claude Sonnet 5 (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "claude-sonnet-5", "name": "Claude Sonnet 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 38.3576962882576, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 40.67592479863847, "strategyAndOps": 39.588982914016995, "legal": 42.619239340487226, "healthcareAndMedical": 43.10341215215245, "engineering": 40.443006193320755, "economics": 49.646192944856345}, "omniscience": 16.45, "omniscienceBreakdown": {"accuracy": 0.4005, "hallucinationRate": 0.39366138448707255}, "mlcrOverall": 0.55, "harveyLab": 0.900709219858156, "gdpPdfAllPass": 0.132, "gdpval": 1500.86, "gdpvalNormalized": 0.5004299999999999, "itBenchSre": null, "tau2": null, "tauBanking": 0.37319587628866, "terminalbenchHard": null, "terminalBench21": 0.805243445692884, "terminalBench40": 0.141414141414141, "scicode": 0.542824074074074, "lcr": 0.82, "ifbench": null, "hle": 0.412882298424467, "gpqa": 0.911111111111111, "critpt": 0.168571428571429, "apexAgents": null, "mmmuPro": 0.772832369942197, "livecodebench": null, "aime25": null, "analystAgent": 0.4625, "automationBenchPartialScore": 0.36512675717036386, "enterpriseOpsGym": 0.4467323187108326, "price1mInputTokens": 2, "price1mOutputTokens": 10, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": 4.116, "price1mBlended0To3To1": 4, "price1mBlended7To2To1": 1.54, "price1mBlended0To1To1": 6, "price1mBlended100To1To1": 0.3137254901960784, "price1mBlended0To100To1": 2.0792079207920793, "intelligenceIndexTimePerTask": 981.3555673479226, "intelligenceIndexCost": {"total": 6998.250634094257, "input": 3331.158834094257, "nonCacheInput": 70.852508, "cacheRead": 2504.300474687456, "cacheWrite": 756.0058514068016, "output": 3667.0918, "reasoning": 3275.00154, "answer": 392.09026}, "intelligenceIndexCostPerTask": {"cost": {"total": 5.091163584815694, "input": 3.9132903761991837, "nonCacheInput": 0.051565896462510113, "cacheRead": 3.134486434589194, "cacheWrite": 0.7272380451474796, "output": 1.177873208616511, "reasoning": 0.8839229202190229, "answer": 0.29395028839748816}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 2.16437639193891}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.4703913880294028}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.05007379050004273}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.969417991135462}, {"slug": "scicode", "weightedCostPerTask": 0.019166355555555556}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.1020804596848934}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.061530626}, {"slug": "critpt", "weightedCostPerTask": 0.23137540857142858}, {"slug": "omniscience", "weightedCostPerTask": 0.0043541554}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.018397018}]}, "canonicalIntelligenceIndexTokenCount": {"input": 12859330968, "output": 366709180, "answer": 39209026, "reasoning": 327500154}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 88392.29202190228, "answer": 29395.02883974881, "output": 117787.3208616511}, "briefcaseBreakdown": {"overall": {"elo": 1355.19, "lower95ci": 1349.09, "upper95ci": 1361.66}, "rubricPassRate": 0.42323232323232324, "analyticalQuality": {"elo": 1412.87, "lower95ci": 1401.21, "upper95ci": 1425.22}, "presentation": {"elo": 1405.85, "lower95ci": 1394.97, "upper95ci": 1417.11}}, "briefcaseTotalCost": 1313.0550111096054, "timescaleData": {"medianOutputSpeed": 72.3002730918935, "medianTimeToFirstChunk": 139.429100229}, "outputSpeedVariance": {"p05": 65.1556083819514, "q25": 68.8547278752933, "median": 72.3002730918935, "q75": 89.4214859005053, "p95": 99.3409600289376}, "timeToFirstChunkVariance": {"p05": 79.3040718746, "q25": 131.48766914, "median": 139.429100229, "q75": 210.244764274, "p95": 262.6189622264}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 82.514795558511, "medianTimeToFirstChunk": 102.08675636, "medianTimeToFirstAnswerToken": 102.08675636, "medianEndToEndResponseTime": 108.14627570578146}, "long": {"medianOutputSpeed": 72.3002730918935, "medianTimeToFirstChunk": 139.429100229, "medianTimeToFirstAnswerToken": 139.429100229, "medianEndToEndResponseTime": 146.34470342962}, "hundredK": {"medianOutputSpeed": 71.5660899888036, "medianTimeToFirstChunk": 222.4255451735, "medianTimeToFirstAnswerToken": 222.4255451735, "medianEndToEndResponseTime": 229.41209425111796}, "mediumParallel": {"medianOutputSpeed": 80.3635201249118, "medianTimeToFirstChunk": 176.637432143, "medianTimeToFirstAnswerToken": 176.637432143, "medianEndToEndResponseTime": 182.85916059918054}}, "endToEndResponseTime": {"input": 139.429100229, "reasoning": 0, "answer": 6.915603200620017, "total": 146.34470342962}, "timeToFirstAnswerToken": {"input": 139.429100229, "reasoning": 0, "total": 139.429100229}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 8, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2443ac9e-a3db-423d-accb-8963f6fb0a53", "slug": "grok-3", "name": "Grok 3", "shortName": "Grok 3", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-19", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "grok-3", "name": "Grok 3"}, "deprecated": true, "deprecatedTo": "grok-4", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.1076211741685, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -33.1833333333333, "omniscienceBreakdown": {"accuracy": 0.289, "hallucinationRate": 0.8731833098921706}, "gdpval": null, "itBenchSre": null, "tau2": 0.488304093567252, "tauBanking": null, "terminalbenchHard": 0.113636363636364, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.58, "ifbench": 0.469387755102041, "hle": 0.0412, "gpqa": 0.692929292929293, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.425396825396825, "aime25": 0.58, "analystAgent": null, "price1mInputTokens": 4, "price1mOutputTokens": 20, "cacheHitPrice": 1.5375, "cacheHitDiscountPercent": 0.985, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 8, "price1mBlended7To2To1": 3.87625, "price1mBlended0To1To1": 12, "price1mBlended100To1To1": 1.7426470588235294, "price1mBlended0To100To1": 4.158415841584159, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": true, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "248deb0d-426c-4fa9-86fa-bc60aa9c3719", "slug": "glm-5v-turbo", "name": "GLM 5V Turbo (Reasoning)", "shortName": "GLM 5V Turbo", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "glm-5v-turbo", "name": "GLM 5V Turbo"}, "deprecated": true, "deprecatedTo": "glm-5-1", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 23.4967112022207, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -19.2833333333333, "omniscienceBreakdown": {"accuracy": 0.29333333333333333, "hallucinationRate": 0.6879716981132076}, "gdpval": null, "itBenchSre": null, "tau2": 0.985380116959064, "tauBanking": null, "terminalbenchHard": 0.325757575757576, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.703333333333333, "ifbench": 0.610884353741497, "hle": 0.171455050973123, "gpqa": 0.809090909090909, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": 0.727745664739884, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "24ac5b00-5f03-4c47-8e37-522d1195383e", "slug": "mistral-small-3-1", "name": "Mistral Small 3.1", "shortName": "Mistral Small 3.1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-17", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-small-3-1", "name": "Mistral Small 3.1"}, "deprecated": true, "deprecatedTo": "mistral-small-3-2", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 24, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503", "microevalsEnabled": false, "intelligenceIndex": 7.36700622656558, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 7.120778969043868, "strategyAndOps": 5.144988394185791, "legal": 8.532256895913754, "engineering": 10.36358188137164, "economics": 12.159570223200495}, "omniscience": -50.75, "omniscienceBreakdown": {"accuracy": 0.151, "hallucinationRate": 0.7756183745583038}, "gdpPdfAllPass": 0.01, "gdpval": 549.93, "gdpvalNormalized": 0.024964999999999973, "itBenchSre": null, "tau2": 0.251461988304094, "tauBanking": 0.0742268041237113, "terminalbenchHard": 0.0757575757575758, "terminalBench21": 0.262172284644195, "terminalBench40": 0, "scicode": 0.277777777777778, "lcr": 0.223333333333333, "ifbench": 0.299319727891156, "hle": 0.0430954587581094, "gpqa": 0.453535353535354, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.211640211640212, "aime25": 0.0366666666666667, "analystAgent": null, "automationBenchPartialScore": 0.012009813466312217, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.1276, "price1mBlended0To3To1": 0.15000000000000002, "price1mBlended7To2To1": 0.12000000000000002, "price1mBlended0To1To1": 0.2, "price1mBlended100To1To1": 0.10196078431372549, "price1mBlended0To100To1": 0.10198019801980199, "intelligenceIndexTimePerTask": 37.86854996469066, "intelligenceIndexCost": {"total": 35.759973, "input": 33.4950465, "nonCacheInput": 1.6967904000000003, "cacheRead": 0, "cacheWrite": 31.7982561, "output": 2.2649265, "reasoning": 0, "answer": 2.2649265}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.03276229387252031, "input": 0.03086868876313027, "nonCacheInput": 0.0010572210593492654, "cacheRead": 0, "cacheWrite": 0.029811467703781, "output": 0.0018936051093900363, "reasoning": 0, "answer": 0.0018936051093900363}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.01279019686813187}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0025300878636363637}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0007713217275494673}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.015505121060606062}, {"slug": "scicode", "weightedCostPerTask": 3.8077395833333337e-05}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 1.4017604263206673e-05}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0005400782000000001}, {"slug": "critpt", "weightedCostPerTask": 9.548199999999999e-05}, {"slug": "omniscience", "weightedCostPerTask": 2.3933025e-06}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0004755178500000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 334950465, "output": 7549755, "answer": 7549755, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 6312.017031300121, "output": 6312.017031300121}, "briefcaseBreakdown": {"overall": {"elo": 324.58, "lower95ci": 314.85, "upper95ci": 333.1}, "rubricPassRate": 0.06060606060606061, "analyticalQuality": {"elo": 83.77, "lower95ci": 63.83, "upper95ci": 103.16}, "presentation": {"elo": 290.4, "lower95ci": 271.14, "upper95ci": 308.2}}, "briefcaseTotalCost": 7.759386100000001, "timescaleData": {"medianOutputSpeed": 159.222353589012, "medianTimeToFirstChunk": 0.757681905499936}, "outputSpeedVariance": {"p05": 95.5183079331755, "q25": 131.849813176211, "median": 159.222353589012, "q75": 180.819136107511, "p95": 196.430583785562}, "timeToFirstChunkVariance": {"p05": 0.649274615600002, "q25": 0.717527409749892, "median": 0.757681905499936, "q75": 1.03755263025005, "p95": 1.7905529531}, "performanceByPromptType": {"long": {"medianOutputSpeed": 159.222353589012, "medianTimeToFirstChunk": 0.757681905499936, "medianTimeToFirstAnswerToken": 0.757681905499936, "medianEndToEndResponseTime": 3.8979444925648794}}, "endToEndResponseTime": {"input": 0.757681905499936, "reasoning": 0, "answer": 3.1402625870649437, "total": 3.8979444925648794}, "timeToFirstAnswerToken": {"input": 0.757681905499936, "reasoning": 0, "total": 0.757681905499936}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 4, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2660d74f-ce79-48a8-8b53-6e668e2071a2", "slug": "claude-opus-4-5-thinking", "name": "Claude Opus 4.5 (Reasoning)", "shortName": "Claude Opus 4.5", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-24", "knowledgeCutoffDate": "2025-08-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "claude-opus-4-5", "name": "Claude Opus 4.5"}, "deprecated": true, "deprecatedTo": "claude-opus-4-6-adaptive", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 29.0955143334264, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 14, "omniscienceBreakdown": {"accuracy": 0.4658333333333333, "hallucinationRate": 0.609984399375975}, "gdpval": null, "itBenchSre": null, "tau2": 0.894736842105263, "tauBanking": null, "terminalbenchHard": 0.46969696969697, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.773333333333333, "ifbench": 0.579591836734694, "hle": 0.301204819277108, "gpqa": 0.865656565656566, "critpt": 0.0457142857142857, "apexAgents": null, "mmmuPro": 0.740462427745665, "livecodebench": 0.870899470899471, "aime25": 0.913333333333333, "analystAgent": null, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.67, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 46.2194957297441, "medianTimeToFirstChunk": 17.871391435}, "outputSpeedVariance": {"p05": 37.0381420467931, "q25": 41.603480020764, "median": 46.2194957297441, "q75": 61.7507729960233, "p95": 74.1665172442111}, "timeToFirstChunkVariance": {"p05": 2.61359761840006, "q25": 4.19068257000002, "median": 17.871391435, "q75": 24.1972864455, "p95": 25.8489459403}, "performanceByPromptType": {"long": {"medianOutputSpeed": 46.2194957297441, "medianTimeToFirstChunk": 17.871391435, "medianTimeToFirstAnswerToken": 17.871391435, "medianEndToEndResponseTime": 28.689337241324104}}, "endToEndResponseTime": {"input": 17.871391435, "reasoning": 0, "answer": 10.817945806324104, "total": 28.689337241324104}, "timeToFirstAnswerToken": {"input": 17.871391435, "reasoning": 0, "total": 17.871391435}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "26614164-6840-4e17-a65a-2deb2fe7e87b", "slug": "grok-4-6-medium", "name": "Grok 4.6 (medium)", "shortName": "Grok 4.6 (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "grok-4-6", "name": "Grok 4.6"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 500000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 43.011172654063, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 46.806487900730104, "strategyAndOps": 49.23150331087329, "legal": 49.646119759178866, "engineering": 43.503490151214244, "economics": 53.30006742354031}, "omniscience": 28, "omniscienceBreakdown": {"accuracy": 0.41933333333333334, "hallucinationRate": 0.2399540757749713}, "gdpPdfAllPass": 0.178, "gdpval": 1642.56, "gdpvalNormalized": 0.57128, "itBenchSre": null, "tau2": null, "tauBanking": 0.443298969072165, "terminalbenchHard": null, "terminalBench21": 0.842696629213483, "terminalBench40": 0.131313131313131, "scicode": 0.559027777777778, "lcr": 0.81, "ifbench": null, "hle": 0.421223354958295, "gpqa": 0.935353535353535, "critpt": 0.177142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.63151269753679, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.35, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 0.5686274509803921, "price1mBlended0To100To1": 2.0396039603960396, "intelligenceIndexTimePerTask": 467.1661723528598, "intelligenceIndexCost": {"total": 1936.747257680374, "input": 1499.3911596803741, "nonCacheInput": 49.076966, "cacheRead": 578.6052807732086, "cacheWrite": 871.7089129071657, "output": 437.356098, "reasoning": 322.368276, "answer": 114.987822}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.4963233956114492, "input": 1.3255249417624821, "nonCacheInput": 0.03295996768051253, "cacheRead": 0.5371558246060252, "cacheWrite": 0.7554091494759443, "output": 0.17079845384896708, "reasoning": 0.08254825639279836, "answer": 0.08825019745616867}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.5410428355568766}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.17747202320957212}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.03550244586355789}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.670162567274232}, {"slug": "scicode", "weightedCostPerTask": 0.0023294180555555556}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.009366873215940683}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.025203748}, {"slug": "critpt", "weightedCostPerTask": 0.024188414285714284}, {"slug": "omniscience", "weightedCostPerTask": 0.00095197615}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.010103093999999998}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1617603501, "output": 72892683, "answer": 19164637, "reasoning": 53728046}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 13758.04273213306, "answer": 14708.366242694778, "output": 28466.40897482784}, "briefcaseBreakdown": {"overall": {"elo": 1490.6, "lower95ci": 1484.65, "upper95ci": 1497.85}, "rubricPassRate": 0.5252525252525253, "analyticalQuality": {"elo": 1604.18, "lower95ci": 1591.99, "upper95ci": 1616.96}, "presentation": {"elo": 1450.79, "lower95ci": 1439.32, "upper95ci": 1463.87}}, "briefcaseTotalCost": 328.2326535711718, "timescaleData": {"medianOutputSpeed": 58.4526214739059, "medianTimeToFirstChunk": 30.5742379915}, "outputSpeedVariance": {"p05": 43.3017518894529, "q25": 53.3904951594925, "median": 58.4526214739059, "q75": 72.6180186558127, "p95": 80.8657477089753}, "timeToFirstChunkVariance": {"p05": 15.3900068144, "q25": 18.93420007875, "median": 30.5742379915, "q75": 44.5971731935, "p95": 73.60530861015}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 59.9584077488211, "medianTimeToFirstChunk": 27.1062917005, "medianTimeToFirstAnswerToken": 27.1062917005, "medianEndToEndResponseTime": 35.44540574259747}, "long": {"medianOutputSpeed": 58.4526214739059, "medianTimeToFirstChunk": 30.5742379915, "medianTimeToFirstAnswerToken": 30.5742379915, "medianEndToEndResponseTime": 39.128174280280604}, "hundredK": {"medianOutputSpeed": 62.754490233661, "medianTimeToFirstChunk": 27.297121288, "medianTimeToFirstAnswerToken": 27.297121288, "medianEndToEndResponseTime": 35.264678639486604}, "mediumParallel": {"medianOutputSpeed": 57.4071543739713, "medianTimeToFirstChunk": 26.4933928565, "medianTimeToFirstAnswerToken": 26.4933928565, "medianEndToEndResponseTime": 35.20310866548813}}, "endToEndResponseTime": {"input": 30.5742379915, "reasoning": 0, "answer": 8.553936288780603, "total": 39.128174280280604}, "timeToFirstAnswerToken": {"input": 30.5742379915, "reasoning": 0, "total": 30.5742379915}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 1, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2698f6c6-e436-47ce-a583-dbc25596c571", "slug": "qwen3-next-80b-a3b-instruct", "name": "Qwen3 Next 80B A3B Instruct", "shortName": "Qwen3 Next 80B A3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-11", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-next-80b-a3b-instruct", "name": "Qwen3 Next 80B A3B Instruct"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 80, "inferenceParametersActiveBillions": 3, "sizeClass": "medium", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 9.64335007559183, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -59.5, "omniscienceBreakdown": {"accuracy": 0.1725, "hallucinationRate": 0.9274924471299094}, "gdpval": null, "itBenchSre": null, "tau2": 0.216374269005848, "tauBanking": null, "terminalbenchHard": 0.0757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.526666666666667, "ifbench": 0.396598639455782, "hle": 0.0764596848934198, "gpqa": 0.738383838383838, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.683597883597884, "aime25": 0.663333333333333, "analystAgent": null, "price1mInputTokens": 0.15, "price1mOutputTokens": 1.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.4125, "price1mBlended7To2To1": 0.255, "price1mBlended0To1To1": 0.6749999999999999, "price1mBlended100To1To1": 0.16029411764705884, "price1mBlended0To100To1": 0.1603960396039604, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 184.283508228776, "medianTimeToFirstChunk": 2.19075961649997}, "outputSpeedVariance": {"p05": 165.774914594107, "q25": 174.812219024082, "median": 184.283508228776, "q75": 189.470315065825, "p95": 226.775907608649}, "timeToFirstChunkVariance": {"p05": 2.06373256599999, "q25": 2.12287661849997, "median": 2.19075961649997, "q75": 2.32583467125005, "p95": 3.77119702305012}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 190.03271218884, "medianTimeToFirstChunk": 1.11963705149996, "medianTimeToFirstAnswerToken": 1.11963705149996, "medianEndToEndResponseTime": 3.7507629994532694}, "long": {"medianOutputSpeed": 184.283508228776, "medianTimeToFirstChunk": 2.19075961649997, "medianTimeToFirstAnswerToken": 2.19075961649997, "medianEndToEndResponseTime": 4.903970390517157}, "hundredK": {"medianOutputSpeed": 140.19958101601, "medianTimeToFirstChunk": 21.582538254, "medianTimeToFirstAnswerToken": 21.582538254, "medianEndToEndResponseTime": 25.148882720770573}, "mediumParallel": {"medianOutputSpeed": 186.908147002654, "medianTimeToFirstChunk": 1.15625919500008, "medianTimeToFirstAnswerToken": 1.15625919500008, "medianEndToEndResponseTime": 3.8313699807963792}}, "endToEndResponseTime": {"input": 2.19075961649997, "reasoning": 0, "answer": 2.7132107740171874, "total": 4.903970390517157}, "timeToFirstAnswerToken": {"input": 2.19075961649997, "reasoning": 0, "total": 2.19075961649997}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 8, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "26c0b5df-efa7-470f-a65e-2d883329e493", "slug": "llama-nemotron-super-49b-v1-5", "name": "Llama Nemotron Super 49B v1.5 (Non-reasoning)", "shortName": "Llama Nemotron Super 49B v1.5 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-25", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-nemotron-super-49b-v1-5", "name": "Llama Nemotron Super 49B v1.5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 49, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "NVIDIA Open Model License Agreement", "licenseUrl": "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", "microevalsEnabled": false, "intelligenceIndex": 7.36435496013793, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -46.1833333333333, "omniscienceBreakdown": {"accuracy": 0.126, "hallucinationRate": 0.6725781845919145}, "gdpval": null, "itBenchSre": null, "tau2": 0.251461988304094, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.246666666666667, "ifbench": 0.329251700680272, "hle": 0.0430954587581094, "gpqa": 0.480808080808081, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.28994708994709, "aime25": 0.08, "analystAgent": null, "price1mInputTokens": 0.4, "price1mOutputTokens": 0.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.4, "price1mBlended7To2To1": 0.4000000000000001, "price1mBlended0To1To1": 0.4, "price1mBlended100To1To1": 0.39999999999999997, "price1mBlended0To100To1": 0.39999999999999997, "openness": {"opennessIndex": 52.77777777777778, "modelAvailability": 4, "transparencyMethodology": 4, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 50.9397927856758, "medianTimeToFirstChunk": 8.96743743950003}, "outputSpeedVariance": {"p05": 11.2117140022905, "q25": 18.2111967990686, "median": 50.9397927856758, "q75": 115.674433177855, "p95": 202.120528790632}, "timeToFirstChunkVariance": {"p05": 1.88528057930006, "q25": 3.90341933299995, "median": 8.96743743950003, "q75": 15.1729105485, "p95": 39.1247759413}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 92.2412148723847, "medianTimeToFirstChunk": 7.373740448, "medianTimeToFirstAnswerToken": 7.373740448, "medianEndToEndResponseTime": 12.794310858870539}, "long": {"medianOutputSpeed": 50.9397927856758, "medianTimeToFirstChunk": 8.96743743950003, "medianTimeToFirstAnswerToken": 8.96743743950003, "medianEndToEndResponseTime": 18.782946546568862}, "hundredK": {"medianOutputSpeed": 82.0832724222941, "medianTimeToFirstChunk": 14.4752810195, "medianTimeToFirstAnswerToken": 14.4752810195, "medianEndToEndResponseTime": 20.56665609806227}, "mediumParallel": {"medianOutputSpeed": 60.9813149744157, "medianTimeToFirstChunk": 7.2512184295, "medianTimeToFirstAnswerToken": 7.2512184295, "medianEndToEndResponseTime": 15.450451263520906}}, "endToEndResponseTime": {"input": 8.96743743950003, "reasoning": 0, "answer": 9.815509107068833, "total": 18.782946546568862}, "timeToFirstAnswerToken": {"input": 8.96743743950003, "reasoning": 0, "total": 8.96743743950003}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "26e0f83a-ca98-4f34-94ac-7c5e251ee410", "slug": "gpt-5-6-terra-medium", "name": "GPT-5.6 Terra (medium)", "shortName": "GPT-5.6 Terra (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-5-6-terra", "name": "GPT-5.6 Terra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 30.4205773419377, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 32.32032919174579, "strategyAndOps": 34.91438843020799, "legal": 34.15710723727875, "healthcareAndMedical": 30.994903161685293, "engineering": 31.31683302520773, "economics": 37.29666670528268}, "omniscience": -5.13333333333333, "omniscienceBreakdown": {"accuracy": 0.446, "hallucinationRate": 0.8977135980746089}, "mlcrOverall": 0.122222222222222, "gdpPdfAllPass": 0.17, "gdpval": 1318.34, "gdpvalNormalized": 0.40917, "itBenchSre": null, "tau2": 0.728070175438596, "tauBanking": 0.255670103092783, "terminalbenchHard": null, "terminalBench21": 0.722846441947566, "terminalBench40": 0.0101010101010101, "scicode": 0.50462962962963, "lcr": 0.74, "ifbench": 0.621768707482993, "hle": 0.332715477293791, "gpqa": 0.871717171717172, "critpt": 0.174285714285714, "apexAgents": null, "mmmuPro": 0.767630057803468, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.3353604038418497, "price1mInputTokens": 2, "price1mOutputTokens": 12, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4.5, "price1mBlended7To2To1": 1.7399999999999998, "price1mBlended0To1To1": 7, "price1mBlended100To1To1": 0.3333333333333333, "price1mBlended0To100To1": 2.099009900990099, "intelligenceIndexTimePerTask": 64.27902568215437, "intelligenceIndexCost": {"total": 446.53341803089853, "input": 246.32063003089854, "nonCacheInput": 55.92868, "cacheRead": 83.14699499731319, "cacheWrite": 107.24495503358537, "output": 200.212788, "reasoning": 106.72633199999999, "answer": 93.486456}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.18337295992969213, "input": 0.11763953367692422, "nonCacheInput": 0.04306293187059226, "cacheRead": 0.033143366970953825, "cacheWrite": 0.041433234835378134, "output": 0.06573342625276794, "reasoning": 0.02252548574064227, "answer": 0.043207940512125675}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.05764218190964986}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.02042007288963886}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.015059042398176367}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.034062633641113164}, {"slug": "scicode", "weightedCostPerTask": 0.0014950979166666665}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002552009545875811}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.034910159999999996}, {"slug": "critpt", "weightedCostPerTask": 0.0069639714285714294}, {"slug": "omniscience", "weightedCostPerTask": 0.0006995722}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.009568218}]}, "canonicalIntelligenceIndexTokenCount": {"input": 486597297, "output": 16684399, "answer": 7790538, "reasoning": 8893861}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 1877.1238117201892, "answer": 3600.6617093438053, "output": 5477.785521063995}, "briefcaseBreakdown": {"overall": {"elo": 1040.72, "lower95ci": 1032.78, "upper95ci": 1048.89}, "rubricPassRate": 0.2202020202020202, "analyticalQuality": {"elo": 976.21, "lower95ci": 961.84, "upper95ci": 991.21}, "presentation": {"elo": 1220.98, "lower95ci": 1205.59, "upper95ci": 1235.53}}, "briefcaseTotalCost": 34.96959035852092, "timescaleData": {"medianOutputSpeed": 85.3122260609179, "medianTimeToFirstChunk": 1.82618514749998}, "outputSpeedVariance": {"p05": 61.3628203960713, "q25": 66.8194002712263, "median": 85.3122260609179, "q75": 98.9633874557236, "p95": 120.176669103725}, "timeToFirstChunkVariance": {"p05": 1.17759493195003, "q25": 1.44869068849997, "median": 1.82618514749998, "q75": 2.44084534299998, "p95": 4.33463382189999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 81.4960639211889, "medianTimeToFirstChunk": 1.9128398215, "medianTimeToFirstAnswerToken": 1.9128398215, "medianEndToEndResponseTime": 8.048105452040476}, "long": {"medianOutputSpeed": 85.3122260609179, "medianTimeToFirstChunk": 1.82618514749998, "medianTimeToFirstAnswerToken": 1.82618514749998, "medianEndToEndResponseTime": 7.687009827458171}, "hundredK": {"medianOutputSpeed": 79.0665604024602, "medianTimeToFirstChunk": 2.32860640000004, "medianTimeToFirstAnswerToken": 2.32860640000004, "medianEndToEndResponseTime": 8.65239230209225}, "mediumParallel": {"medianOutputSpeed": 71.8627830754786, "medianTimeToFirstChunk": 5.62014820249988, "medianTimeToFirstAnswerToken": 5.62014820249988, "medianEndToEndResponseTime": 12.577852574662064}}, "endToEndResponseTime": {"input": 1.82618514749998, "reasoning": 0, "answer": 5.860824679958191, "total": 7.687009827458171}, "timeToFirstAnswerToken": {"input": 1.82618514749998, "reasoning": 0, "total": 1.82618514749998}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "27202e5f-c82d-4710-92e9-4317877d4883", "slug": "gemini-2-5-pro", "name": "Gemini 2.5 Pro", "shortName": "Gemini 2.5 Pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-05", "knowledgeCutoffDate": "2025-01-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-pro", "name": "Gemini 2.5 Pro"}, "deprecated": true, "deprecatedTo": "gemini-3-pro", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 16.6573962941864, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 18.142773782714187, "strategyAndOps": 13.597248340817101, "legal": 24.395611413800847, "engineering": 19.44584218191448, "economics": 25.216673424467107}, "omniscience": -16.35, "omniscienceBreakdown": {"accuracy": 0.3905, "hallucinationRate": 0.9089417555373257}, "gdpPdfAllPass": 0.102, "gdpval": 615.9, "gdpvalNormalized": 0.05794999999999999, "itBenchSre": null, "tau2": 0.54093567251462, "tauBanking": 0.0969072164948454, "terminalbenchHard": 0.265151515151515, "terminalBench21": 0.284644194756554, "terminalBench40": 0, "scicode": 0.462962962962963, "lcr": 0.69, "ifbench": 0.487074829931973, "hle": 0.225208526413346, "gpqa": 0.844444444444444, "critpt": 0.0257142857142857, "apexAgents": null, "mmmuPro": 0.749132947976879, "livecodebench": 0.801058201058201, "aime25": 0.876666666666667, "analystAgent": null, "automationBenchPartialScore": 0.021749464193408737, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 1.29, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 1.3375, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.3366336633663367, "intelligenceIndexTimePerTask": 79.91656044882451, "intelligenceIndexCost": {"total": 706.8931435160719, "input": 159.88285351607178, "nonCacheInput": 21.310035, "cacheRead": 26.84998988710314, "cacheWrite": 111.72282862896864, "output": 547.01029, "reasoning": 475.74247, "answer": 71.26782}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.23166603200256353, "input": 0.1261723827130317, "nonCacheInput": 0.013170713617252895, "cacheRead": 0.022836335408506794, "cacheWrite": 0.090165333687272, "output": 0.10549364928953187, "reasoning": 0.06770828935960758, "answer": 0.03778535992992428}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.04960931927325067}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.02386378419603816}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.006476637792309795}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.08247727626474503}, {"slug": "scicode", "weightedCostPerTask": 0.007984639756944445}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.014609955746061165}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.010541543749999998}, {"slug": "critpt", "weightedCostPerTask": 0.026686426785714285}, {"slug": "omniscience", "weightedCostPerTask": 0.0025901296874999997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.006826318750000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 321226210, "output": 54701029, "answer": 7126782, "reasoning": 47574247}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 6770.828935960761, "answer": 3778.535992992429, "output": 10549.36492895319}, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 315.4, "lower95ci": 305.74, "upper95ci": 324.38}, "rubricPassRate": 0.06565656565656566, "analyticalQuality": {"elo": 49.89, "lower95ci": 30.14, "upper95ci": 70.14}, "presentation": {"elo": 278.48, "lower95ci": 260.47, "upper95ci": 294.76}}, "briefcaseTotalCost": 30.096320359105405, "timescaleData": {"medianOutputSpeed": 127.81105866417, "medianTimeToFirstChunk": 21.5809371745001}, "outputSpeedVariance": {"p05": 105.020361017006, "q25": 121.529567443035, "median": 127.81105866417, "q75": 136.828606233485, "p95": 148.182556640748}, "timeToFirstChunkVariance": {"p05": 13.2699905589999, "q25": 18.2546842589999, "median": 21.5809371745001, "q75": 28.0446493265, "p95": 34.8963179010002}, "performanceByPromptType": {"long": {"medianOutputSpeed": 127.81105866417, "medianTimeToFirstChunk": 21.5809371745001, "medianTimeToFirstAnswerToken": 21.5809371745001, "medianEndToEndResponseTime": 25.49296173032336}}, "endToEndResponseTime": {"input": 21.5809371745001, "reasoning": 0, "answer": 3.912024555823258, "total": 25.49296173032336}, "timeToFirstAnswerToken": {"input": 21.5809371745001, "reasoning": 0, "total": 21.5809371745001}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 2, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "272ff333-442f-4169-a804-ac9177bc99d7", "slug": "minimax-m2-1", "name": "MiniMax-M2.1", "shortName": "MiniMax-M2.1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-23", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "minimax-m2-1", "name": "MiniMax-M2.1"}, "deprecated": true, "deprecatedTo": "minimax-m2-5", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 230, "inferenceParametersActiveBillions": 10, "sizeClass": "large", "contextWindowTokens": 204800, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/MiniMaxAI/MiniMax-M2-1", "microevalsEnabled": false, "intelligenceIndex": 20.9452850207622, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -32.8666666666667, "omniscienceBreakdown": {"accuracy": 0.21166666666666667, "hallucinationRate": 0.6854122621564482}, "gdpval": null, "itBenchSre": null, "tau2": 0.853801169590643, "tauBanking": null, "terminalbenchHard": 0.287878787878788, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.676666666666667, "ifbench": 0.698639455782313, "hle": 0.231696014828545, "gpqa": 0.83030303030303, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.80952380952381, "aime25": 0.826666666666667, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 1.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5249999999999999, "price1mBlended7To2To1": 0.39, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.3088235294117647, "price1mBlended0To100To1": 0.3089108910891089, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 93.0584382077408, "medianTimeToFirstChunk": 1.82207972150007}, "outputSpeedVariance": {"p05": 67.6268522788104, "q25": 74.0844468778306, "median": 93.0584382077408, "q75": 107.47740831121, "p95": 121.166368885358}, "timeToFirstChunkVariance": {"p05": 1.33492865215, "q25": 1.56114244675, "median": 1.82207972150007, "q75": 2.16091240749997, "p95": 3.18432297319998}, "performanceByPromptType": {"long": {"medianOutputSpeed": 93.0584382077408, "medianTimeToFirstChunk": 1.82207972150007, "medianTimeToFirstAnswerToken": 23.313951265005468, "medianEndToEndResponseTime": 28.686919150881817}}, "endToEndResponseTime": {"input": 1.82207972150007, "reasoning": 21.491871543505397, "answer": 5.372967885876349, "total": 28.686919150881817}, "timeToFirstAnswerToken": {"input": 1.82207972150007, "reasoning": 21.491871543505397, "total": 23.313951265005468}, "performanceDataSource": {"type": "firstParty", "providerName": "MiniMax"}, "hostModelCount": 3, "creator": {"id": "a31a9071-6144-4dbb-92dc-2e02d653ecea", "slug": "minimax", "name": "MiniMax", "logo": "/img/logos/minimax_small.svg", "color": "#EB3568", "country": "cn", "url": "https://minimaxi.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "277f939a-985b-4b37-859d-b3eabc7c0b26", "slug": "minimax-m3", "name": "MiniMax-M3", "shortName": "MiniMax-M3", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-06-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "minimax-m3", "name": "MiniMax-M3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 428, "inferenceParametersActiveBillions": 23, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "MINIMAX COMMUNITY LICENSE", "licenseUrl": "https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/MiniMaxAI/MiniMax-M3", "microevalsEnabled": true, "intelligenceIndex": 29.6125932236316, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 30.680173606031005, "strategyAndOps": 25.66512496179065, "legal": 32.02544933331668, "healthcareAndMedical": 30.18537551299024, "engineering": 31.608313614297362, "economics": 44.21488189295645}, "omniscience": 1.35, "omniscienceBreakdown": {"accuracy": 0.167, "hallucinationRate": 0.1842737094837935}, "mlcrOverall": 0.172222222222222, "harveyLab": 0.884064264003474, "gdpPdfAllPass": 0.098, "gdpval": 1303.96, "gdpvalNormalized": 0.40198, "itBenchSre": null, "tau2": 0.888888888888889, "tauBanking": 0.152577319587629, "terminalbenchHard": 0.424242424242424, "terminalBench21": 0.651685393258427, "terminalBench40": 0.0202020202020202, "scicode": 0.471064814814815, "lcr": 0.83, "ifbench": 0.828571428571429, "hle": 0.389712696941613, "gpqa": 0.929292929292929, "critpt": 0.0371428571428571, "apexAgents": null, "mmmuPro": 0.785549132947977, "livecodebench": null, "aime25": null, "analystAgent": 0.1, "automationBenchPartialScore": 0.21251257600749407, "enterpriseOpsGym": 0.3210981796478663, "price1mInputTokens": 0.3, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.06, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": 0.375, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5249999999999999, "price1mBlended7To2To1": 0.22199999999999998, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.07352941176470588, "price1mBlended0To100To1": 0.3089108910891089, "intelligenceIndexTimePerTask": 361.2268444555616, "intelligenceIndexCost": {"total": 537.9784470272406, "input": 397.50768662724056, "nonCacheInput": 9.651415799999999, "cacheRead": 300.46775615195423, "cacheWrite": 87.38851467528632, "output": 140.4707604, "reasoning": 105.51258119999999, "answer": 34.9581792}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.5076126905781733, "input": 0.44978224884613227, "nonCacheInput": 0.006632555000846242, "cacheRead": 0.3556943830256406, "cacheWrite": 0.08745531081964547, "output": 0.05783044173204086, "reasoning": 0.026181895131328185, "answer": 0.03164854660071267}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.1409294180290121}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.034830452813155055}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.005769193508959136}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.303987715847943}, {"slug": "scicode", "weightedCostPerTask": 0.002607846770833333}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0025920784893419834}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0053294001}, {"slug": "critpt", "weightedCostPerTask": 0.00955445957142857}, {"slug": "omniscience", "weightedCostPerTask": 0.0005243618474999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0014877636}]}, "canonicalIntelligenceIndexTokenCount": {"input": 5273003361, "output": 117058967, "answer": 29131816, "reasoning": 87927151}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 21818.245942773487, "answer": 26373.78883392722, "output": 48192.034776700704}, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1096.03, "lower95ci": 1089.75, "upper95ci": 1102.54}, "rubricPassRate": 0.30303030303030304, "analyticalQuality": {"elo": 1055.51, "lower95ci": 1043.38, "upper95ci": 1067.59}, "presentation": {"elo": 1177.57, "lower95ci": 1166.95, "upper95ci": 1187.85}}, "briefcaseTotalCost": 85.49718027093401, "timescaleData": {"medianOutputSpeed": 130.437886425487, "medianTimeToFirstChunk": 1.25567153099998}, "outputSpeedVariance": {"p05": 46.9019946806108, "q25": 74.7246402942235, "median": 130.437886425487, "q75": 170.850402504205, "p95": 231.989125699878}, "timeToFirstChunkVariance": {"p05": 0.778811834399989, "q25": 0.978450163499964, "median": 1.25567153099998, "q75": 2.04538319124998, "p95": 2.97626364550002}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 110.273902594475, "medianTimeToFirstChunk": 1.03524519000001, "medianTimeToFirstAnswerToken": 19.171902666926965, "medianEndToEndResponseTime": 23.706067036158704}, "long": {"medianOutputSpeed": 130.437886425487, "medianTimeToFirstChunk": 1.25567153099998, "medianTimeToFirstAnswerToken": 16.5886400021083, "medianEndToEndResponseTime": 20.421882119885378}, "hundredK": {"medianOutputSpeed": 134.751184945165, "medianTimeToFirstChunk": 3.54077012150003, "medianTimeToFirstAnswerToken": 18.382940161146585, "medianEndToEndResponseTime": 22.093482671058226}, "mediumParallel": {"medianOutputSpeed": 146.626253789265, "medianTimeToFirstChunk": 0.774955578499999, "medianTimeToFirstAnswerToken": 14.415077646096782, "medianEndToEndResponseTime": 17.825108162995978}}, "endToEndResponseTime": {"input": 1.25567153099998, "reasoning": 15.33296847110832, "answer": 3.83324211777708, "total": 20.421882119885378}, "timeToFirstAnswerToken": {"input": 1.25567153099998, "reasoning": 15.33296847110832, "total": 16.5886400021083}, "performanceDataSource": {"type": "firstParty", "providerName": "MiniMax"}, "hostModelCount": 15, "creator": {"id": "a31a9071-6144-4dbb-92dc-2e02d653ecea", "slug": "minimax", "name": "MiniMax", "logo": "/img/logos/minimax_small.svg", "color": "#EB3568", "country": "cn", "url": "https://minimaxi.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "291a510a-dcc0-40df-8a80-b3aa31900a6c", "slug": "grok-2-1212", "name": "Grok 2 (Dec '24)", "shortName": "Grok 2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-12", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "grok-2-1212", "name": "Grok 2 (Dec '24)"}, "deprecated": true, "deprecatedTo": "grok-3", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 270, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 131072, "licenseName": "Grok 2 Community License Agreement", "licenseUrl": "https://huggingface.co/xai-org/grok-2/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/xai-org/grok-2", "microevalsEnabled": false, "intelligenceIndex": 7.10559707757169, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0306, "gpqa": 0.51010101010101, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.266666666666667, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "296ace9b-0815-43b2-bafa-fd6cec5cce36", "slug": "mimo-v2-omni-0327", "name": "MiMo-V2-Omni-0327", "shortName": "MiMo-V2-Omni-0327", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-27", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "mimo-v2-omni-0327", "name": "MiMo-V2-Omni-0327"}, "deprecated": true, "deprecatedTo": "mimo-v2-omni-0401", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 25.1205269950478, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -15.1, "omniscienceBreakdown": {"accuracy": 0.17816666666666667, "hallucinationRate": 0.4005272764145204}, "gdpval": null, "itBenchSre": null, "tau2": 0.880116959064328, "tauBanking": null, "terminalbenchHard": 0.356060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.733333333333333, "ifbench": 0.673469387755102, "hle": 0.225671918443003, "gpqa": 0.854545454545455, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": 0.739306358381503, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5147c8b4-61d5-4070-9324-8adf8aa144c2", "slug": "xiaomi", "name": "Xiaomi", "logo": "/img/logos/xiaomi_small.svg", "color": "#ff6900", "country": "cn", "url": "https://huggingface.co/XiaomiMiMo"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "29855680-7469-43eb-8b88-cd3fb1d99da3", "slug": "gpt-5-mini", "name": "GPT-5 mini (high)", "shortName": "GPT-5 mini (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-05-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5-mini", "name": "GPT-5 mini"}, "deprecated": true, "deprecatedTo": "gpt-5-4-mini", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 17.4073881042515, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 18.17540658462189, "strategyAndOps": 13.536968913957123, "legal": 20.77520729530068, "engineering": 21.3071076459685, "economics": 28.517622007259817}, "omniscience": -17.3166666666667, "omniscienceBreakdown": {"accuracy": 0.24966666666666668, "hallucinationRate": 0.5635273211905819}, "gdpPdfAllPass": 0.084, "gdpval": 880.27, "gdpvalNormalized": 0.190135, "itBenchSre": null, "tau2": 0.684210526315789, "tauBanking": 0.154639175257732, "terminalbenchHard": 0.333333333333333, "terminalBench21": 0.0374531835205993, "terminalBench40": 0, "scicode": 0.390046296296296, "lcr": 0.723333333333333, "ifbench": 0.754421768707483, "hle": 0.214550509731233, "gpqa": 0.828282828282828, "critpt": 0, "apexAgents": null, "mmmuPro": 0.700578034682081, "livecodebench": 0.838095238095238, "aime25": 0.906666666666667, "analystAgent": null, "automationBenchPartialScore": 0.06487466331916088, "price1mInputTokens": 0.25, "price1mOutputTokens": 2, "cacheHitPrice": 0.025, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.41, "price1mBlended0To3To1": 0.6875, "price1mBlended7To2To1": 0.26749999999999996, "price1mBlended0To1To1": 1.125, "price1mBlended100To1To1": 0.04656862745098039, "price1mBlended0To100To1": 0.26732673267326734, "intelligenceIndexTimePerTask": 236.21513403101102, "intelligenceIndexCost": {"total": 188.65757986463046, "input": 40.41511786463049, "nonCacheInput": 4.5950175, "cacheRead": 20.023575292818837, "cacheWrite": 15.79652507181165, "output": 148.242462, "reasoning": 129.449434, "answer": 18.793028}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.05349965791130692, "input": 0.020210159436472985, "nonCacheInput": 0.0029452641150660335, "cacheRead": 0.009922190791165662, "cacheWrite": 0.007342704530241291, "output": 0.033289498474833944, "reasoning": 0.023045673792997025, "answer": 0.010243824681836912}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.012402014264753234}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.004880851624927167}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0037635980353256633}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.014864751441910937}, {"slug": "scicode", "weightedCostPerTask": 0.0010917830729166667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0029077999768303987}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.003626325}, {"slug": "critpt", "weightedCostPerTask": 0.007689965357142859}, {"slug": "omniscience", "weightedCostPerTask": 0.0008337448874999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0014388242499999999}]}, "canonicalIntelligenceIndexTokenCount": {"input": 882509182, "output": 74121231, "answer": 9396514, "reasoning": 64724717}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 11522.83689649851, "answer": 5121.912340918456, "output": 16644.749237416967}, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 437.58, "lower95ci": 427.76, "upper95ci": 446.91}, "rubricPassRate": 0.08282828282828283, "analyticalQuality": {"elo": 368.26, "lower95ci": 349.93, "upper95ci": 387.21}, "presentation": {"elo": 292.06, "lower95ci": 272.27, "upper95ci": 310.1}}, "briefcaseTotalCost": 7.523888653950295, "timescaleData": {"medianOutputSpeed": 69.1716324536816, "medianTimeToFirstChunk": 123.105517083}, "outputSpeedVariance": {"p05": 47.5312354571442, "q25": 64.2895598749517, "median": 69.1716324536816, "q75": 74.8485657635354, "p95": 91.1651141386731}, "timeToFirstChunkVariance": {"p05": 53.8050973532501, "q25": 77.8118271589999, "median": 123.105517083, "q75": 218.3585739625, "p95": 339.7753462673}, "performanceByPromptType": {"long": {"medianOutputSpeed": 69.1716324536816, "medianTimeToFirstChunk": 123.105517083, "medianTimeToFirstAnswerToken": 123.105517083, "medianEndToEndResponseTime": 130.33391378644353}}, "endToEndResponseTime": {"input": 123.105517083, "reasoning": 0, "answer": 7.228396703443536, "total": 130.33391378644353}, "timeToFirstAnswerToken": {"input": 123.105517083, "reasoning": 0, "total": 123.105517083}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "29976311-665a-4b2f-ac72-557c33e0758e", "slug": "nemotron-3-5-lightning", "name": "Nemotron 3.5 Lightning", "shortName": "Nemotron 3.5 Lightning", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "nemotron-3-5-lightning", "name": "Nemotron 3.5 Lightning"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 31.6, "inferenceParametersActiveBillions": 3.6, "sizeClass": "small", "contextWindowTokens": 1000000, "licenseName": "OpenMDW-1.1", "licenseUrl": "https://openmdw.ai/license/1-1/", "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 13.6352556217144, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 13.371527167546255, "strategyAndOps": 8.26463990339053, "legal": 16.422799876296732, "healthcareAndMedical": 12.492734210636172, "engineering": 18.822508317184834, "economics": 23.74822256333026}, "omniscience": -17.7166666666667, "omniscienceBreakdown": {"accuracy": 0.14433333333333334, "hallucinationRate": 0.3757304246201792}, "mlcrOverall": 0.0111111111111111, "gdpPdfAllPass": 0.03, "gdpval": 766.89, "gdpvalNormalized": 0.13344499999999998, "itBenchSre": null, "tau2": null, "tauBanking": 0.088659793814433, "terminalbenchHard": null, "terminalBench21": 0.243445692883895, "terminalBench40": 0.00505050505050505, "scicode": 0.320601851851852, "lcr": 0.603333333333333, "ifbench": null, "hle": 0.105653382761817, "gpqa": 0.743434343434343, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.008410069634719542, "enterpriseOpsGym": 0.18352730528200537, "price1mInputTokens": 0.06, "price1mOutputTokens": 0.2, "cacheHitPrice": 0.05, "cacheHitDiscountPercent": 0.5, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.095, "price1mBlended7To2To1": 0.067, "price1mBlended0To1To1": 0.13, "price1mBlended100To1To1": 0.05156862745098039, "price1mBlended0To100To1": 0.061386138613861385, "intelligenceIndexTimePerTask": 118.28473999750634, "intelligenceIndexCost": {"total": 105.47767858, "input": 81.29123418, "nonCacheInput": 1.06195218, "cacheRead": 0, "cacheWrite": 80.229282, "output": 24.1864444, "reasoning": 19.2445752, "answer": 4.9418692}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.09309918417597017, "input": 0.08573949660515129, "nonCacheInput": 0.0006088997905380644, "cacheRead": 0, "cacheWrite": 0.08513059681461324, "output": 0.007359687570818874, "reasoning": 0.003395932204264034, "answer": 0.003963755366554841}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.046060967406593406}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.008515721936363636}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0013779571308980213}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.03447366406060606}, {"slug": "scicode", "weightedCostPerTask": 0.00032312875694444446}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0005344758183503243}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00050201838}, {"slug": "critpt", "weightedCostPerTask": 0.0008246710857142858}, {"slug": "omniscience", "weightedCostPerTask": 9.008988049999999e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0003964897199999999}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1354853903, "output": 120932222, "answer": 24709346, "reasoning": 96222876}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 16979.66102132017, "answer": 19818.7768327742, "output": 36798.43785409437}, "openness": {"opennessIndex": 83.33333333333333, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "briefcaseBreakdown": {"overall": {"elo": 508.5, "lower95ci": 498.79, "upper95ci": 518.44}, "rubricPassRate": 0.08888888888888889, "analyticalQuality": {"elo": 356.49, "lower95ci": 335.86, "upper95ci": 377.1}, "presentation": {"elo": 495.41, "lower95ci": 478.61, "upper95ci": 512.46}}, "briefcaseTotalCost": 27.94365356, "timescaleData": {"medianOutputSpeed": 292.620729320668, "medianTimeToFirstChunk": 0.601090442000042}, "outputSpeedVariance": {"p05": 114.506611754004, "q25": 196.68027620084, "median": 292.620729320668, "q75": 327.828556808792, "p95": 567.678211165765}, "timeToFirstChunkVariance": {"p05": 0.399112976399971, "q25": 0.457329731249956, "median": 0.601090442000042, "q75": 1.136863312, "p95": 3.29443536269972}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 271.472480225367, "medianTimeToFirstChunk": 0.454255143000026, "medianTimeToFirstAnswerToken": 7.821484404469437, "medianEndToEndResponseTime": 9.66329171983679}, "long": {"medianOutputSpeed": 292.620729320668, "medianTimeToFirstChunk": 0.601090442000042, "medianTimeToFirstAnswerToken": 7.435876223045318, "medianEndToEndResponseTime": 9.144572668306637}, "hundredK": {"medianOutputSpeed": 304.791028382322, "medianTimeToFirstChunk": 2.27950863649997, "medianTimeToFirstAnswerToken": 8.841381571589292, "medianEndToEndResponseTime": 10.481849805361623}, "mediumParallel": {"medianOutputSpeed": 194.670465279576, "medianTimeToFirstChunk": 0.514462909999565, "medianTimeToFirstAnswerToken": 10.788235036283334, "medianEndToEndResponseTime": 13.356678067854276}}, "endToEndResponseTime": {"input": 0.601090442000042, "reasoning": 6.834785781045276, "answer": 1.708696445261319, "total": 9.144572668306637}, "timeToFirstAnswerToken": {"input": 0.601090442000042, "reasoning": 6.834785781045276, "total": 7.435876223045318}, "performanceDataSource": {"type": "median"}, "hostModelCount": 7, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2aacdc07-5f4e-4ab9-8ea5-5f7ab93f9eeb", "slug": "qwen3-4b-2507-instruct-reasoning", "name": "Qwen3 4B 2507 (Reasoning)", "shortName": "Qwen3 4B 2507", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-06", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-4b-2507-instruct", "name": "Qwen3 4B 2507"}, "deprecated": true, "deprecatedTo": "qwen3-5-4b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 4.02, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507", "microevalsEnabled": false, "intelligenceIndex": 8.79842923104994, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -60.2666666666667, "omniscienceBreakdown": {"accuracy": 0.12533333333333332, "hallucinationRate": 0.8323170731707317}, "gdpval": null, "itBenchSre": null, "tau2": 0.254385964912281, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.373333333333333, "ifbench": 0.497959183673469, "hle": 0.061631139944393, "gpqa": 0.666666666666667, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.641269841269841, "aime25": 0.826666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2ac96b67-f4f8-4c8c-ac08-c7510faa7bb9", "slug": "gemini-1-5-pro", "name": "Gemini 1.5 Pro (Sep '24)", "shortName": "Gemini 1.5 Pro (Sep)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-24", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-1-5-pro", "name": "Gemini 1.5 Pro (Sep '24)"}, "deprecated": true, "deprecatedTo": "gemini-2-0-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.90554657851904, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0464, "gpqa": 0.588888888888889, "critpt": null, "apexAgents": null, "mmmuPro": 0.55028901734104, "livecodebench": 0.316402116402116, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2ae624ca-25b4-4cc8-8970-cdfdd3320691", "slug": "gemini-1-0-ultra", "name": "Gemini 1.0 Ultra", "shortName": "Gemini 1.0 Ultra", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-12-06", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-1-0-ultra", "name": "Gemini 1.0 Ultra"}, "deprecated": true, "deprecatedTo": "gemini-2-0-pro-experimental-02-05", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 32768, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.83837664836323, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2bb84433-f38e-4edc-9b65-4d7b1f473db9", "slug": "qwen3-1.7b-instruct", "name": "Qwen3 1.7B (Non-reasoning)", "shortName": "Qwen3 1.7B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-1.7b-instruct", "name": "Qwen3 1.7B"}, "deprecated": true, "deprecatedTo": "qwen3-5-2b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 2.03, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-1.7B", "microevalsEnabled": false, "intelligenceIndex": 4.8568135993386, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -84.0833333333333, "omniscienceBreakdown": {"accuracy": 0.06916666666666667, "hallucinationRate": 0.9776186213070726}, "gdpval": null, "itBenchSre": null, "tau2": 0.216374269005848, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.210884353741497, "hle": 0.0532, "gpqa": 0.282828282828283, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.125925925925926, "aime25": 0.0733333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2bfdd17a-e027-4068-a54e-b0e90a6df118", "slug": "gemma-3-27b", "name": "Gemma 3 27B Instruct", "shortName": "Gemma 3 27B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-12", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-3-27b-instruct", "name": "Gemma 3 27B Instruct"}, "deprecated": true, "deprecatedTo": "gemma-4-31b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 27.4, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Gemma license", "licenseUrl": "https://ai.google.dev/gemma/terms", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-3-27b-it", "microevalsEnabled": false, "intelligenceIndex": 4.85297805617922, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 5.038942127019917, "strategyAndOps": 3.64848076896151, "legal": 4.587571325388226, "engineering": 6.89, "economics": 7.664166666666667}, "omniscience": -67.2166666666667, "omniscienceBreakdown": {"accuracy": 0.1295, "hallucinationRate": 0.9209266704958836}, "gdpPdfAllPass": 0.002, "gdpval": -171.05, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.105263157894737, "tauBanking": 0.00824742268041237, "terminalbenchHard": 0.0378787878787879, "terminalBench21": 0.0449438202247191, "terminalBench40": 0, "scicode": 0.232638888888889, "lcr": 0.0733333333333333, "ifbench": 0.318367346938776, "hle": 0.044, "gpqa": 0.428282828282828, "critpt": 0, "apexAgents": null, "mmmuPro": 0.480346820809249, "livecodebench": 0.136507936507936, "aime25": 0.206666666666667, "analystAgent": null, "automationBenchPartialScore": 0.0019111706206154657, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "intelligenceIndexCost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "intelligenceIndexCostPerTask": {"cost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0}, {"slug": "gdpval-aa", "weightedCostPerTask": 0}, {"slug": "automationbench-aa", "weightedCostPerTask": 0}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0}, {"slug": "scicode", "weightedCostPerTask": 0}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0}, {"slug": "gdp-pdf", "weightedCostPerTask": 0}, {"slug": "critpt", "weightedCostPerTask": 0}, {"slug": "omniscience", "weightedCostPerTask": 0}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1739694982, "output": 10685759, "answer": 10685759, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 8893.943845424661, "output": 8893.943845424661}, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseTotalCost": 0, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 6, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2c4394a2-b443-470a-908e-5c4a271b780c", "slug": "glm-4-7-flash", "name": "GLM-4.7-Flash (Reasoning)", "shortName": "GLM-4.7-Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "glm-4-7-flash", "name": "GLM-4.7-Flash"}, "deprecated": true, "deprecatedTo": "glm-5", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 31.2, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 200000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-4.7-Flash", "microevalsEnabled": false, "intelligenceIndex": 14.8719733920138, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -62.6166666666667, "omniscienceBreakdown": {"accuracy": 0.1615, "hallucinationRate": 0.9393758696084278}, "gdpval": null, "itBenchSre": null, "tau2": 0.988304093567251, "tauBanking": null, "terminalbenchHard": 0.21969696969697, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.416666666666667, "ifbench": 0.608163265306122, "hle": 0.0759962928637627, "gpqa": 0.580808080808081, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.07, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.07, "cacheHitDiscountPercent": 0.8333333333333333, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15250000000000002, "price1mBlended7To2To1": 0.10300000000000002, "price1mBlended0To1To1": 0.23500000000000001, "price1mBlended100To1To1": 0.07323529411764708, "price1mBlended0To100To1": 0.07326732673267328, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 72.4295515238497, "medianTimeToFirstChunk": 1.58003290049998}, "outputSpeedVariance": {"p05": 20.7945195713166, "q25": 49.0980148086028, "median": 72.4295515238497, "q75": 166.970977701346, "p95": 224.899695532461}, "timeToFirstChunkVariance": {"p05": 0.903331533650027, "q25": 1.01383766375002, "median": 1.58003290049998, "q75": 4.18154149075, "p95": 61.46396775595}, "performanceByPromptType": {"long": {"medianOutputSpeed": 72.4295515238497, "medianTimeToFirstChunk": 1.58003290049998, "medianTimeToFirstAnswerToken": 29.19307147276613, "medianEndToEndResponseTime": 36.09633111583266}}, "endToEndResponseTime": {"input": 1.58003290049998, "reasoning": 27.61303857226615, "answer": 6.903259643066537, "total": 36.09633111583266}, "timeToFirstAnswerToken": {"input": 1.58003290049998, "reasoning": 27.61303857226615, "total": 29.19307147276613}, "performanceDataSource": {"type": "median"}, "hostModelCount": 3, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2cd04201-2b6e-47ef-853e-7601f705f2a8", "slug": "phi-4-multimodal", "name": "Phi-4 Multimodal Instruct", "shortName": "Phi-4 Multimodal", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-26", "knowledgeCutoffDate": "2024-06-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "phi-4-multimodal", "name": "Phi-4 Multimodal Instruct"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 5.6, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/microsoft/Phi-4-multimodal-instruct", "microevalsEnabled": false, "intelligenceIndex": 5.80520041934726, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.05, "gpqa": 0.315151515151515, "critpt": null, "apexAgents": null, "mmmuPro": 0.145086705202312, "livecodebench": 0.131216931216931, "aime25": null, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 17.0522398289197, "medianTimeToFirstChunk": 0.890364648500054}, "outputSpeedVariance": {"p05": 16.4281868853492, "q25": 16.9698371048055, "median": 17.0522398289197, "q75": 17.1069079766364, "p95": 17.2415888084169}, "timeToFirstChunkVariance": {"p05": 0.831170414550047, "q25": 0.856941897249954, "median": 0.890364648500054, "q75": 0.901982324499955, "p95": 1.03973055410001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 17.3384837003245, "medianTimeToFirstChunk": 0.41641163449998, "medianTimeToFirstAnswerToken": 0.41641163449998, "medianEndToEndResponseTime": 29.253996779886265}, "long": {"medianOutputSpeed": 17.0522398289197, "medianTimeToFirstChunk": 0.890364648500054, "medianTimeToFirstAnswerToken": 0.890364648500054, "medianEndToEndResponseTime": 30.21202590921176}, "hundredK": {"medianOutputSpeed": 16.6625344660203, "medianTimeToFirstChunk": 14.988907604, "medianTimeToFirstAnswerToken": 14.988907604, "medianEndToEndResponseTime": 44.99634740972966}, "mediumParallel": {"medianOutputSpeed": 23.0833456192636, "medianTimeToFirstChunk": 0.51673700550009, "medianTimeToFirstAnswerToken": 0.51673700550009, "medianEndToEndResponseTime": 22.177375296283127}}, "endToEndResponseTime": {"input": 0.890364648500054, "reasoning": 0, "answer": 29.321661260711707, "total": 30.21202590921176}, "timeToFirstAnswerToken": {"input": 0.890364648500054, "reasoning": 0, "total": 0.890364648500054}, "performanceDataSource": {"type": "firstParty", "providerName": "Microsoft"}, "hostModelCount": 1, "creator": {"id": "ef5ce458-9986-4652-915a-e31fac5506b0", "slug": "azure", "name": "Microsoft", "logo": "/img/logos/microsoft_small.svg", "color": "#0078D5", "country": "us", "url": "https://azure.microsoft.com/en-us"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2cff73da-4855-403c-afc9-5540feadcc15", "slug": "granite-3-3-8b-instruct", "name": "Granite 3.3 8B (Non-reasoning)", "shortName": "Granite 3.3 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-16", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "granite-3-3-8b-instruct", "name": "Granite 3.3 8B"}, "deprecated": true, "deprecatedTo": "granite-4-0-micro", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8.17, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-3.3-8b-instruct", "microevalsEnabled": false, "intelligenceIndex": 4.92158293624767, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -77.2833333333333, "omniscienceBreakdown": {"accuracy": 0.0965, "hallucinationRate": 0.9621840988747463}, "gdpval": null, "itBenchSre": null, "tau2": 0.105263157894737, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.224489795918367, "hle": 0.0417052826691381, "gpqa": 0.338383838383838, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.126984126984127, "aime25": 0.0666666666666667, "analystAgent": null, "price1mInputTokens": 0.03, "price1mOutputTokens": 0.25, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.08499999999999999, "price1mBlended7To2To1": 0.052000000000000005, "price1mBlended0To1To1": 0.14, "price1mBlended100To1To1": 0.03215686274509804, "price1mBlended0To100To1": 0.03217821782178218, "timescaleData": {"medianOutputSpeed": 16.3900485350026, "medianTimeToFirstChunk": 26.662879076}, "outputSpeedVariance": {"p05": 11.0451329956696, "q25": 14.6479859616086, "median": 16.3900485350026, "q75": 33.8317398336494, "p95": 43.1677553093777}, "timeToFirstChunkVariance": {"p05": 9.8820265357, "q25": 14.0719053782499, "median": 26.662879076, "q75": 27.4579558692501, "p95": 28.6524271869001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 16.3900485350026, "medianTimeToFirstChunk": 26.662879076, "medianTimeToFirstAnswerToken": 26.662879076, "medianEndToEndResponseTime": 57.16919508429001}}, "endToEndResponseTime": {"input": 26.662879076, "reasoning": 0, "answer": 30.50631600829001, "total": 57.16919508429001}, "timeToFirstAnswerToken": {"input": 26.662879076, "reasoning": 0, "total": 26.662879076}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2d19c2d1-062d-436e-b2c2-3d3ecad34acc", "slug": "deepseek-v2", "name": "DeepSeek-V2-Chat", "shortName": "DeepSeek-V2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-05-06", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v2", "name": "DeepSeek-V2-Chat"}, "deprecated": true, "deprecatedTo": "deepseek-v3-0324", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 236, "inferenceParametersActiveBillions": 21, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "DEEPSEEK LICENSE AGREEMENT", "licenseUrl": "https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V2-Chat", "microevalsEnabled": false, "intelligenceIndex": 5.50606445861584, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2d28a13a-096e-475a-beb8-26bbd1c7d51c", "slug": "qwen3-5-9b", "name": "Qwen3.5 9B (Reasoning)", "shortName": "Qwen3.5 9B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-5-9b", "name": "Qwen3.5 9B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 9.65, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-9B", "microevalsEnabled": false, "intelligenceIndex": 13.6541001649716, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -53.4666666666667, "omniscienceBreakdown": {"accuracy": 0.16416666666666666, "hallucinationRate": 0.8360917248255234}, "gdpval": 588.42, "gdpvalNormalized": 0.04420999999999998, "itBenchSre": null, "tau2": 0.868421052631579, "tauBanking": 0.0701030927835052, "terminalbenchHard": 0.242424242424242, "terminalBench21": 0.292134831460674, "terminalBench40": null, "scicode": null, "lcr": 0.7, "ifbench": 0.66734693877551, "hle": 0.149212233549583, "gpqa": 0.806060606060606, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.692485549132948, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.135, "price1mOutputTokens": 0.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15125, "price1mBlended7To2To1": 0.14150000000000001, "price1mBlended0To1To1": 0.1675, "price1mBlended100To1To1": 0.13563725490196077, "price1mBlended0To100To1": 0.13564356435643563, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 68.8857087425941, "medianTimeToFirstChunk": 1.85800168100002}, "outputSpeedVariance": {"p05": 13.3062096832956, "q25": 52.5214574842882, "median": 68.8857087425941, "q75": 91.8163751245216, "p95": 104.01104958919}, "timeToFirstChunkVariance": {"p05": 0.603569809000056, "q25": 0.720817715499948, "median": 1.85800168100002, "q75": 2.57861074799985, "p95": 5.34380086480005}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 72.6786675106352, "medianTimeToFirstChunk": 0.707784119999928, "medianTimeToFirstAnswerToken": 28.226175258738632, "medianEndToEndResponseTime": 35.105773043423305}, "long": {"medianOutputSpeed": 68.8857087425941, "medianTimeToFirstChunk": 1.85800168100002, "medianTimeToFirstAnswerToken": 30.891600035535635, "medianEndToEndResponseTime": 38.14999962416954}, "hundredK": {"medianOutputSpeed": 72.1567926791368, "medianTimeToFirstChunk": 9.84087284950001, "medianTimeToFirstAnswerToken": 37.55829106809378, "medianEndToEndResponseTime": 44.48764562274222}, "mediumParallel": {"medianOutputSpeed": 72.5321906367754, "medianTimeToFirstChunk": 0.908495684999991, "medianTimeToFirstAnswerToken": 28.48245949943298, "medianEndToEndResponseTime": 35.37595045304123}}, "endToEndResponseTime": {"input": 1.85800168100002, "reasoning": 29.033598354535616, "answer": 7.258399588633904, "total": 38.14999962416954}, "timeToFirstAnswerToken": {"input": 1.85800168100002, "reasoning": 29.033598354535616, "total": 30.891600035535635}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2dad8957-4c16-4e74-bf2d-8b21514e0ae9", "slug": "o3-mini", "name": "o3-mini", "shortName": "o3-mini", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-31", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "o3-mini", "name": "o3-mini"}, "deprecated": true, "deprecatedTo": "gpt-5-mini-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.4707708274399, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.286549707602339, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0791, "gpqa": 0.748484848484848, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.717460317460317, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.1, "price1mOutputTokens": 4.4, "cacheHitPrice": 0.55, "cacheHitDiscountPercent": 0.5, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.9250000000000003, "price1mBlended7To2To1": 1.0450000000000002, "price1mBlended0To1To1": 2.75, "price1mBlended100To1To1": 0.5931372549019609, "price1mBlended0To100To1": 1.1326732673267328, "timescaleData": {"medianOutputSpeed": 193.392703293955, "medianTimeToFirstChunk": 5.45976496149999}, "outputSpeedVariance": {"p05": 118.884072084623, "q25": 169.192168304895, "median": 193.392703293955, "q75": 226.541706968232, "p95": 266.889977775912}, "timeToFirstChunkVariance": {"p05": 2.60344763435, "q25": 4.071807508, "median": 5.45976496149999, "q75": 7.31240008749996, "p95": 9.87845070760008}, "performanceByPromptType": {"long": {"medianOutputSpeed": 193.392703293955, "medianTimeToFirstChunk": 5.45976496149999, "medianTimeToFirstAnswerToken": 5.45976496149999, "medianEndToEndResponseTime": 8.045177913921492}}, "endToEndResponseTime": {"input": 5.45976496149999, "reasoning": 0, "answer": 2.5854129524215033, "total": 8.045177913921492}, "timeToFirstAnswerToken": {"input": 5.45976496149999, "reasoning": 0, "total": 5.45976496149999}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2dbb6dc7-8c40-4b6d-af9c-cf805f83b79a", "slug": "grok-4-fast", "name": "Grok 4 Fast (Non-reasoning)", "shortName": "Grok 4 Fast (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-19", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "grok-4-fast", "name": "Grok 4 Fast"}, "deprecated": true, "deprecatedTo": "grok-4-1-fast", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.0641868989941, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.4333333333333, "omniscienceBreakdown": {"accuracy": 0.177, "hallucinationRate": 0.8764682057513163}, "gdpval": null, "itBenchSre": null, "tau2": 0.637426900584795, "tauBanking": null, "terminalbenchHard": 0.121212121212121, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.24, "ifbench": 0.37687074829932, "hle": 0.0454124189063948, "gpqa": 0.606060606060606, "critpt": 0, "apexAgents": null, "mmmuPro": 0.480924855491329, "livecodebench": 0.401058201058201, "aime25": 0.413333333333333, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.275, "price1mBlended7To2To1": 0.23000000000000004, "price1mBlended0To1To1": 0.35, "price1mBlended100To1To1": 0.20294117647058824, "price1mBlended0To100To1": 0.20297029702970298, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2e40e695-3cec-43da-83f9-615af30b8e91", "slug": "claude-sonnet-4-6", "name": "Claude Sonnet 4.6 (Non-reasoning, High Effort)", "shortName": "Claude Sonnet 4.6 (Non-reasoning, high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-17", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "claude-sonnet-4-6", "name": "Claude Sonnet 4.6"}, "deprecated": true, "deprecatedTo": "claude-sonnet-5-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 24.6869297210126, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -3.55, "omniscienceBreakdown": {"accuracy": 0.3855, "hallucinationRate": 0.6851098454027664}, "mlcrOverall": 0.2, "harveyLab": 0.844405847445361, "gdpval": null, "itBenchSre": null, "tau2": 0.795321637426901, "tauBanking": null, "terminalbenchHard": 0.462121212121212, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.683333333333333, "ifbench": 0.41156462585034, "hle": 0.133456904541242, "gpqa": 0.798989898989899, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": 0.705780346820809, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 3.75, "pricePer1k1mpImages": 4, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 2.31, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 0.47058823529411764, "price1mBlended0To100To1": 3.118811881188119, "timescaleData": {"medianOutputSpeed": 43.4851283206752, "medianTimeToFirstChunk": 1.33738948600004}, "outputSpeedVariance": {"p05": 35.29270007826, "q25": 39.3735391744725, "median": 43.4851283206752, "q75": 49.6590122572857, "p95": 75.1514829028992}, "timeToFirstChunkVariance": {"p05": 1.01612674550002, "q25": 1.10883331224994, "median": 1.33738948600004, "q75": 1.98583070350006, "p95": 4.20451797184997}, "performanceByPromptType": {"long": {"medianOutputSpeed": 43.4851283206752, "medianTimeToFirstChunk": 1.33738948600004, "medianTimeToFirstAnswerToken": 1.33738948600004, "medianEndToEndResponseTime": 12.835573332045465}}, "endToEndResponseTime": {"input": 1.33738948600004, "reasoning": 0, "answer": 11.498183846045425, "total": 12.835573332045465}, "timeToFirstAnswerToken": {"input": 1.33738948600004, "reasoning": 0, "total": 1.33738948600004}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2e46d2fd-eb2b-42b9-9fe4-be50630fe870", "slug": "ling-2-6-1t", "name": "Ling-2.6-1T", "shortName": "Ling-2.6-1T", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-23", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "ling-2-6-1t", "name": "Ling-2.6-1T"}, "deprecated": true, "deprecatedTo": "ling-3-0-flash", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1026, "inferenceParametersActiveBillions": 63, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ling-2.6-1T", "microevalsEnabled": true, "intelligenceIndex": 17.0002388154878, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -50.6, "omniscienceBreakdown": {"accuracy": 0.219, "hallucinationRate": 0.9282970550576184}, "gdpval": null, "itBenchSre": null, "tau2": 0.89766081871345, "tauBanking": null, "terminalbenchHard": 0.310606060606061, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.416666666666667, "ifbench": 0.568707482993197, "hle": 0.0871177015755329, "gpqa": 0.751515151515151, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.52, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.32156862745098036, "price1mBlended0To100To1": 0.3217821782178218, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2e6400f5-85ca-4ebc-ba8f-c2811a631138", "slug": "gemma-3-12b", "name": "Gemma 3 12B Instruct", "shortName": "Gemma 3 12B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-12", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-3-12b-instruct", "name": "Gemma 3 12B Instruct"}, "deprecated": true, "deprecatedTo": "gemma-4-26b-a4b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 12.2, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Gemma license", "licenseUrl": "https://ai.google.dev/gemma/terms", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-3-12b-it", "microevalsEnabled": false, "intelligenceIndex": 3.7508042118297, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 3.767409836065574, "strategyAndOps": 2.85348076896151, "legal": 3.8473414239482198, "engineering": 4.7615, "economics": 5.320166666666665}, "omniscience": -77.0666666666667, "omniscienceBreakdown": {"accuracy": 0.103, "hallucinationRate": 0.9739873652917131}, "gdpPdfAllPass": 0.01, "gdpval": -169.68, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.108187134502924, "tauBanking": 0.00824742268041237, "terminalbenchHard": 0.00757575757575758, "terminalBench21": 0, "terminalBench40": 0, "scicode": 0.164351851851852, "lcr": 0.0833333333333333, "ifbench": 0.36734693877551, "hle": 0.0421, "gpqa": 0.349494949494949, "critpt": 0, "apexAgents": null, "mmmuPro": 0.37514450867052, "livecodebench": 0.136507936507936, "aime25": 0.183333333333333, "analystAgent": null, "automationBenchPartialScore": 0.0019111706206154657, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "intelligenceIndexCost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "intelligenceIndexCostPerTask": {"cost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0}, {"slug": "gdpval-aa", "weightedCostPerTask": 0}, {"slug": "automationbench-aa", "weightedCostPerTask": 0}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0}, {"slug": "scicode", "weightedCostPerTask": 0}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0}, {"slug": "gdp-pdf", "weightedCostPerTask": 0}, {"slug": "critpt", "weightedCostPerTask": 0}, {"slug": "omniscience", "weightedCostPerTask": 0}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2624564516, "output": 26063136, "answer": 26063136, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 18737.031199134126, "output": 18737.031199134126}, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseTotalCost": 0, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 3, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2e8694f9-7782-47a6-a6ba-fdce89d939c8", "slug": "nvidia-nemotron-nano-9b-v2", "name": "NVIDIA Nemotron Nano 9B V2 (Non-reasoning)", "shortName": "NVIDIA Nemotron Nano 9B V2 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-18", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "nvidia-nemotron-nano-9b-v2", "name": "NVIDIA Nemotron Nano 9B V2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 9, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "NVIDIA Open Model License Agreement", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2", "microevalsEnabled": false, "intelligenceIndex": 6.84412514839364, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -57.25, "omniscienceBreakdown": {"accuracy": 0.09816666666666667, "hallucinationRate": 0.7436703012382184}, "gdpval": null, "itBenchSre": null, "tau2": 0.233918128654971, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.24, "ifbench": 0.271428571428571, "hle": 0.0458758109360519, "gpqa": 0.556565656565657, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.700529100529101, "aime25": 0.623333333333333, "analystAgent": null, "price1mInputTokens": 0.05, "price1mOutputTokens": 0.195, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.08625000000000001, "price1mBlended7To2To1": 0.0645, "price1mBlended0To1To1": 0.1225, "price1mBlended100To1To1": 0.05142156862745098, "price1mBlended0To100To1": 0.05143564356435644, "openness": {"opennessIndex": 72.22222222222223, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {"medianOutputSpeed": 132.91691393713, "medianTimeToFirstChunk": 2.1272080795}, "outputSpeedVariance": {"p05": 62.9217312295392, "q25": 99.5332298443972, "median": 132.91691393713, "q75": 165.013606874063, "p95": 171.909416639065}, "timeToFirstChunkVariance": {"p05": 1.01713672629989, "q25": 1.09960409074997, "median": 2.1272080795, "q75": 6.32688780975, "p95": 19.4897104974}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 148.916538810538, "medianTimeToFirstChunk": 1.24904389850004, "medianTimeToFirstAnswerToken": 1.24904389850004, "medianEndToEndResponseTime": 4.60662932180977}, "long": {"medianOutputSpeed": 132.91691393713, "medianTimeToFirstChunk": 2.1272080795, "medianTimeToFirstAnswerToken": 2.1272080795, "medianEndToEndResponseTime": 5.888956567254546}, "hundredK": {"medianOutputSpeed": 146.573495886048, "medianTimeToFirstChunk": 5.68945046299996, "medianTimeToFirstAnswerToken": 5.68945046299996, "medianEndToEndResponseTime": 9.100708391846247}, "mediumParallel": {"medianOutputSpeed": 126.225701481438, "medianTimeToFirstChunk": 3.29450643049995, "medianTimeToFirstAnswerToken": 3.29450643049995, "medianEndToEndResponseTime": 7.255664848570037}}, "endToEndResponseTime": {"input": 2.1272080795, "reasoning": 0, "answer": 3.7617484877545464, "total": 5.888956567254546}, "timeToFirstAnswerToken": {"input": 2.1272080795, "reasoning": 0, "total": 2.1272080795}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2e9ff877-fd2c-4ce7-b631-7ca1bdb6d13e", "slug": "command-a-plus", "name": "Command A+", "shortName": "Command A+", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "command-a-plus", "name": "Command A+"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 218, "inferenceParametersActiveBillions": 25, "sizeClass": "large", "contextWindowTokens": 192000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/CohereLabs/command-a-plus-05-2026-bf16", "microevalsEnabled": false, "intelligenceIndex": 13.9235002685349, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 11.749883811186079, "strategyAndOps": 5.532183372930056, "legal": 16.240841329697, "healthcareAndMedical": 12.673297523268266, "engineering": 19.500939067776432, "economics": 24.745763361136845}, "omniscience": -4.01666666666667, "omniscienceBreakdown": {"accuracy": 0.08883333333333333, "hallucinationRate": 0.1415767331260289}, "mlcrOverall": 0.00555555555555556, "gdpPdfAllPass": 0.01, "gdpval": 658.08, "gdpvalNormalized": 0.07904000000000003, "itBenchSre": null, "tau2": 0.807017543859649, "tauBanking": 0.0597938144329897, "terminalbenchHard": 0.25, "terminalBench21": 0.228464419475655, "terminalBench40": 0.00505050505050505, "scicode": 0.385416666666667, "lcr": 0.526666666666667, "ifbench": 0.739455782312925, "hle": 0.119555143651529, "gpqa": 0.760606060606061, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.632369942196532, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.018104537047977383, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "intelligenceIndexTimePerTask": 87.91447908153141, "intelligenceIndexCost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "intelligenceIndexCostPerTask": {"cost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0}, {"slug": "gdpval-aa", "weightedCostPerTask": 0}, {"slug": "automationbench-aa", "weightedCostPerTask": 0}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0}, {"slug": "scicode", "weightedCostPerTask": 0}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0}, {"slug": "gdp-pdf", "weightedCostPerTask": 0}, {"slug": "critpt", "weightedCostPerTask": 0}, {"slug": "omniscience", "weightedCostPerTask": 0}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0}]}, "canonicalIntelligenceIndexTokenCount": {"input": 868082457, "output": 66974426, "answer": 11560104, "reasoning": 55414322}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 13829.839592646882, "answer": 8481.701336345193, "output": 22311.540928992075}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 366.16, "lower95ci": 356.59, "upper95ci": 374.72}, "rubricPassRate": 0.06917599186164802, "analyticalQuality": {"elo": 80.49, "lower95ci": 62.18, "upper95ci": 97.74}, "presentation": {"elo": 395.36, "lower95ci": 374.37, "upper95ci": 412.17}}, "briefcaseTotalCost": 0, "timescaleData": {"medianOutputSpeed": 246.960155521429, "medianTimeToFirstChunk": 0.408045752000021}, "outputSpeedVariance": {"p05": 175.728412250214, "q25": 223.794082541193, "median": 246.960155521429, "q75": 268.830304013244, "p95": 298.294529707065}, "timeToFirstChunkVariance": {"p05": 0.338098061699995, "q25": 0.375859657000206, "median": 0.408045752000021, "q75": 0.429004757999977, "p95": 0.817067051250003}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 256.189004511931, "medianTimeToFirstChunk": 0.1684705495, "medianTimeToFirstAnswerToken": 7.975206844877806, "medianEndToEndResponseTime": 9.926890918722258}, "long": {"medianOutputSpeed": 246.960155521429, "medianTimeToFirstChunk": 0.408045752000021, "medianTimeToFirstAnswerToken": 8.506518138273108, "medianEndToEndResponseTime": 10.531136234841382}, "hundredK": {"medianOutputSpeed": 252.954028426977, "medianTimeToFirstChunk": 3.819020152, "medianTimeToFirstAnswerToken": 11.725595162634242, "medianEndToEndResponseTime": 13.702238915292803}, "mediumParallel": {"medianOutputSpeed": 200.097620014419, "medianTimeToFirstChunk": 0.196797397999944, "medianTimeToFirstAnswerToken": 10.191918778533507, "medianEndToEndResponseTime": 12.6906991236669}}, "endToEndResponseTime": {"input": 0.408045752000021, "reasoning": 8.098472386273087, "answer": 2.024618096568272, "total": 10.531136234841382}, "timeToFirstAnswerToken": {"input": 0.408045752000021, "reasoning": 8.098472386273087, "total": 8.506518138273108}, "performanceDataSource": {"type": "firstParty", "providerName": "Cohere"}, "hostModelCount": 1, "creator": {"id": "671d3708-c407-4b8f-b350-f728e4689d26", "slug": "cohere", "name": "Cohere", "logo": "/img/logos/cohere_small.svg", "color": "#D18EE2", "country": "ca", "url": "https://cohere.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2f339a97-9a0d-499a-9cb5-e0db665bfa25", "slug": "gpt-6-astra", "name": "GPT-6 Astra (max)", "shortName": "GPT-6 Astra (max)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-09-03", "knowledgeCutoffDate": "2026-04-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "gpt-6-astra", "name": "GPT-6 Astra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 52.814069395513, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 55.47977223592988, "strategyAndOps": 57.615894712319644, "legal": 58.72792095980942, "healthcareAndMedical": 51.86352154941319, "engineering": 54.863868145709716, "economics": 60.027736658171136}, "omniscience": 43.4, "omniscienceBreakdown": {"accuracy": 0.626, "hallucinationRate": 0.5133689839572193}, "mlcrOverall": 0.35, "gdpPdfAllPass": 0.31, "gdpval": 1580.2, "gdpvalNormalized": 0.5401, "itBenchSre": null, "tau2": null, "tauBanking": 0.414432989690722, "terminalbenchHard": null, "terminalBench21": 0.883895131086142, "terminalBench40": 0.590909090909091, "scicode": 0.564814814814815, "lcr": 0.806666666666667, "ifbench": null, "hle": 0.546802594995366, "gpqa": 0.960606060606061, "critpt": 0.317142857142857, "apexAgents": null, "mmmuPro": 0.86878612716763, "livecodebench": null, "aime25": null, "analystAgent": 0.5125, "automationBenchPartialScore": 0.6849174806688876, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 1, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 12.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.7, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 1.5686274509803921, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 508.14544241895965, "intelligenceIndexCost": {"total": 5324.104027952404, "input": 2323.7177779524045, "nonCacheInput": 279.07919, "cacheRead": 1066.1488814823995, "cacheWrite": 978.4897064700049, "output": 3000.38625, "reasoning": 2222.3894, "answer": 777.99685}, "intelligenceIndexCostPerTask": {"cost": {"total": 3.2575003134834164, "input": 1.897225067659909, "nonCacheInput": 0.2150003946397127, "cacheRead": 0.9812903754697416, "cacheWrite": 0.7009342975504547, "output": 1.3602752458235075, "reasoning": 0.8345619022352239, "answer": 0.5257133435882834}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 1.4253125872586803}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.45294844005565466}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.07977961555688814}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.8498119471851334}, {"slug": "scicode", "weightedCostPerTask": 0.023225916666666666}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0378076797961075}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.20758206999999998}, {"slug": "critpt", "weightedCostPerTask": 0.11661618571428572}, {"slug": "omniscience", "weightedCostPerTask": 0.014550586249999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.04986528500000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1172335977, "output": 60007725, "answer": 15559937, "reasoning": 44447788}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 16691.238044704474, "answer": 10514.266871765667, "output": 27205.50491647014}, "briefcaseBreakdown": {"overall": {"elo": 1562.01, "lower95ci": 1553.49, "upper95ci": 1571.75}, "rubricPassRate": 0.5202020202020202, "analyticalQuality": {"elo": 1753.18, "lower95ci": 1736.58, "upper95ci": 1772.26}, "presentation": {"elo": 1536.38, "lower95ci": 1520.16, "upper95ci": 1553.41}}, "briefcaseTotalCost": 864.6896362702661, "timescaleData": {"medianOutputSpeed": 52.9841513460148, "medianTimeToFirstChunk": 317.3219131575}, "outputSpeedVariance": {"p05": 43.7639769133705, "q25": 49.9210621367352, "median": 52.9841513460148, "q75": 65.3430413487106, "p95": 73.5285066818873}, "timeToFirstChunkVariance": {"p05": 188.32278668575, "q25": 241.5469879935, "median": 317.3219131575, "q75": 378.94427774175, "p95": 424.1984038925}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 56.7675978497405, "medianTimeToFirstChunk": 218.4672671925, "medianTimeToFirstAnswerToken": 218.4672671925, "medianEndToEndResponseTime": 227.2751086185801}, "long": {"medianOutputSpeed": 52.9841513460148, "medianTimeToFirstChunk": 317.3219131575, "medianTimeToFirstAnswerToken": 317.3219131575, "medianEndToEndResponseTime": 326.7586973146102}, "hundredK": {"medianOutputSpeed": 59.6802082988112, "medianTimeToFirstChunk": 160.6609634595, "medianTimeToFirstAnswerToken": 160.6609634595, "medianEndToEndResponseTime": 169.03895030392528}, "mediumParallel": {"medianOutputSpeed": 56.9622077116645, "medianTimeToFirstChunk": 295.30422946, "medianTimeToFirstAnswerToken": 295.30422946, "medianEndToEndResponseTime": 304.0819791309913}}, "endToEndResponseTime": {"input": 317.3219131575, "reasoning": 0, "answer": 9.436784157110171, "total": 326.7586973146102}, "timeToFirstAnswerToken": {"input": 317.3219131575, "reasoning": 0, "total": 317.3219131575}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 6, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2f60d80d-c3d3-4a43-bded-0557898c4618", "slug": "exaone-4-0-32b", "name": "EXAONE 4.0 32B (Non-reasoning)", "shortName": "EXAONE 4.0 32B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-15", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "exaone-4-0-32b", "name": "EXAONE 4.0 32B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 32, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131000, "licenseName": "EXAONE AI Model License Agreement 1.2 - NC", "licenseUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B", "microevalsEnabled": false, "intelligenceIndex": 6.32621718534092, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -62.7666666666667, "omniscienceBreakdown": {"accuracy": 0.10616666666666667, "hallucinationRate": 0.8209957113555846}, "gdpval": null, "itBenchSre": null, "tau2": 0.0409356725146199, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.33469387755102, "hle": 0.0500463392029657, "gpqa": 0.628282828282828, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.471957671957672, "aime25": 0.393333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 3, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "45157c16-fcbb-4110-b20f-7bca754b6554", "slug": "lg", "name": "LG AI Research", "logo": "/img/logos/lg_small.png", "color": "#df3b8a", "country": "kr", "url": "https://www.lgresearch.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2fa8e143-77a8-4d05-bfa8-d3b54634c00f", "slug": "claude-opus-4-7-non-reasoning", "name": "Claude Opus 4.7 (Non-reasoning, High Effort)", "shortName": "Claude Opus 4.7 (Non-reasoning, high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-16", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "claude-opus-4-7", "name": "Claude Opus 4.7"}, "deprecated": true, "deprecatedTo": "claude-opus-5-low", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 30.9316777597043, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 14.8333333333333, "omniscienceBreakdown": {"accuracy": 0.44733333333333336, "hallucinationRate": 0.5410132689987938}, "mlcrOverall": 0.288888888888889, "gdpval": null, "itBenchSre": null, "tau2": 0.739766081871345, "tauBanking": null, "terminalbenchHard": 0.545454545454545, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.756666666666667, "ifbench": 0.436054421768707, "hle": 0.333178869323448, "gpqa": 0.884848484848485, "critpt": 0.0514285714285714, "apexAgents": null, "mmmuPro": 0.763583815028902, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.7, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "briefcaseBreakdown": {"overall": {"elo": 1071.03, "lower95ci": 1065.37, "upper95ci": 1077.44}, "rubricPassRate": 0.27635619242579323, "analyticalQuality": {"elo": 1041.6, "lower95ci": 1031.21, "upper95ci": 1052.86}, "presentation": {"elo": 1164.45, "lower95ci": 1153.12, "upper95ci": 1175.45}}, "briefcaseTotalCost": 380.3414366170135, "timescaleData": {"medianOutputSpeed": 46.0067180913184, "medianTimeToFirstChunk": 1.17335523949998}, "outputSpeedVariance": {"p05": 35.3797724764606, "q25": 39.656639777799, "median": 46.0067180913184, "q75": 58.0573172816542, "p95": 69.6195197266025}, "timeToFirstChunkVariance": {"p05": 0.686722917299903, "q25": 0.904346225000026, "median": 1.17335523949998, "q75": 2.33616692650008, "p95": 3.39716156745}, "performanceByPromptType": {"long": {"medianOutputSpeed": 46.0067180913184, "medianTimeToFirstChunk": 1.17335523949998, "medianTimeToFirstAnswerToken": 1.17335523949998, "medianEndToEndResponseTime": 12.0413332380078}}, "endToEndResponseTime": {"input": 1.17335523949998, "reasoning": 0, "answer": 10.86797799850782, "total": 12.0413332380078}, "timeToFirstAnswerToken": {"input": 1.17335523949998, "reasoning": 0, "total": 1.17335523949998}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 2, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "2ffa7571-fa78-453a-b589-9aa3fac702d2", "slug": "g9v3-3b", "name": "G9v3-3B", "shortName": "G9v3-3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-23", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "g9v3-3b", "name": "G9v3-3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ai9stars/G9v3-3B", "microevalsEnabled": false, "intelligenceIndex": 10.841600440564, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -4.36666666666667, "omniscienceBreakdown": {"accuracy": 0.06533333333333333, "hallucinationRate": 0.1166191155492154}, "gdpval": 807.38, "gdpvalNormalized": 0.15369, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": 0.0599250936329588, "terminalBench40": null, "scicode": null, "lcr": 0.413333333333333, "ifbench": null, "hle": 0.0449490268767377, "gpqa": 0.438383838383838, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 6, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "9f712f4a-7885-4632-974d-30b4d93c3f7c", "slug": "ai9star", "name": "AI9Stars", "logo": "/img/logos/ai9stars.svg", "color": "#795BCF", "country": "cn", "url": "https://github.com/AI9Stars"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3068def4-7270-4c06-a320-6f6a5623d564", "slug": "glm-4-5v-reasoning", "name": "GLM-4.5V (Reasoning)", "shortName": "GLM-4.5V", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "glm-4-5v", "name": "GLM-4.5V"}, "deprecated": true, "deprecatedTo": "glm-4-6v-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 108, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 64000, "licenseName": "MIT", "licenseUrl": "https://huggingface.co/zai-org/GLM-4.5", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-4.5V", "microevalsEnabled": false, "intelligenceIndex": 7.55612311182388, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -46.2833333333333, "omniscienceBreakdown": {"accuracy": 0.20833333333333334, "hallucinationRate": 0.8477894736842105}, "gdpval": null, "itBenchSre": null, "tau2": 0.225146198830409, "tauBanking": null, "terminalbenchHard": 0.053030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.342176870748299, "hle": 0.0630213160333642, "gpqa": 0.683838383838384, "critpt": 0, "apexAgents": null, "mmmuPro": 0.504624277456647, "livecodebench": 0.604232804232804, "aime25": 0.73, "analystAgent": null, "price1mInputTokens": 0.6, "price1mOutputTokens": 1.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.8999999999999999, "price1mBlended7To2To1": 0.72, "price1mBlended0To1To1": 1.2, "price1mBlended100To1To1": 0.6117647058823529, "price1mBlended0To100To1": 0.6118811881188119, "openness": {"opennessIndex": 52.77777777777778, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 38.7287675418379, "medianTimeToFirstChunk": 2.77811439050003}, "outputSpeedVariance": {"p05": 25.8055902594084, "q25": 33.546228189478, "median": 38.7287675418379, "q75": 48.5482999352149, "p95": 105.473085695603}, "timeToFirstChunkVariance": {"p05": 1.83519899464991, "q25": 2.65469789149988, "median": 2.77811439050003, "q75": 3.98960535974999, "p95": 6.65713415885001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 38.7287675418379, "medianTimeToFirstChunk": 2.77811439050003, "medianTimeToFirstAnswerToken": 54.41931360602995, "medianEndToEndResponseTime": 67.32961340991244}}, "endToEndResponseTime": {"input": 2.77811439050003, "reasoning": 51.64119921552992, "answer": 12.91029980388248, "total": 67.32961340991244}, "timeToFirstAnswerToken": {"input": 2.77811439050003, "reasoning": 51.64119921552992, "total": 54.41931360602995}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "30c9ba61-d0a1-4794-938e-35865f379d15", "slug": "qwen3-5-4b-non-reasoning", "name": "Qwen3.5 4B (Non-reasoning)", "shortName": "Qwen3.5 4B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-5-4b", "name": "Qwen3.5 4B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 4.66, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-4B", "microevalsEnabled": false, "intelligenceIndex": 10.812307683746, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -74.7333333333333, "omniscienceBreakdown": {"accuracy": 0.11216666666666666, "hallucinationRate": 0.9680871034353294}, "gdpval": null, "itBenchSre": null, "tau2": 0.87719298245614, "tauBanking": 0.0432989690721649, "terminalbenchHard": 0.113636363636364, "terminalBench21": 0.213483146067416, "terminalBench40": null, "scicode": null, "lcr": 0.346666666666667, "ifbench": 0.33265306122449, "hle": 0.0797034291010195, "gpqa": 0.712121212121212, "critpt": 0, "apexAgents": null, "mmmuPro": 0.620809248554913, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.03, "price1mOutputTokens": 0.15, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.06, "price1mBlended7To2To1": 0.042, "price1mBlended0To1To1": 0.09, "price1mBlended100To1To1": 0.03117647058823529, "price1mBlended0To100To1": 0.031188118811881188, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 12.9586947724176, "medianTimeToFirstChunk": 0.775328611000077}, "outputSpeedVariance": {"p05": 6.78991586190067, "q25": 10.6353801156692, "median": 12.9586947724176, "q75": 20.0323658539747, "p95": 45.6571332166015}, "timeToFirstChunkVariance": {"p05": 0.550196230699828, "q25": 0.683977904000016, "median": 0.775328611000077, "q75": 1.15348092849996, "p95": 3.10361610299998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 14.6544721097337, "medianTimeToFirstChunk": 0.579837091999991, "medianTimeToFirstAnswerToken": 0.579837091999991, "medianEndToEndResponseTime": 34.69911455596904}, "long": {"medianOutputSpeed": 12.9586947724176, "medianTimeToFirstChunk": 0.775328611000077, "medianTimeToFirstAnswerToken": 0.775328611000077, "medianEndToEndResponseTime": 39.35946140994855}, "hundredK": {"medianOutputSpeed": 47.1277697560615, "medianTimeToFirstChunk": 4.69772905400004, "medianTimeToFirstAnswerToken": 4.69772905400004, "medianEndToEndResponseTime": 15.307185062380128}, "mediumParallel": {"medianOutputSpeed": 11.791035777036, "medianTimeToFirstChunk": 0.643379979000059, "medianTimeToFirstAnswerToken": 0.643379979000059, "medianEndToEndResponseTime": 43.048475634276635}}, "endToEndResponseTime": {"input": 0.775328611000077, "reasoning": 0, "answer": 38.584132798948474, "total": 39.35946140994855}, "timeToFirstAnswerToken": {"input": 0.775328611000077, "reasoning": 0, "total": 0.775328611000077}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "30ef2a79-e800-4165-9f13-2a338f120db7", "slug": "qwen3-5-397b-a17b-non-reasoning", "name": "Qwen3.5 397B A17B (Non-reasoning)", "shortName": "Qwen3.5 397B A17B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-16", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-5-397b-a17b", "name": "Qwen3.5 397B A17B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 397, "inferenceParametersActiveBillions": 17, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-397B-A17B", "microevalsEnabled": true, "intelligenceIndex": 21.4366547759392, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -37.9, "omniscienceBreakdown": {"accuracy": 0.24516666666666667, "hallucinationRate": 0.8268933539412674}, "gdpval": null, "itBenchSre": null, "tau2": 0.839181286549708, "tauBanking": null, "terminalbenchHard": 0.356060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.643333333333333, "ifbench": 0.516326530612245, "hle": 0.198331788693234, "gpqa": 0.860606060606061, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": 0.526589595375723, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.6, "price1mOutputTokens": 3.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.615, "price1mBlended0To3To1": 1.35, "price1mBlended7To2To1": 0.9, "price1mBlended0To1To1": 2.1, "price1mBlended100To1To1": 0.6294117647058823, "price1mBlended0To100To1": 0.6297029702970297, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 80.0002152800965, "medianTimeToFirstChunk": 2.17274089800003}, "outputSpeedVariance": {"p05": 70.2657011962342, "q25": 74.5106671776397, "median": 80.0002152800965, "q75": 92.541102889265, "p95": 94.6345032423023}, "timeToFirstChunkVariance": {"p05": 1.89824781479994, "q25": 2.12942004099998, "median": 2.17274089800003, "q75": 2.26936348800014, "p95": 2.40519621849996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 84.1492137642532, "medianTimeToFirstChunk": 1.738675167, "medianTimeToFirstAnswerToken": 1.738675167, "medianEndToEndResponseTime": 7.680501330709224}, "long": {"medianOutputSpeed": 80.0002152800965, "medianTimeToFirstChunk": 2.17274089800003, "medianTimeToFirstAnswerToken": 2.17274089800003, "medianEndToEndResponseTime": 8.42272407928775}, "hundredK": {"medianOutputSpeed": 109.883659368368, "medianTimeToFirstChunk": 5.60209338900003, "medianTimeToFirstAnswerToken": 5.60209338900003, "medianEndToEndResponseTime": 10.152360488531428}, "mediumParallel": {"medianOutputSpeed": 81.0906227249208, "medianTimeToFirstChunk": 1.84257850800003, "medianTimeToFirstAnswerToken": 1.84257850800003, "medianEndToEndResponseTime": 8.008519565033493}}, "endToEndResponseTime": {"input": 2.17274089800003, "reasoning": 0, "answer": 6.24998318128772, "total": 8.42272407928775}, "timeToFirstAnswerToken": {"input": 2.17274089800003, "reasoning": 0, "total": 2.17274089800003}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 6, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "31da3a71-0773-47d9-8560-9f19f069926b", "slug": "k2-4b-ph1", "name": "K2 Horizon 3.7B", "shortName": "K2 Horizon 3.7B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-03", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "k2-horizon-3-7b", "name": "K2 Horizon 3.7B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3.7, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 524288, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/IFM/K2-Horizon-3.7B", "microevalsEnabled": false, "intelligenceIndex": 16.1641701330976, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 17.254313847397984, "strategyAndOps": 15.496073945184076, "legal": 18.246407595513872, "engineering": 20.711763253012055, "economics": 26.52850175702811}, "omniscience": -28.6166666666667, "omniscienceBreakdown": {"accuracy": 0.10766666666666666, "hallucinationRate": 0.441352259992529}, "gdpPdfAllPass": 0.032, "gdpval": 962.39, "gdpvalNormalized": 0.23119499999999998, "itBenchSre": null, "tau2": null, "tauBanking": 0.195876288659794, "terminalbenchHard": null, "terminalBench21": 0.280898876404494, "terminalBench40": 0, "scicode": 0.219907407407407, "lcr": 0.623333333333333, "ifbench": null, "hle": 0.13855421686747, "gpqa": 0.691919191919192, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.14695137139561937, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "canonicalIntelligenceIndexTokenCount": {"input": 10766186482, "output": 176817175, "answer": 33577280, "reasoning": 143239895}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 48430.98982369936, "answer": 23650.324095897675, "output": 72081.31391959704}, "briefcaseBreakdown": {"overall": {"elo": 792.8, "lower95ci": 781.9, "upper95ci": 802.41}, "rubricPassRate": 0.2010204081632653, "analyticalQuality": {"elo": 739.66, "lower95ci": 720.35, "upper95ci": 757.66}, "presentation": {"elo": 765.33, "lower95ci": 745.52, "upper95ci": 784.58}}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "8b8b84fb-4b24-45be-b9e2-74ed50d00ff7", "slug": "mbzuai", "name": "MBZUAI Institute of Foundation Models", "logo": "/img/logos/mbzuai_small.svg", "color": "#1521a9", "country": "ae", "url": "https://mbzuai.ac.ae/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3373245b-e6dc-4b66-a7b0-3f06f9b7bd46", "slug": "qwen3-235b-a22b-instruct-2507", "name": "Qwen3 235B A22B 2507 Instruct", "shortName": "Qwen3 235B 2507 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-21", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-235b-a22b-instruct-2507", "name": "Qwen3 235B A22B 2507"}, "deprecated": true, "deprecatedTo": "qwen3-5-397b-a17b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 235, "inferenceParametersActiveBillions": 22, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507", "microevalsEnabled": false, "intelligenceIndex": 11.9970837221274, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -43.9833333333333, "omniscienceBreakdown": {"accuracy": 0.18733333333333332, "hallucinationRate": 0.7717391304347826}, "gdpval": null, "itBenchSre": null, "tau2": 0.333333333333333, "tauBanking": null, "terminalbenchHard": 0.151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.339, "ifbench": 0.460544217687075, "hle": 0.111214087117702, "gpqa": 0.752525252525253, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.523809523809524, "aime25": 0.716666666666667, "analystAgent": null, "price1mInputTokens": 0.23, "price1mOutputTokens": 0.92, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.4025, "price1mBlended7To2To1": 0.29900000000000004, "price1mBlended0To1To1": 0.5750000000000001, "price1mBlended100To1To1": 0.23676470588235296, "price1mBlended0To100To1": 0.23683168316831685, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 58.0435314145891, "medianTimeToFirstChunk": 2.37960341200005}, "outputSpeedVariance": {"p05": 48.208246789033, "q25": 55.9082731478506, "median": 58.0435314145891, "q75": 69.5437660864922, "p95": 73.6180280283274}, "timeToFirstChunkVariance": {"p05": 1.91572788560003, "q25": 2.09213337824994, "median": 2.37960341200005, "q75": 2.73211858749977, "p95": 3.31039816834991}, "performanceByPromptType": {"long": {"medianOutputSpeed": 58.0435314145891, "medianTimeToFirstChunk": 2.37960341200005, "medianTimeToFirstAnswerToken": 2.37960341200005, "medianEndToEndResponseTime": 10.99382773320195}}, "endToEndResponseTime": {"input": 2.37960341200005, "reasoning": 0, "answer": 8.6142243212019, "total": 10.99382773320195}, "timeToFirstAnswerToken": {"input": 2.37960341200005, "reasoning": 0, "total": 2.37960341200005}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 10, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "338216fb-62c2-48f1-898a-9166d12fb35e", "slug": "olmo-3-7b-think", "name": "Olmo 3 7B Think", "shortName": "Olmo 3 7B Think", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-20", "knowledgeCutoffDate": "2024-12-01", "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "olmo-3-7b-think", "name": "Olmo 3 7B Think"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 65536, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/allenai/Olmo-3-7B-Think", "microevalsEnabled": false, "intelligenceIndex": 5.61691854830355, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -71.8, "omniscienceBreakdown": {"accuracy": 0.11083333333333334, "hallucinationRate": 0.9321462043111528}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.414965986394558, "hle": 0.0597775718257646, "gpqa": 0.516161616161616, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.616931216931217, "aime25": 0.706666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "ab6c5270-d7b9-4c09-92fe-62662618c631", "slug": "ai2", "name": "Allen Institute for AI", "logo": "/img/logos/ai2_small.svg", "color": "#F0529C", "country": "us", "url": "https://allenai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "339a92c1-8a42-417f-8d1f-cdbc605acd9e", "slug": "hyperclova-x-seed-think-32b", "name": "HyperCLOVA X SEED Think (32B)", "shortName": "HyperCLOVA X SEED Think (32B)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-26", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "hyperclova-x-seed-think-32b", "name": "HyperCLOVA X SEED Think (32B)"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 32, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "HyperCLOVA X SEED 32B Think Model License Agreement", "licenseUrl": "https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-32B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-32B", "microevalsEnabled": false, "intelligenceIndex": 11.3648115832519, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -53.2833333333333, "omniscienceBreakdown": {"accuracy": 0.154, "hallucinationRate": 0.8118597320724981}, "gdpval": null, "itBenchSre": null, "tau2": 0.874269005847953, "tauBanking": null, "terminalbenchHard": 0.121212121212121, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.136666666666667, "ifbench": 0.37891156462585, "hle": 0.0546802594995366, "gpqa": 0.615151515151515, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.628571428571429, "aime25": 0.59, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 30.555555555555557, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "6da63157-6fed-41df-8761-62c519ebd6ab", "slug": "naver", "name": "Naver", "logo": "/img/logos/naver_small.webp", "color": "#03c75b", "country": "kr", "url": "https://www.naver.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "340fb211-4fad-41d3-87d5-ed0d0cd34088", "slug": "hypernova-60b", "name": "HyperNova 60B 2605 (high, based on gpt-oss-120b)", "shortName": "HyperNova 60B 2605 (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-26", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "hypernova-60b", "name": "HyperNova 60B 2605"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 58.7, "inferenceParametersActiveBillions": 4.8, "sizeClass": "medium", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/MultiverseComputingCAI/Hypernova-60B-2605", "microevalsEnabled": false, "intelligenceIndex": 11.7380211033452, "intelligenceIndexIsEstimated": true, "capabilities": {"economics": 17.257343988276958}, "omniscience": -54.5833333333333, "omniscienceBreakdown": {"accuracy": 0.15216666666666667, "hallucinationRate": 0.8232750147434638}, "gdpval": 603.87, "gdpvalNormalized": 0.051935, "itBenchSre": null, "tau2": 0.631578947368421, "tauBanking": 0.0556701030927835, "terminalbenchHard": 0.234848484848485, "terminalBench21": 0.183520599250936, "terminalBench40": null, "scicode": null, "lcr": 0.363333333333333, "ifbench": 0.664625850340136, "hle": 0.166357738646895, "gpqa": 0.733333333333333, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 249.39, "lower95ci": 239, "upper95ci": 258.91}, "rubricPassRate": 0.0707070707070707, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 152.94, "lower95ci": 133.29, "upper95ci": 172.22}}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "7d59f244-cf07-4d56-8f28-e1f1379f31c8", "slug": "multiversecomputing", "name": "Multiverse Computing", "logo": "/img/logos/multiversecomputing_small.svg", "color": "#f11338", "country": "es", "url": "https://multiversecomputing.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3435db18-9227-45a5-8e79-9546b14b5aaa", "slug": "sonar-pro", "name": "Sonar Pro", "shortName": "Sonar Pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-21", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "sonar-pro", "name": "Sonar Pro"}, "deprecated": true, "deprecatedTo": "sonar-reasoning-pro", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.60691968274841, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0655, "gpqa": 0.577777777777778, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.275132275132275, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "941fc0f0-1d4e-405a-95b2-2d49494e0e6c", "slug": "perplexity", "name": "Perplexity", "logo": "/img/logos/perplexity.svg", "color": "#1B818E", "country": "us", "url": "https://perplexity.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "344c6718-c573-41d4-9556-10287a3fa1fc", "slug": "nova-micro", "name": "Nova Micro", "shortName": "Nova Micro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-03", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "nova-micro", "name": "Nova Micro"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 130000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.8765232381273, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -48.5166666666667, "omniscienceBreakdown": {"accuracy": 0.10033333333333333, "hallucinationRate": 0.6507965913301222}, "gdpval": null, "itBenchSre": null, "tau2": 0.140350877192982, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.13, "ifbench": 0.293877551020408, "hle": 0.046339202965709, "gpqa": 0.357575757575758, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.13968253968254, "aime25": 0.06, "analystAgent": null, "price1mInputTokens": 0.035, "price1mOutputTokens": 0.14, "cacheHitPrice": 0.00875, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.061250000000000006, "price1mBlended7To2To1": 0.027125, "price1mBlended0To1To1": 0.08750000000000001, "price1mBlended100To1To1": 0.010294117647058827, "price1mBlended0To100To1": 0.036039603960396044, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 279.300826374198, "medianTimeToFirstChunk": 0.862373769999934}, "outputSpeedVariance": {"p05": 130.683966273774, "q25": 237.835847482646, "median": 279.300826374198, "q75": 338.91473417727, "p95": 367.660880931837}, "timeToFirstChunkVariance": {"p05": 0.767875280549917, "q25": 0.827331603999838, "median": 0.862373769999934, "q75": 0.954164329249949, "p95": 1.53002723759999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 278.126919365667, "medianTimeToFirstChunk": 0.59083580650001, "medianTimeToFirstAnswerToken": 0.59083580650001, "medianEndToEndResponseTime": 2.3885762091203895}, "long": {"medianOutputSpeed": 279.300826374198, "medianTimeToFirstChunk": 0.862373769999934, "medianTimeToFirstAnswerToken": 0.862373769999934, "medianEndToEndResponseTime": 2.6525582334362023}, "hundredK": {"medianOutputSpeed": 230.175414849802, "medianTimeToFirstChunk": 5.63585216749999, "medianTimeToFirstAnswerToken": 5.63585216749999, "medianEndToEndResponseTime": 7.80810848916783}, "mediumParallel": {"medianOutputSpeed": 362.753931458165, "medianTimeToFirstChunk": 1.27302644449998, "medianTimeToFirstAnswerToken": 1.27302644449998, "medianEndToEndResponseTime": 2.6513712579942013}}, "endToEndResponseTime": {"input": 0.862373769999934, "reasoning": 0, "answer": 1.7901844634362685, "total": 2.6525582334362023}, "timeToFirstAnswerToken": {"input": 0.862373769999934, "reasoning": 0, "total": 0.862373769999934}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "34ef2b5c-3df3-437e-b9c5-81346f8c14a8", "slug": "sarvam-m-reasoning", "name": "Sarvam M (Reasoning)", "shortName": "Sarvam M", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-23", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "sarvam-m", "name": "Sarvam M"}, "deprecated": true, "deprecatedTo": "sarvam-30b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 23.6, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/sarvamai/sarvam-m", "microevalsEnabled": false, "intelligenceIndex": 5.31069666559541, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -61.6, "omniscienceBreakdown": {"accuracy": 0.15233333333333332, "hallucinationRate": 0.906409752261109}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.318367346938775, "hle": 0.031047265987025, "gpqa": 0.416161616161616, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.295238095238095, "aime25": null, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "20273002-dc38-4ebc-8377-8f432aec9e7e", "slug": "sarvam", "name": "Sarvam", "logo": "/img/logos/sarvam.svg", "color": "#807D77", "country": "in", "url": "https://www.sarvam.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "352f834f-a03c-4117-8a29-c3ccd8a568ce", "slug": "qwen-turbo", "name": "Qwen2.5 Turbo", "shortName": "Qwen2.5 Turbo", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-11-18", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen-turbo", "name": "Qwen2.5 Turbo"}, "deprecated": true, "deprecatedTo": "qwen3-32b-instruct", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.43324005500213, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0409, "gpqa": 0.41010101010101, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.162962962962963, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.05, "price1mOutputTokens": 0.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.08750000000000001, "price1mBlended7To2To1": 0.06500000000000002, "price1mBlended0To1To1": 0.125, "price1mBlended100To1To1": 0.051470588235294115, "price1mBlended0To100To1": 0.05148514851485149, "timescaleData": {"medianOutputSpeed": 107.362393678764, "medianTimeToFirstChunk": 2.14743350100002}, "outputSpeedVariance": {"p05": 95.8181384959245, "q25": 105.115432683501, "median": 107.362393678764, "q75": 112.407089526595, "p95": 116.465482959855}, "timeToFirstChunkVariance": {"p05": 2.06085548169995, "q25": 2.10935957999999, "median": 2.14743350100002, "q75": 2.25058456950012, "p95": 2.67925997649997}, "performanceByPromptType": {"long": {"medianOutputSpeed": 107.362393678764, "medianTimeToFirstChunk": 2.14743350100002, "medianTimeToFirstAnswerToken": 2.14743350100002, "medianEndToEndResponseTime": 6.804557684501702}}, "endToEndResponseTime": {"input": 2.14743350100002, "reasoning": 0, "answer": 4.657124183501683, "total": 6.804557684501702}, "timeToFirstAnswerToken": {"input": 2.14743350100002, "reasoning": 0, "total": 2.14743350100002}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3538d399-1b3f-455d-9b13-1d8f9fee26c8", "slug": "exaone-4-5-33b-non-reasoning", "name": "EXAONE 4.5 33B (Non-reasoning)", "shortName": "EXAONE 4.5 33B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-09", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "exaone-4-5-33b", "name": "EXAONE 4.5 33B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 34.4, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "EXAONE AI Model License Agreement 1.2 - NC", "licenseUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B", "microevalsEnabled": false, "intelligenceIndex": null, "intelligenceIndexIsEstimated": false, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 3, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "45157c16-fcbb-4110-b20f-7bca754b6554", "slug": "lg", "name": "LG AI Research", "logo": "/img/logos/lg_small.png", "color": "#df3b8a", "country": "kr", "url": "https://www.lgresearch.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "353c92f3-2148-4c2d-9231-aa7e1322a1fd", "slug": "qwen3-8-27b-non-reasoning", "name": "Qwen3.8 27B (Non-reasoning)", "shortName": "Qwen3.8 27B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-14", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-8-27b", "name": "Qwen3.8 27B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 27, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.8-27B", "microevalsEnabled": false, "intelligenceIndex": 22.4190392584054, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -7.95, "omniscienceBreakdown": {"accuracy": 0.08583333333333333, "hallucinationRate": 0.18085688240656336}, "gdpval": 1113.3, "gdpvalNormalized": 0.30665, "itBenchSre": null, "tau2": null, "tauBanking": 0.2, "terminalbenchHard": null, "terminalBench21": 0.49063670411985, "terminalBench40": null, "scicode": 0.362268518518519, "lcr": 0.693333333333333, "ifbench": null, "hle": 0.121408711770158, "gpqa": 0.818181818181818, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.699421965317919, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.12434667722683214, "price1mInputTokens": 0.5, "price1mOutputTokens": 3, "cacheHitPrice": 0.05, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.125, "price1mBlended7To2To1": 0.43499999999999994, "price1mBlended0To1To1": 1.75, "price1mBlended100To1To1": 0.08333333333333333, "price1mBlended0To100To1": 0.5247524752475248, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 50.0267572506589, "medianTimeToFirstChunk": 3.91135598799997}, "outputSpeedVariance": {"p05": 38.2104118479578, "q25": 43.7969615343511, "median": 50.0267572506589, "q75": 60.4845537248062, "p95": 64.7111744345795}, "timeToFirstChunkVariance": {"p05": 3.67134039830006, "q25": 3.79163850499999, "median": 3.91135598799997, "q75": 4.213034204, "p95": 4.8954640243}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 46.5939549034801, "medianTimeToFirstChunk": 1.24334469799999, "medianTimeToFirstAnswerToken": 1.24334469799999, "medianEndToEndResponseTime": 11.974350491256983}, "long": {"medianOutputSpeed": 50.0267572506589, "medianTimeToFirstChunk": 3.91135598799997, "medianTimeToFirstAnswerToken": 3.91135598799997, "medianEndToEndResponseTime": 13.90600740013831}, "hundredK": {"medianOutputSpeed": 93.3737554004116, "medianTimeToFirstChunk": 17.4299960070001, "medianTimeToFirstAnswerToken": 17.4299960070001, "medianEndToEndResponseTime": 22.784819724391205}, "mediumParallel": {"medianOutputSpeed": 50.2900112661866, "medianTimeToFirstChunk": 1.27083127150013, "medianTimeToFirstAnswerToken": 1.27083127150013, "medianEndToEndResponseTime": 11.213163504306449}}, "endToEndResponseTime": {"input": 3.91135598799997, "reasoning": 0, "answer": 9.99465141213834, "total": 13.90600740013831}, "timeToFirstAnswerToken": {"input": 3.91135598799997, "reasoning": 0, "total": 3.91135598799997}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "35d602fc-b8b8-4698-9f4d-f2ce11ca50e4", "slug": "mistral-small-2402", "name": "Mistral Small (Feb '24)", "shortName": "Mistral Small (Feb)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-02-26", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-small-2402", "name": "Mistral Small (Feb '24)"}, "deprecated": true, "deprecatedTo": "mistral-small", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 32768, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.50039200868795, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0409, "gpqa": 0.302020202020202, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.111111111111111, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.26249999999999996, "price1mBlended7To2To1": 0.195, "price1mBlended0To1To1": 0.375, "price1mBlended100To1To1": 0.15441176470588236, "price1mBlended0To100To1": 0.15445544554455445, "timescaleData": {"medianOutputSpeed": 151.64412546312, "medianTimeToFirstChunk": 0.776026815999998}, "outputSpeedVariance": {"p05": 103.622792105811, "q25": 134.419826753693, "median": 151.64412546312, "q75": 175.084831507866, "p95": 194.5517957574}, "timeToFirstChunkVariance": {"p05": 0.661596542600012, "q25": 0.710618074499962, "median": 0.776026815999998, "q75": 0.898588791500003, "p95": 1.56266921890001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 151.64412546312, "medianTimeToFirstChunk": 0.776026815999998, "medianTimeToFirstAnswerToken": 0.776026815999998, "medianEndToEndResponseTime": 4.073220152523941}}, "endToEndResponseTime": {"input": 0.776026815999998, "reasoning": 0, "answer": 3.297193336523943, "total": 4.073220152523941}, "timeToFirstAnswerToken": {"input": 0.776026815999998, "reasoning": 0, "total": 0.776026815999998}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "369329e4-629f-425d-975a-e8980aec2965", "slug": "intellect-3", "name": "INTELLECT-3", "shortName": "INTELLECT-3", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-27", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "intellect-3", "name": "INTELLECT-3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 107, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 131100, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/PrimeIntellect/INTELLECT-3", "microevalsEnabled": true, "intelligenceIndex": 10.6061102858178, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -50.85, "omniscienceBreakdown": {"accuracy": 0.19583333333333333, "hallucinationRate": 0.8758549222797928}, "gdpval": null, "itBenchSre": null, "tau2": 0.266081871345029, "tauBanking": null, "terminalbenchHard": 0.0909090909090909, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.396666666666667, "ifbench": 0.340136054421769, "hle": 0.130676552363299, "gpqa": 0.760606060606061, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.776719576719577, "aime25": 0.88, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 72.22222222222223, "modelAvailability": 6, "transparencyMethodology": 5, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "386c82f9-9669-4467-b13e-fed5bede9002", "slug": "prime-intellect", "name": "Prime Intellect", "logo": "/img/logos/prime-intellect_small.svg", "color": "#000000", "country": "us", "url": "https://www.primeintellect.ai/blog/intellect-3"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "36f73aaf-d38a-4b56-a2b3-d04d17186910", "slug": "gpt-oss-20b", "name": "gpt-oss-20b (high)", "shortName": "gpt-oss-20b (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-05", "knowledgeCutoffDate": "2024-05-31", "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-oss-20b", "name": "gpt-oss-20b"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 21, "inferenceParametersActiveBillions": 3.6, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/openai/gpt-oss-20b", "microevalsEnabled": true, "intelligenceIndex": 9.0371671856126, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 7.434263644400488, "strategyAndOps": 4.918701602294844, "legal": 7.349435673954709, "healthcareAndMedical": 6.672374489618242, "engineering": 11.748794379716665, "economics": 11.351732719338884}, "omniscience": -63.05, "omniscienceBreakdown": {"accuracy": 0.16, "hallucinationRate": 0.9410714285714286}, "mlcrOverall": 0.00555555555555556, "gdpPdfAllPass": 0.02, "gdpval": 513.93, "gdpvalNormalized": 0.006964999999999975, "itBenchSre": null, "tau2": 0.60233918128655, "tauBanking": 0.0701030927835052, "terminalbenchHard": 0.106060606060606, "terminalBench21": 0.138576779026217, "terminalBench40": 0, "scicode": 0.388888888888889, "lcr": 0.346666666666667, "ifbench": 0.651020408163265, "hle": 0.10982391102873, "gpqa": 0.687878787878788, "critpt": 0.0142857142857143, "apexAgents": 0.00737463126843658, "mmmuPro": null, "livecodebench": 0.776719576719577, "aime25": 0.893333333333333, "analystAgent": null, "automationBenchPartialScore": 0.0019111706206154657, "price1mInputTokens": 0.060000000000000005, "price1mOutputTokens": 0.19, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.0925, "price1mBlended7To2To1": 0.073, "price1mBlended0To1To1": 0.125, "price1mBlended100To1To1": 0.06127450980392158, "price1mBlended0To100To1": 0.0612871287128713, "intelligenceIndexTimePerTask": 85.84298162661153, "intelligenceIndexCost": {"total": 29.41154909, "input": 16.150823040000002, "nonCacheInput": 0.89569734, "cacheRead": 0, "cacheWrite": 15.2551257, "output": 13.26072605, "reasoning": 12.50161563, "answer": 0.7591104200000001}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.011327291692644618, "input": 0.007886619392112458, "nonCacheInput": 0.0005088635341106404, "cacheRead": 0, "cacheWrite": 0.007377755858001817, "output": 0.0034406723005321617, "reasoning": 0.003060544059975391, "answer": 0.0003801282405567702}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.0011914822912087912}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.007170579450000001}, {"slug": "automationbench-aa", "weightedCostPerTask": 8.235388964992391e-05}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.000870270681818182}, {"slug": "scicode", "weightedCostPerTask": 0.00020078340972222222}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00030925352085264135}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00039219682}, {"slug": "critpt", "weightedCostPerTask": 0.0007354419571428572}, {"slug": "omniscience", "weightedCostPerTask": 6.179263725e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00031313703500000003}]}, "canonicalIntelligenceIndexTokenCount": {"input": 269180384, "output": 69793295, "answer": 3995318, "reasoning": 65797977}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 16108.126631449428, "answer": 2000.674950298791, "output": 18108.80158174822}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "rubricPassRate": 0.024242424242424242, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 0.72283259, "timescaleData": {"medianOutputSpeed": 205.187613509645, "medianTimeToFirstChunk": 0.739481149999847}, "outputSpeedVariance": {"p05": 70.2549457192963, "q25": 113.324820908073, "median": 205.187613509645, "q75": 390.475560333633, "p95": 950.396193980082}, "timeToFirstChunkVariance": {"p05": 0.292455246899905, "q25": 0.46659420800006, "median": 0.739481149999847, "q75": 1.28691835200005, "p95": 43.3202401618}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 219.459953791505, "medianTimeToFirstChunk": 0.412137810499928, "medianTimeToFirstAnswerToken": 9.52541777546371, "medianEndToEndResponseTime": 11.803737766704655}, "long": {"medianOutputSpeed": 205.187613509645, "medianTimeToFirstChunk": 0.739481149999847, "medianTimeToFirstAnswerToken": 10.486658212936877, "medianEndToEndResponseTime": 12.923452478671134}, "hundredK": {"medianOutputSpeed": 102.271023223334, "medianTimeToFirstChunk": 4.91797466200001, "medianTimeToFirstAnswerToken": 24.473856054058704, "medianEndToEndResponseTime": 29.362826402073377}, "mediumParallel": {"medianOutputSpeed": 182.740942316359, "medianTimeToFirstChunk": 0.426694822999934, "medianTimeToFirstAnswerToken": 11.371149714436486, "medianEndToEndResponseTime": 14.107263437295623}}, "endToEndResponseTime": {"input": 0.739481149999847, "reasoning": 9.74717706293703, "answer": 2.4367942657342576, "total": 12.923452478671134}, "timeToFirstAnswerToken": {"input": 0.739481149999847, "reasoning": 9.74717706293703, "total": 10.486658212936877}, "performanceDataSource": {"type": "median"}, "hostModelCount": 10, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "385376b1-9815-47dd-83cc-85aac34f247d", "slug": "minimax-m1-40k", "name": "MiniMax M1 40k", "shortName": "MiniMax M1 40k", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-17", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "minimax-m1-40k", "name": "MiniMax M1 40k"}, "deprecated": true, "deprecatedTo": "minimax-m2", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 456, "inferenceParametersActiveBillions": 45.9, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/MiniMaxAI/MiniMax-M1-40k", "microevalsEnabled": false, "intelligenceIndex": 9.98569091349641, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.315789473684211, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.412244897959184, "hle": 0.0783132530120482, "gpqa": 0.681818181818182, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.657142857142857, "aime25": 0.136666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "a31a9071-6144-4dbb-92dc-2e02d653ecea", "slug": "minimax", "name": "MiniMax", "logo": "/img/logos/minimax_small.svg", "color": "#EB3568", "country": "cn", "url": "https://minimaxi.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "392063ba-c3b5-47e8-ba67-a7b0b34f6824", "slug": "gpt-5-4-mini-medium", "name": "GPT-5.4 mini (medium)", "shortName": "GPT-5.4 mini (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-17", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-5-4-mini", "name": "GPT-5.4 mini"}, "deprecated": true, "deprecatedTo": "gpt-5-6-terra-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 19.7484210566215, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -20.6166666666667, "omniscienceBreakdown": {"accuracy": 0.36466666666666664, "hallucinationRate": 0.8984784889821616}, "gdpval": null, "itBenchSre": null, "tau2": 0.365497076023392, "tauBanking": null, "terminalbenchHard": 0.340909090909091, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.67, "ifbench": 0.647619047619048, "hle": 0.185820203892493, "gpqa": 0.823232323232323, "critpt": 0.0285714285714286, "apexAgents": null, "mmmuPro": 0.711560693641618, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.75, "price1mOutputTokens": 4.5, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 1.24, "price1mBlended0To3To1": 1.6875, "price1mBlended7To2To1": 0.6525000000000001, "price1mBlended0To1To1": 2.625, "price1mBlended100To1To1": 0.125, "price1mBlended0To100To1": 0.7871287128712872, "timescaleData": {"medianOutputSpeed": 189.622505338251, "medianTimeToFirstChunk": 4.45560328049998}, "outputSpeedVariance": {"p05": 147.694301202238, "q25": 168.820139248687, "median": 189.622505338251, "q75": 202.149032136672, "p95": 242.714429334563}, "timeToFirstChunkVariance": {"p05": 1.64134461910006, "q25": 2.626172287, "median": 4.45560328049998, "q75": 11.68864871125, "p95": 31.30685182885}, "performanceByPromptType": {"long": {"medianOutputSpeed": 189.622505338251, "medianTimeToFirstChunk": 4.45560328049998, "medianTimeToFirstAnswerToken": 4.45560328049998, "medianEndToEndResponseTime": 7.09242109444086}}, "endToEndResponseTime": {"input": 4.45560328049998, "reasoning": 0, "answer": 2.636817813940881, "total": 7.09242109444086}, "timeToFirstAnswerToken": {"input": 4.45560328049998, "reasoning": 0, "total": 4.45560328049998}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "39b64e04-7a69-4aa2-9e2e-fe38c24681ec", "slug": "olmo-3-1-32b-think", "name": "Olmo 3.1 32B Think", "shortName": "Olmo 3.1 32B Think", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "olmo-3-1-32b-think", "name": "Olmo 3.1 32B Think"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32.2, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 65500, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/allenai/Olmo-3.1-32B-Think", "microevalsEnabled": false, "intelligenceIndex": 7.12364412279906, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -43.3666666666667, "omniscienceBreakdown": {"accuracy": 0.13783333333333334, "hallucinationRate": 0.6628648753141311}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.659863945578231, "hle": 0.0625579240037071, "gpqa": 0.590909090909091, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.695238095238095, "aime25": 0.773333333333333, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "ab6c5270-d7b9-4c09-92fe-62662618c631", "slug": "ai2", "name": "Allen Institute for AI", "logo": "/img/logos/ai2_small.svg", "color": "#F0529C", "country": "us", "url": "https://allenai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3b156101-b0d7-4438-b350-2d1f1168f40a", "slug": "qwen3-6-27b-non-reasoning", "name": "Qwen3.6 27B (Non-reasoning)", "shortName": "Qwen3.6 27B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-22", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-6-27b", "name": "Qwen3.6 27B"}, "deprecated": true, "deprecatedTo": "qwen3-8-27b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 27.8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.6-27B", "microevalsEnabled": false, "intelligenceIndex": 19.8288203580036, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -53.2, "omniscienceBreakdown": {"accuracy": 0.16716666666666666, "hallucinationRate": 0.8395037022213327}, "gdpval": 1042.8, "gdpvalNormalized": 0.2714, "itBenchSre": null, "tau2": 0.935672514619883, "tauBanking": 0.0927835051546392, "terminalbenchHard": 0.212121212121212, "terminalBench21": 0.51310861423221, "terminalBench40": null, "scicode": null, "lcr": 0.666666666666667, "ifbench": 0.457142857142857, "hle": 0.150602409638554, "gpqa": 0.829292929292929, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": 0.717341040462428, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.6, "price1mOutputTokens": 3.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.615, "price1mBlended0To3To1": 1.35, "price1mBlended7To2To1": 0.9, "price1mBlended0To1To1": 2.1, "price1mBlended100To1To1": 0.6294117647058823, "price1mBlended0To100To1": 0.6297029702970297, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 60.7244226966649, "medianTimeToFirstChunk": 3.66734270599994}, "outputSpeedVariance": {"p05": 49.1231941223738, "q25": 52.1261470564658, "median": 60.7244226966649, "q75": 65.5006200176543, "p95": 69.0409428688841}, "timeToFirstChunkVariance": {"p05": 3.46696847120006, "q25": 3.58423029775, "median": 3.66734270599994, "q75": 3.88852974299992, "p95": 5.14639699810001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 56.9367340964973, "medianTimeToFirstChunk": 1.38913472400001, "medianTimeToFirstAnswerToken": 1.38913472400001, "medianEndToEndResponseTime": 10.170811578745347}, "long": {"medianOutputSpeed": 60.7244226966649, "medianTimeToFirstChunk": 3.66734270599994, "medianTimeToFirstAnswerToken": 3.66734270599994, "medianEndToEndResponseTime": 11.901262071485501}, "hundredK": {"medianOutputSpeed": 64.4526970752916, "medianTimeToFirstChunk": 32.9138881895, "medianTimeToFirstAnswerToken": 32.9138881895, "medianEndToEndResponseTime": 40.671515452419904}, "mediumParallel": {"medianOutputSpeed": 52.7269246929552, "medianTimeToFirstChunk": 1.40465907050001, "medianTimeToFirstAnswerToken": 1.40465907050001, "medianEndToEndResponseTime": 10.887480283981565}}, "endToEndResponseTime": {"input": 3.66734270599994, "reasoning": 0, "answer": 8.23391936548556, "total": 11.901262071485501}, "timeToFirstAnswerToken": {"input": 3.66734270599994, "reasoning": 0, "total": 3.66734270599994}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 5, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3b5ba264-ad25-429b-a460-4d8698205f0d", "slug": "nex-n2-pro", "name": "Nex-N2-Pro", "shortName": "Nex-N2-Pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "nex-n2-pro", "name": "Nex-N2-Pro"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 397, "inferenceParametersActiveBillions": 17, "sizeClass": "large", "contextWindowTokens": 262000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/nex-agi/Nex-N2-Pro", "microevalsEnabled": true, "intelligenceIndex": 28.1990972887912, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -27.05, "omniscienceBreakdown": {"accuracy": 0.3481666666666667, "hallucinationRate": 0.9491178726668371}, "gdpPdfAllPass": 0.126, "gdpval": 1175.2, "gdpvalNormalized": 0.3376, "itBenchSre": null, "tau2": 0.815789473684211, "tauBanking": 0.175257731958763, "terminalbenchHard": null, "terminalBench21": 0.677902621722846, "terminalBench40": null, "scicode": 0.43287037037037, "lcr": 0.816666666666667, "ifbench": 0.661904761904762, "hle": 0.337349397590361, "gpqa": 0.891919191919192, "critpt": 0.0857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.17629116737896317, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b2c5c58a-a26f-46f2-80ea-3bd23dfbd3ca", "slug": "nex", "name": "Nex AGI", "logo": "/img/logos/nex_small.svg", "color": "#0351bc", "country": "cn", "url": "https://nex-agi.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3b608b70-6434-4baa-99ad-45d499703c67", "slug": "gpt-4-1", "name": "GPT-4.1", "shortName": "GPT-4.1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-14", "knowledgeCutoffDate": "2024-05-31", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4-1", "name": "GPT-4.1"}, "deprecated": true, "deprecatedTo": "gpt-5-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.6913226077818, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -39.6333333333333, "omniscienceBreakdown": {"accuracy": 0.2776666666666667, "hallucinationRate": 0.9330872173511767}, "gdpval": null, "itBenchSre": null, "tau2": 0.470760233918129, "tauBanking": null, "terminalbenchHard": 0.136363636363636, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.683333333333333, "ifbench": 0.429931972789116, "hle": 0.0418, "gpqa": 0.665656565656566, "critpt": 0, "apexAgents": null, "mmmuPro": 0.612138728323699, "livecodebench": 0.457142857142857, "aime25": 0.346666666666667, "analystAgent": null, "price1mInputTokens": 2, "price1mOutputTokens": 8, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": 1.53, "price1mBlended0To3To1": 3.5, "price1mBlended7To2To1": 1.55, "price1mBlended0To1To1": 5, "price1mBlended100To1To1": 0.5882352941176471, "price1mBlended0To100To1": 2.0594059405940595, "timescaleData": {"medianOutputSpeed": 132.718707880343, "medianTimeToFirstChunk": 1.08935632049992}, "outputSpeedVariance": {"p05": 80.2545557549824, "q25": 124.544857438168, "median": 132.718707880343, "q75": 147.279709906035, "p95": 174.637119809315}, "timeToFirstChunkVariance": {"p05": 0.828648647900047, "q25": 0.927222120499849, "median": 1.08935632049992, "q75": 1.26046085325001, "p95": 2.1702670607}, "performanceByPromptType": {"long": {"medianOutputSpeed": 132.718707880343, "medianTimeToFirstChunk": 1.08935632049992, "medianTimeToFirstAnswerToken": 1.08935632049992, "medianEndToEndResponseTime": 4.856722715076273}}, "endToEndResponseTime": {"input": 1.08935632049992, "reasoning": 0, "answer": 3.767366394576353, "total": 4.856722715076273}, "timeToFirstAnswerToken": {"input": 1.08935632049992, "reasoning": 0, "total": 1.08935632049992}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3b7de71c-e034-4591-8ca6-6b6be2fa471f", "slug": "claude-fable-5-1-medium", "name": "Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)", "shortName": "Claude Fable 5.1 (medium with fallback)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "claude-fable-5-1", "name": "Claude Fable 5.1"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 49.0591662609523, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 51.5746540252242, "strategyAndOps": 54.14367496138974, "legal": 56.9110673846879, "engineering": 51.646375010331035, "economics": 58.006455958449166}, "omniscience": 37.6, "omniscienceBreakdown": {"accuracy": 0.631, "hallucinationRate": 0.6910569105691057}, "harveyLab": 0.926472716746273, "gdpPdfAllPass": 0.268, "gdpval": 1579.31, "gdpvalNormalized": 0.539655, "itBenchSre": null, "tau2": null, "tauBanking": 0.410309278350515, "terminalbenchHard": null, "terminalBench21": 0.880149812734082, "terminalBench40": 0.44949494949495, "scicode": 0.563657407407407, "lcr": 0.846666666666667, "ifbench": null, "hle": 0.537998146431881, "gpqa": 0.885858585858586, "critpt": 0.291428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5466103465672885, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.975, "cacheWritePrice": 12.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.175, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 316.660069234107, "intelligenceIndexCost": {"total": 3983.2789352019263, "input": 1816.8455658810517, "nonCacheInput": 348.85775955651, "cacheRead": 419.47044940844114, "cacheWrite": 1048.5173569161007, "output": 2166.4333693208746, "reasoning": 998.847721371875, "answer": 1167.5856479489998}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.982597436096585, "input": 1.5896416523336108, "nonCacheInput": 0.256042067651855, "cacheRead": 0.5021156425832897, "cacheWrite": 0.8314839420984659, "output": 1.3929557837629736, "reasoning": 0.603394545278131, "answer": 0.7895612384848425}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 1.287029196715029}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.21841698816942393}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.08215230042992551}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.9124327942195763}, {"slug": "scicode", "weightedCostPerTask": 0.007562430555555557}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.02254167465942447}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.19601907}, {"slug": "critpt", "weightedCostPerTask": 0.18038545714285717}, {"slug": "omniscience", "weightedCostPerTask": 0.0022983592047922503}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.073759165}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1766972607, "output": 44205040, "answer": 23716665, "reasoning": 20488375}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 12081.522329392306, "answer": 15806.115480715269, "output": 27887.637810107575}, "briefcaseBreakdown": {"overall": {"elo": 1531.2, "lower95ci": 1522.9, "upper95ci": 1539.95}, "rubricPassRate": 0.5606060606060606, "analyticalQuality": {"elo": 1787.26, "lower95ci": 1772.22, "upper95ci": 1804.33}, "presentation": {"elo": 1332.82, "lower95ci": 1317.72, "upper95ci": 1347.16}}, "briefcaseTotalCost": 780.7977126737842, "timescaleData": {"medianOutputSpeed": 54.0313776621313, "medianTimeToFirstChunk": 6.38494349949996}, "outputSpeedVariance": {"p05": 42.4949996371358, "q25": 44.0592252149631, "median": 54.0313776621313, "q75": 64.5606660712922, "p95": 73.7596649438599}, "timeToFirstChunkVariance": {"p05": 3.52371331540005, "q25": 4.85702500575002, "median": 6.38494349949996, "q75": 9.51620332175012, "p95": 27.46467633655}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 55.703453159268, "medianTimeToFirstChunk": 6.95238333849996, "medianTimeToFirstAnswerToken": 6.95238333849996, "medianEndToEndResponseTime": 15.928487541059788}, "long": {"medianOutputSpeed": 54.0313776621313, "medianTimeToFirstChunk": 6.38494349949996, "medianTimeToFirstAnswerToken": 6.38494349949996, "medianEndToEndResponseTime": 15.63882562567111}, "hundredK": {"medianOutputSpeed": 63.7867038606362, "medianTimeToFirstChunk": 13.638485654, "medianTimeToFirstAnswerToken": 13.638485654, "medianEndToEndResponseTime": 21.47710984584444}, "mediumParallel": {"medianOutputSpeed": 53.6466089120603, "medianTimeToFirstChunk": 14.0446180525001, "medianTimeToFirstAnswerToken": 14.0446180525001, "medianEndToEndResponseTime": 23.364871655474715}}, "endToEndResponseTime": {"input": 6.38494349949996, "reasoning": 0, "answer": 9.25388212617115, "total": 15.63882562567111}, "timeToFirstAnswerToken": {"input": 6.38494349949996, "reasoning": 0, "total": 6.38494349949996}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3bc32f13-5afa-4e28-bce1-10e57376686b", "slug": "command-a", "name": "Command A", "shortName": "Command A", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-13", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "command-a", "name": "Command A"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 111, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": "CC-BY-NC 4.0 License with Acceptable Use Addendum", "licenseUrl": "https://cohere.com/c4ai-cc-by-nc-license", "modelWeightsSourceUrl": "https://huggingface.co/CohereForAI/c4ai-command-a-03-2025", "microevalsEnabled": true, "intelligenceIndex": 6.9581988704518, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -48.2666666666667, "omniscienceBreakdown": {"accuracy": 0.16383333333333333, "hallucinationRate": 0.7731712178592784}, "gdpval": null, "itBenchSre": null, "tau2": 0.152046783625731, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.213333333333333, "ifbench": 0.364625850340136, "hle": 0.0403151065801668, "gpqa": 0.527272727272727, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.286772486772487, "aime25": 0.13, "analystAgent": null, "price1mInputTokens": 2.5, "price1mOutputTokens": 10, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4.375, "price1mBlended7To2To1": 3.25, "price1mBlended0To1To1": 6.25, "price1mBlended100To1To1": 2.573529411764706, "price1mBlended0To100To1": 2.5742574257425743, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 3, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 53.2421838836857, "medianTimeToFirstChunk": 1.820189766}, "outputSpeedVariance": {"p05": 23.0022593805563, "q25": 35.0590973181634, "median": 53.2421838836857, "q75": 64.2001331309412, "p95": 72.7506059151783}, "timeToFirstChunkVariance": {"p05": 1.54432586855, "q25": 1.63726539550003, "median": 1.820189766, "q75": 2.37118820874997, "p95": 3.01222543659989}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 53.7266327549511, "medianTimeToFirstChunk": 0.410166845999981, "medianTimeToFirstAnswerToken": 0.410166845999981, "medianEndToEndResponseTime": 9.716538274124206}, "long": {"medianOutputSpeed": 53.2421838836857, "medianTimeToFirstChunk": 1.820189766, "medianTimeToFirstAnswerToken": 1.820189766, "medianEndToEndResponseTime": 11.211239560131537}, "hundredK": {"medianOutputSpeed": 73.6411818359869, "medianTimeToFirstChunk": 18.089482675, "medianTimeToFirstAnswerToken": 18.089482675, "medianEndToEndResponseTime": 24.879161867188905}, "mediumParallel": {"medianOutputSpeed": 55.6351950164802, "medianTimeToFirstChunk": 0.533523392500229, "medianTimeToFirstAnswerToken": 0.533523392500229, "medianEndToEndResponseTime": 9.520640267922172}}, "endToEndResponseTime": {"input": 1.820189766, "reasoning": 0, "answer": 9.391049794131536, "total": 11.211239560131537}, "timeToFirstAnswerToken": {"input": 1.820189766, "reasoning": 0, "total": 1.820189766}, "performanceDataSource": {"type": "firstParty", "providerName": "Cohere"}, "hostModelCount": 2, "creator": {"id": "671d3708-c407-4b8f-b350-f728e4689d26", "slug": "cohere", "name": "Cohere", "logo": "/img/logos/cohere_small.svg", "color": "#D18EE2", "country": "ca", "url": "https://cohere.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3c5289e5-1c62-434c-bc44-c51c39f640a1", "slug": "lfm2-5-vl-1-6b", "name": "LFM2.5-VL-1.6B", "shortName": "LFM2.5-VL-1.6B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-05", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "lfm2-5-vl-1-6b", "name": "LFM2.5-VL-1.6B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1.6, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "lfm 1.0", "licenseUrl": "https://huggingface.co/LiquidAI/LFM2-8B-A1B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -84.4166666666667, "omniscienceBreakdown": {"accuracy": 0.057833333333333334, "hallucinationRate": 0.9573677693260216}, "gdpval": null, "itBenchSre": null, "tau2": 0.0847953216374269, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.331292517006803, "hle": 0.0509731232622799, "gpqa": 0.288888888888889, "critpt": 0, "apexAgents": null, "mmmuPro": 0.265317919075145, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "5b1886c4-43ba-4007-b840-9d21a2b7d42c", "slug": "liquidai", "name": "Liquid AI", "logo": "/img/logos/liquidai_small.svg", "color": "#000000", "country": "us", "url": "https://www.liquid.ai"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3cf875b8-b6b5-42c0-ad70-617d5be59d00", "slug": "qwen3-vl-8b-instruct", "name": "Qwen3 VL 8B Instruct", "shortName": "Qwen3 VL 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-14", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-vl-8b-instruct", "name": "Qwen3 VL 8B Instruct"}, "deprecated": true, "deprecatedTo": "qwen3-5-9b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8.77, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 7.25835272478202, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -51.8833333333333, "omniscienceBreakdown": {"accuracy": 0.20483333333333334, "hallucinationRate": 0.9100817438692098}, "gdpval": null, "itBenchSre": null, "tau2": 0.292397660818713, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.166666666666667, "ifbench": 0.32312925170068, "hle": 0.0268767377201112, "gpqa": 0.427272727272727, "critpt": 0, "apexAgents": null, "mmmuPro": 0.473410404624277, "livecodebench": 0.332275132275132, "aime25": 0.273333333333333, "analystAgent": null, "price1mInputTokens": 0.18, "price1mOutputTokens": 0.7, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.184, "price1mBlended0To3To1": 0.31, "price1mBlended7To2To1": 0.23200000000000004, "price1mBlended0To1To1": 0.43999999999999995, "price1mBlended100To1To1": 0.18509803921568627, "price1mBlended0To100To1": 0.18514851485148515, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 114.248621656257, "medianTimeToFirstChunk": 2.29051251649997}, "outputSpeedVariance": {"p05": 91.7017881679068, "q25": 105.410406919805, "median": 114.248621656257, "q75": 121.079218883957, "p95": 122.96307320595}, "timeToFirstChunkVariance": {"p05": 2.15687260854992, "q25": 2.17128533674998, "median": 2.29051251649997, "q75": 2.38257036499994, "p95": 3.78893739740003}, "performanceByPromptType": {"long": {"medianOutputSpeed": 114.248621656257, "medianTimeToFirstChunk": 2.29051251649997, "medianTimeToFirstAnswerToken": 2.29051251649997, "medianEndToEndResponseTime": 6.666932929731422}}, "endToEndResponseTime": {"input": 2.29051251649997, "reasoning": 0, "answer": 4.376420413231451, "total": 6.666932929731422}, "timeToFirstAnswerToken": {"input": 2.29051251649997, "reasoning": 0, "total": 2.29051251649997}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3d4e7366-928c-4eff-a8b0-2919c7d334c9", "slug": "jt-mini", "name": "JT-MINI", "shortName": "JT-MINI", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-15", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "jt-mini", "name": "JT-MINI"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.2117782837313, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -64.1, "omniscienceBreakdown": {"accuracy": 0.14216666666666666, "hallucinationRate": 0.9129590052457742}, "gdpval": null, "itBenchSre": null, "tau2": 0.929824561403509, "tauBanking": null, "terminalbenchHard": 0.181818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.13, "ifbench": 0.366666666666667, "hle": 0.0644114921223355, "gpqa": 0.675757575757576, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "7e7b7290-eacc-420e-a35f-7c8eb4e5205d", "slug": "china-mobile", "name": "China Mobile", "logo": "/img/logos/china_mobile_small.png", "color": "#00b8ea", "country": "cn", "url": "https://jiutian.10086.cn/portal/common-helpcenter#/document/1181?platformCode=DMX_TYZX"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3d64bf83-232e-427e-8590-26b478bae4a8", "slug": "ling-mini-2-0", "name": "Ling-mini-2.0", "shortName": "Ling-mini-2.0", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-09", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "ling-mini-2-0", "name": "Ling-mini-2.0"}, "deprecated": true, "deprecatedTo": "ling-3-0-tiny", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 16.3, "inferenceParametersActiveBillions": 1.4, "sizeClass": "small", "contextWindowTokens": 131000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ling-mini-2.0", "microevalsEnabled": false, "intelligenceIndex": 5.54385892635499, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -78.4666666666667, "omniscienceBreakdown": {"accuracy": 0.08883333333333333, "hallucinationRate": 0.9586610572526065}, "gdpval": null, "itBenchSre": null, "tau2": 0.131578947368421, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.236054421768707, "hle": 0.0505097312326228, "gpqa": 0.561616161616162, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.428571428571429, "aime25": 0.493333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3de55b83-e02b-412e-8211-315bbebe3e94", "slug": "gemini-2-0-flash-lite-preview", "name": "Gemini 2.0 Flash-Lite (Preview)", "shortName": "Gemini 2.0 Flash-Lite (Preview)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-05", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-2-0-flash-lite-preview", "name": "Gemini 2.0 Flash-Lite (Preview)"}, "deprecated": true, "deprecatedTo": "gemini-2-0-flash-lite-001", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.32739604924354, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0409, "gpqa": 0.542424242424242, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.178835978835979, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3e6cf518-a1f4-42d3-8fcf-827c9bd8e6d5", "slug": "qwen3-30b-a3b-instruct-reasoning", "name": "Qwen3 30B A3B (Reasoning)", "shortName": "Qwen3 30B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-30b-a3b-instruct", "name": "Qwen3 30B A3B"}, "deprecated": true, "deprecatedTo": "qwen3-30b-a3b-2507-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30.5, "inferenceParametersActiveBillions": 3.3, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-30B-A3B", "microevalsEnabled": false, "intelligenceIndex": 7.62614322282085, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -51.4833333333333, "omniscienceBreakdown": {"accuracy": 0.16183333333333333, "hallucinationRate": 0.8073175581626566}, "gdpval": null, "itBenchSre": null, "tau2": 0.260233918128655, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.414965986394558, "hle": 0.0616, "gpqa": 0.616161616161616, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.505820105820106, "aime25": 0.723333333333333, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 2.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.75, "price1mBlended7To2To1": 0.42000000000000004, "price1mBlended0To1To1": 1.3, "price1mBlended100To1To1": 0.22156862745098038, "price1mBlended0To100To1": 0.22178217821782176, "timescaleData": {"medianOutputSpeed": 106.273405527951, "medianTimeToFirstChunk": 2.15086291350002}, "outputSpeedVariance": {"p05": 94.7737269616024, "q25": 101.805153797418, "median": 106.273405527951, "q75": 109.706309792394, "p95": 112.710823162925}, "timeToFirstChunkVariance": {"p05": 2.07694313854999, "q25": 2.11517567249997, "median": 2.15086291350002, "q75": 2.32778378149997, "p95": 3.63664305945012}, "performanceByPromptType": {"long": {"medianOutputSpeed": 106.273405527951, "medianTimeToFirstChunk": 2.15086291350002, "medianTimeToFirstAnswerToken": 20.97024665362096, "medianEndToEndResponseTime": 25.675092588651196}}, "endToEndResponseTime": {"input": 2.15086291350002, "reasoning": 18.81938374012094, "answer": 4.704845935030235, "total": 25.675092588651196}, "timeToFirstAnswerToken": {"input": 2.15086291350002, "reasoning": 18.81938374012094, "total": 20.97024665362096}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 3, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3e87c73e-a257-495e-9730-367a66229811", "slug": "claude-fable-5-1", "name": "Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)", "shortName": "Claude Fable 5.1 (max with fallback)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-09-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "claude-fable-5-1", "name": "Claude Fable 5.1"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 53.3737509623252, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 56.51005571946496, "strategyAndOps": 59.78074073285824, "legal": 60.56925700562835, "healthcareAndMedical": 58.082293029874144, "engineering": 56.53179660780986, "economics": 62.74837971115231}, "omniscience": 43.45, "omniscienceBreakdown": {"accuracy": 0.6723333333333333, "hallucinationRate": 0.7258392675483215}, "mlcrOverall": 0.711111111111111, "harveyLab": 0.930235924156897, "gdpPdfAllPass": 0.262, "gdpval": 1763.64, "gdpvalNormalized": 0.63182, "itBenchSre": null, "tau2": null, "tauBanking": 0.472164948453608, "terminalbenchHard": null, "terminalBench21": 0.913857677902622, "terminalBench40": 0.52020202020202, "scicode": 0.630787037037037, "lcr": 0.853333333333333, "ifbench": null, "hle": 0.591288229842447, "gpqa": 0.937373737373737, "critpt": 0.297142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.575, "automationBenchPartialScore": 0.5937591715646424, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.975, "cacheWritePrice": 12.5, "pricePer1k1mpImages": 13.05, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.175, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 745.7250104934574, "intelligenceIndexCost": {"total": 13128.859210511622, "input": 3891.477294227097, "nonCacheInput": 351.269572652325, "cacheRead": 1387.5926117156475, "cacheWrite": 2152.6151098591245, "output": 9237.381916284525, "reasoning": 7218.918316940026, "answer": 2018.4635993445}, "intelligenceIndexCostPerTask": {"cost": {"total": 7.629706364004841, "input": 3.726348513816252, "nonCacheInput": 0.25859453097928414, "cacheRead": 1.603090760194992, "cacheWrite": 1.8646632226419768, "output": 3.9033578501885873, "reasoning": 2.359948393842491, "answer": 1.543409456346096}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 3.4070187981352693}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.9774869276879293}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.1305647128794272}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.9218480031061167}, {"slug": "scicode", "weightedCostPerTask": 0.06585189583333334}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.15858915690099742}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.27748913}, {"slug": "critpt", "weightedCostPerTask": 0.5713794857142858}, {"slug": "omniscience", "weightedCostPerTask": 0.040254274432821376}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.07922397931466}]}, "canonicalIntelligenceIndexTokenCount": {"input": 5630485614, "output": 188465663, "answer": 41121780, "reasoning": 147343883}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 47239.81546124743, "answer": 30870.99075157802, "output": 78110.80621282545}, "briefcaseBreakdown": {"overall": {"elo": 1661.82, "lower95ci": 1652.55, "upper95ci": 1671.71}, "rubricPassRate": 0.6151515151515151, "analyticalQuality": {"elo": 1958.55, "lower95ci": 1941.58, "upper95ci": 1978.46}, "presentation": {"elo": 1472.72, "lower95ci": 1458.25, "upper95ci": 1488.74}}, "briefcaseTotalCost": 2066.9247375353966, "timescaleData": {"medianOutputSpeed": 67.6942867003517, "medianTimeToFirstChunk": 262.877531015}, "outputSpeedVariance": {"p05": 55.6093225831226, "q25": 61.9120004910438, "median": 67.6942867003517, "q75": 71.0584928104012, "p95": 74.1528538494964}, "timeToFirstChunkVariance": {"p05": 95.5435508104, "q25": 126.2897172, "median": 262.877531015, "q75": 302.714253127, "p95": 356.1454879933}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 69.2182186971995, "medianTimeToFirstChunk": 130.154852777, "medianTimeToFirstAnswerToken": 130.154852777, "medianEndToEndResponseTime": 137.37838452067703}, "long": {"medianOutputSpeed": 67.6942867003517, "medianTimeToFirstChunk": 262.877531015, "medianTimeToFirstAnswerToken": 262.877531015, "medianEndToEndResponseTime": 270.26367871477925}, "hundredK": {"medianOutputSpeed": 69.868153076027, "medianTimeToFirstChunk": 92.684119409, "medianTimeToFirstAnswerToken": 92.684119409, "medianEndToEndResponseTime": 99.8404557079705}, "mediumParallel": {"medianOutputSpeed": 63.198594434419, "medianTimeToFirstChunk": 194.2697089585, "medianTimeToFirstAnswerToken": 194.2697089585, "medianEndToEndResponseTime": 202.18127731654076}}, "endToEndResponseTime": {"input": 262.877531015, "reasoning": 0, "answer": 7.3861476997792535, "total": 270.26367871477925}, "timeToFirstAnswerToken": {"input": 262.877531015, "reasoning": 0, "total": 262.877531015}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 5, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3edcb2ed-6981-4f88-a556-563f7f8f00aa", "slug": "mixtral-8x7b-instruct", "name": "Mixtral 8x7B Instruct", "shortName": "Mixtral 8x7B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-12-11", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mixtral-8x7b-instruct", "name": "Mixtral 8x7B Instruct"}, "deprecated": true, "deprecatedTo": "mistral-small-3-2", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 46.7, "inferenceParametersActiveBillions": 12.9, "sizeClass": "medium", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1", "microevalsEnabled": false, "intelligenceIndex": 5.12294610372299, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0468, "gpqa": 0.291919191919192, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0656084656084656, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.45, "price1mOutputTokens": 0.7, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5125, "price1mBlended7To2To1": 0.475, "price1mBlended0To1To1": 0.575, "price1mBlended100To1To1": 0.4524509803921569, "price1mBlended0To100To1": 0.4524752475247525, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3ef6db79-1dfa-4780-8c4b-affe2740d9ac", "slug": "molmo2-8b", "name": "Molmo2-8B", "shortName": "Molmo2-8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-11", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "molmo2-8b", "name": "Molmo2-8B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8.66, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 36864, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/allenai/Molmo2-8B", "microevalsEnabled": false, "intelligenceIndex": 5.00251209304105, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -69.2166666666667, "omniscienceBreakdown": {"accuracy": 0.1145, "hallucinationRate": 0.9109730848861284}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.269387755102041, "hle": 0.0426320667284523, "gpqa": 0.425252525252525, "critpt": 0, "apexAgents": null, "mmmuPro": 0.374566473988439, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 72.22222222222223, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "ab6c5270-d7b9-4c09-92fe-62662618c631", "slug": "ai2", "name": "Allen Institute for AI", "logo": "/img/logos/ai2_small.svg", "color": "#F0529C", "country": "us", "url": "https://allenai.org/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "3fd96175-4ef1-434c-8795-f873aec2abc1", "slug": "mistral-small-4", "name": "Mistral Small 4 (Reasoning)", "shortName": "Mistral Small 4", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "mistral-small-4", "name": "Mistral Small 4"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 119, "inferenceParametersActiveBillions": 6.5, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-Small-4-119B-2603", "microevalsEnabled": true, "intelligenceIndex": 11.4511294141469, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 10.764372607463526, "strategyAndOps": 6.986667696223364, "legal": 12.98917949025212, "engineering": 16.554350577916736, "economics": 18.297640104567787}, "omniscience": -30.4, "omniscienceBreakdown": {"accuracy": 0.21683333333333332, "hallucinationRate": 0.6650351138540115}, "gdpPdfAllPass": 0, "gdpval": 536.71, "gdpvalNormalized": 0.018355000000000017, "itBenchSre": null, "tau2": 0.412280701754386, "tauBanking": 0.0494845360824742, "terminalbenchHard": 0.174242424242424, "terminalBench21": 0.209737827715356, "terminalBench40": 0, "scicode": 0.387731481481481, "lcr": 0.496666666666667, "ifbench": 0.481632653061224, "hle": 0.0987025023169602, "gpqa": 0.768686868686869, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.568208092485549, "livecodebench": null, "aime25": null, "analystAgent": 0.0125, "automationBenchPartialScore": 0.009635410038882158, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.2, "price1mBlended0To3To1": 0.26249999999999996, "price1mBlended7To2To1": 0.195, "price1mBlended0To1To1": 0.375, "price1mBlended100To1To1": 0.15441176470588236, "price1mBlended0To100To1": 0.15445544554455445, "intelligenceIndexTimePerTask": 100.15160170952858, "intelligenceIndexCost": {"total": 78.69587594999999, "input": 46.34231954999999, "nonCacheInput": 1.92049605, "cacheRead": 0, "cacheWrite": 44.421823499999995, "output": 32.3535564, "reasoning": 28.6803198, "answer": 3.6732366}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.045070159253737405, "input": 0.036435901508102005, "nonCacheInput": 0.0009650824392211152, "cacheRead": 0, "cacheWrite": 0.03547081906888089, "output": 0.008634257745635398, "reasoning": 0.005652259687455583, "answer": 0.0029819980581798134}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.009799971181318682}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.002273352545454545}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0016394358333333332}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.025214359999999998}, {"slug": "scicode", "weightedCostPerTask": 0.00050509671875}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0009874342284522707}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00025780335}, {"slug": "critpt", "weightedCostPerTask": 0.003578315571428572}, {"slug": "omniscience", "weightedCostPerTask": 6.343702499999999e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0007509528}]}, "canonicalIntelligenceIndexTokenCount": {"input": 308948797, "output": 53922594, "answer": 6122061, "reasoning": 47800533}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 9420.43281242597, "answer": 4969.996763633023, "output": 14390.429576058992}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 255.96, "lower95ci": 245.72, "upper95ci": 265.6}, "rubricPassRate": 0.05656565656565657, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0.34}, "presentation": {"elo": 192.93, "lower95ci": 173.06, "upper95ci": 212.9}}, "briefcaseTotalCost": 5.94531585, "timescaleData": {"medianOutputSpeed": 173.575436705566, "medianTimeToFirstChunk": 0.772091026999988}, "outputSpeedVariance": {"p05": 100.654014960764, "q25": 136.263900853182, "median": 173.575436705566, "q75": 189.99313857376, "p95": 198.71653216539}, "timeToFirstChunkVariance": {"p05": 0.698742621999941, "q25": 0.727969982999998, "median": 0.772091026999988, "q75": 0.827027352999963, "p95": 1.13399586980002}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 171.129916253849, "medianTimeToFirstChunk": 0.546742739000024, "medianTimeToFirstAnswerToken": 12.233770020853303, "medianEndToEndResponseTime": 15.155526841316622}, "long": {"medianOutputSpeed": 173.575436705566, "medianTimeToFirstChunk": 0.772091026999988, "medianTimeToFirstAnswerToken": 12.29445869583424, "medianEndToEndResponseTime": 15.175050613042805}, "hundredK": {"medianOutputSpeed": 128.417774447195, "medianTimeToFirstChunk": 5.31488860649999, "medianTimeToFirstAnswerToken": 20.88905665768666, "medianEndToEndResponseTime": 24.782598670483324}, "mediumParallel": {"medianOutputSpeed": 161.059875379616, "medianTimeToFirstChunk": 0.599508390000011, "medianTimeToFirstAnswerToken": 13.017250520285575, "medianEndToEndResponseTime": 16.121686052856965}}, "endToEndResponseTime": {"input": 0.772091026999988, "reasoning": 11.522367668834253, "answer": 2.8805919172085632, "total": 15.175050613042805}, "timeToFirstAnswerToken": {"input": 0.772091026999988, "reasoning": 11.522367668834253, "total": 12.29445869583424}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "405e2235-0925-4634-a3c7-fbd5f6394bc0", "slug": "qwen3-5-0-8b-non-reasoning", "name": "Qwen3.5 0.8B (Non-reasoning)", "shortName": "Qwen3.5 0.8B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-5-0-8b", "name": "Qwen3.5 0.8B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 0.873, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-0.8B", "microevalsEnabled": false, "intelligenceIndex": 5.40008099703412, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -88.5833333333333, "omniscienceBreakdown": {"accuracy": 0.049833333333333334, "hallucinationRate": 0.9847395193825644}, "gdpval": -133.2, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.652046783625731, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": 0.00374531835205993, "terminalBench40": null, "scicode": null, "lcr": 0.08, "ifbench": 0.215646258503401, "hle": 0.0509731232622799, "gpqa": 0.236363636363636, "critpt": 0, "apexAgents": null, "mmmuPro": 0.256647398843931, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "40663ad2-b218-471e-bdd4-a1e0c2360e2b", "slug": "glm-5", "name": "GLM-5 (Reasoning)", "shortName": "GLM-5", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 3105, "release": {"slug": "glm-5", "name": "GLM-5"}, "deprecated": true, "deprecatedTo": "glm-5-1", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 744, "inferenceParametersActiveBillions": 40, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-5", "microevalsEnabled": false, "intelligenceIndex": 27.9111550817227, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 0.266666666666667, "omniscienceBreakdown": {"accuracy": 0.263, "hallucinationRate": 0.35323383084577115}, "gdpval": null, "itBenchSre": null, "tau2": 0.982456140350877, "tauBanking": null, "terminalbenchHard": 0.431818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.756666666666667, "ifbench": 0.72312925170068, "hle": 0.292863762743281, "gpqa": 0.82020202020202, "critpt": 0.02, "apexAgents": 0.14454277286135694, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1, "price1mOutputTokens": 3.2, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.55, "price1mBlended7To2To1": 0.66, "price1mBlended0To1To1": 2.1, "price1mBlended100To1To1": 0.2372549019607843, "price1mBlended0To100To1": 1.0217821782178218, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 63.3456247121388, "medianTimeToFirstChunk": 1.442981358}, "outputSpeedVariance": {"p05": 27.2262191190025, "q25": 50.4476128803412, "median": 63.3456247121388, "q75": 79.1748722747929, "p95": 108.523914672053}, "timeToFirstChunkVariance": {"p05": 0.840549311599966, "q25": 1.23149407, "median": 1.442981358, "q75": 1.73721025200001, "p95": 5.81951683039997}, "performanceByPromptType": {"long": {"medianOutputSpeed": 63.3456247121388, "medianTimeToFirstChunk": 1.442981358, "medianTimeToFirstAnswerToken": 50.45978424075687, "medianEndToEndResponseTime": 58.35298921382561}}, "endToEndResponseTime": {"input": 1.442981358, "reasoning": 49.01680288275687, "answer": 7.893204973068739, "total": 58.35298921382561}, "timeToFirstAnswerToken": {"input": 1.442981358, "reasoning": 49.01680288275687, "total": 50.45978424075687}, "performanceDataSource": {"type": "median"}, "hostModelCount": 6, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4077490a-bbfb-404e-979a-a97a20e3b5de", "slug": "claude-opus-4-5", "name": "Claude Opus 4.5 (Non-reasoning)", "shortName": "Claude Opus 4.5 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-24", "knowledgeCutoffDate": "2025-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-opus-4-5", "name": "Claude Opus 4.5"}, "deprecated": true, "deprecatedTo": "claude-opus-4-6", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 23.6788975349785, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -4.13333333333333, "omniscienceBreakdown": {"accuracy": 0.4091666666666667, "hallucinationRate": 0.7624823695345557}, "gdpval": null, "itBenchSre": null, "tau2": 0.862573099415205, "tauBanking": null, "terminalbenchHard": 0.409090909090909, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.706666666666667, "ifbench": 0.429931972789116, "hle": 0.131603336422614, "gpqa": 0.81010101010101, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.712138728323699, "livecodebench": 0.737566137566138, "aime25": 0.626666666666667, "analystAgent": null, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.67, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 45.5672287053282, "medianTimeToFirstChunk": 1.23069592999991}, "outputSpeedVariance": {"p05": 36.9049133208674, "q25": 38.762362673658, "median": 45.5672287053282, "q75": 61.6051344222947, "p95": 89.5536642997638}, "timeToFirstChunkVariance": {"p05": 0.905183740199993, "q25": 0.947186240500059, "median": 1.23069592999991, "q75": 1.327069672, "p95": 1.5885044569}, "performanceByPromptType": {"long": {"medianOutputSpeed": 45.5672287053282, "medianTimeToFirstChunk": 1.23069592999991, "medianTimeToFirstAnswerToken": 1.23069592999991, "medianEndToEndResponseTime": 12.203494017708387}}, "endToEndResponseTime": {"input": 1.23069592999991, "reasoning": 0, "answer": 10.972798087708476, "total": 12.203494017708387}, "timeToFirstAnswerToken": {"input": 1.23069592999991, "reasoning": 0, "total": 1.23069592999991}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "41f73c27-880c-4f30-8b07-9999ce89a4ae", "slug": "qwen-chat-72b", "name": "Qwen Chat 72B", "shortName": "Qwen Chat 72B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-11-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen-chat-72b", "name": "Qwen Chat 72B"}, "deprecated": true, "deprecatedTo": "qwen3-32b-instruct", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 72, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 33792, "licenseName": "Tongyi Qianwen LICENSE AGREEMENT", "licenseUrl": "https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen-72B-Chat", "microevalsEnabled": false, "intelligenceIndex": 5.4363632246188, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "41faf421-118b-465b-b170-d200776580d1", "slug": "gemini-1-5-flash", "name": "Gemini 1.5 Flash (Sep '24)", "shortName": "Gemini 1.5 Flash (Sep)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-24", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-1-5-flash-sep-24", "name": "Gemini 1.5 Flash (Sep '24)"}, "deprecated": true, "deprecatedTo": "gemini-2-0-flash-lite-001", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.07110907005398, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0317, "gpqa": 0.462626262626263, "critpt": null, "apexAgents": null, "mmmuPro": 0.483815028901734, "livecodebench": 0.273015873015873, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "426d24c8-49ae-482a-b4a8-20f1c53f21c1", "slug": "gpt-5-6-luna", "name": "GPT-5.6 Luna (max)", "shortName": "GPT-5.6 Luna (max)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "gpt-5-6-luna", "name": "GPT-5.6 Luna"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 37.5048489690841, "intelligenceIndexIsEstimated": false, "capabilities": {"engineering": 36.17933866715615, "economics": 42.76612115770777}, "omniscience": -10.2833333333333, "omniscienceBreakdown": {"accuracy": 0.42733333333333334, "hallucinationRate": 0.9257857974388825}, "mlcrOverall": 0.194444444444444, "harveyLab": 0.878998407873788, "gdpPdfAllPass": 0.24, "gdpval": 1459.92, "gdpvalNormalized": 0.47996000000000005, "itBenchSre": 0.403201506591337, "tau2": null, "tauBanking": 0.311340206185567, "terminalbenchHard": null, "terminalBench21": 0.808988764044944, "terminalBench40": 0.116161616161616, "scicode": 0.53587962962963, "lcr": 0.836666666666667, "ifbench": null, "hle": 0.394810009267841, "gpqa": 0.911111111111111, "critpt": 0.205714285714286, "apexAgents": 0.358407079646018, "mmmuPro": 0.785549132947977, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5020861763756194, "enterpriseOpsGym": 0.40823634735899733, "price1mInputTokens": 0.2, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.02, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.25, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.45, "price1mBlended7To2To1": 0.174, "price1mBlended0To1To1": 0.7, "price1mBlended100To1To1": 0.03333333333333334, "price1mBlended0To100To1": 0.2099009900990099, "intelligenceIndexTimePerTask": 340.28133199723294, "intelligenceIndexCost": {"total": 319.92851141699316, "input": 135.5404426169932, "nonCacheInput": 5.8352326, "cacheRead": 94.19413986808753, "cacheWrite": 35.51107014890568, "output": 184.38806879999999, "reasoning": 162.3706872, "answer": 22.0173816}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.17829726152289094, "input": 0.12881575370170473, "nonCacheInput": 0.004640576617249952, "cacheRead": 0.09774468082447282, "cacheWrite": 0.026430496259981964, "output": 0.04948150782118623, "reasoning": 0.03371790235319099, "answer": 0.01576360546799524}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.05925961270752338}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.010989409800659948}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.004559162854250227}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.08493287460827653}, {"slug": "scicode", "weightedCostPerTask": 0.000927091111111111}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002925640926784059}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.005679524}, {"slug": "critpt", "weightedCostPerTask": 0.006332287714285714}, {"slug": "omniscience", "weightedCostPerTask": 0.0016457128}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0010459450000000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4880927437, "output": 153656724, "answer": 18347818, "reasoning": 135308906}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 28098.251960992493, "answer": 13136.33788999603, "output": 41234.58985098852}, "briefcaseBreakdown": {"overall": {"elo": 1332.39, "lower95ci": 1326, "upper95ci": 1339.09}, "rubricPassRate": 0.3797979797979798, "analyticalQuality": {"elo": 1342.45, "lower95ci": 1330.12, "upper95ci": 1355.23}, "presentation": {"elo": 1463.22, "lower95ci": 1452.22, "upper95ci": 1475.32}}, "briefcaseTotalCost": 35.950831709230854, "timescaleData": {"medianOutputSpeed": 123.503964548474, "medianTimeToFirstChunk": 116.30851641}, "outputSpeedVariance": {"p05": 90.7006462717847, "q25": 111.388144484709, "median": 123.503964548474, "q75": 135.822629761651, "p95": 163.377398373781}, "timeToFirstChunkVariance": {"p05": 23.38159990035, "q25": 75.27053748025, "median": 116.30851641, "q75": 192.4204357305, "p95": 278.26479099965}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 123.517189390285, "medianTimeToFirstChunk": 91.7547824495, "medianTimeToFirstAnswerToken": 91.7547824495, "medianEndToEndResponseTime": 95.80280202044504}, "long": {"medianOutputSpeed": 123.503964548474, "medianTimeToFirstChunk": 116.30851641, "medianTimeToFirstAnswerToken": 116.30851641, "medianEndToEndResponseTime": 120.35696944410284}, "hundredK": {"medianOutputSpeed": 108.950664023241, "medianTimeToFirstChunk": 37.9006075425001, "medianTimeToFirstAnswerToken": 37.9006075425001, "medianEndToEndResponseTime": 42.48984070121992}, "mediumParallel": {"medianOutputSpeed": 123.544798711843, "medianTimeToFirstChunk": 154.743591716, "medianTimeToFirstAnswerToken": 154.743591716, "medianEndToEndResponseTime": 158.79070665093306}}, "endToEndResponseTime": {"input": 116.30851641, "reasoning": 0, "answer": 4.048453034102847, "total": 120.35696944410284}, "timeToFirstAnswerToken": {"input": 116.30851641, "reasoning": 0, "total": 116.30851641}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 6, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "43098bd0-77ca-408b-b698-9d60b1d1c3b8", "slug": "glm-4-6v", "name": "GLM-4.6V (Non-reasoning)", "shortName": "GLM-4.6V (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-08", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "glm-4-6v", "name": "GLM-4.6V"}, "deprecated": true, "deprecatedTo": "glm-5v-turbo", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 108, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-4.6V", "microevalsEnabled": false, "intelligenceIndex": 8.35003925872647, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -37.6333333333333, "omniscienceBreakdown": {"accuracy": 0.174, "hallucinationRate": 0.6662631154156577}, "gdpval": null, "itBenchSre": null, "tau2": 0.307017543859649, "tauBanking": null, "terminalbenchHard": 0.0303030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.17, "ifbench": 0.27891156462585, "hle": 0.0366079703429101, "gpqa": 0.565656565656566, "critpt": 0, "apexAgents": null, "mmmuPro": 0.421965317919075, "livecodebench": 0.410582010582011, "aime25": 0.263333333333333, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 0.9, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.44999999999999996, "price1mBlended7To2To1": 0.36, "price1mBlended0To1To1": 0.6, "price1mBlended100To1To1": 0.30588235294117644, "price1mBlended0To100To1": 0.30594059405940593, "timescaleData": {"medianOutputSpeed": 60.9470794737144, "medianTimeToFirstChunk": 2.86189333350004}, "outputSpeedVariance": {"p05": 27.2529200947327, "q25": 40.3854259673791, "median": 60.9470794737144, "q75": 78.2866704897265, "p95": 96.3742299989931}, "timeToFirstChunkVariance": {"p05": 1.92538590784999, "q25": 2.10992210700003, "median": 2.86189333350004, "q75": 4.49458507825002, "p95": 9.53706492515}, "performanceByPromptType": {"long": {"medianOutputSpeed": 60.9470794737144, "medianTimeToFirstChunk": 2.86189333350004, "medianTimeToFirstAnswerToken": 2.86189333350004, "medianEndToEndResponseTime": 11.0657318819188}}, "endToEndResponseTime": {"input": 2.86189333350004, "reasoning": 0, "answer": 8.20383854841876, "total": 11.0657318819188}, "timeToFirstAnswerToken": {"input": 2.86189333350004, "reasoning": 0, "total": 2.86189333350004}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "432d6c36-8825-47f3-b4eb-58529cea346b", "slug": "solar-pro-2-preview", "name": "Solar Pro 2 (Preview) (Non-reasoning)", "shortName": "Solar Pro 2 (Preview) (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-20", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "solar-pro-2-preview", "name": "Solar Pro 2 (Preview)"}, "deprecated": true, "deprecatedTo": "solar-pro-2", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 30.9, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 64000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.90554657851904, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0366079703429101, "gpqa": 0.544444444444445, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.385185185185185, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "64ff7f06-c6fb-42ea-ba24-9cd103ab2d61", "slug": "upstage", "name": "Upstage", "logo": "/img/logos/upstage_small.svg", "color": "#7c59f5", "country": "kr", "url": "https://www.upstage.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "433d5c5d-3092-4026-9727-1587ca07915d", "slug": "ling-3-0-flash-vl", "name": "Ling-3.0-flash-VL", "shortName": "Ling-3.0-flash-VL", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "ling-3-0-flash-vl", "name": "Ling-3.0-flash-VL"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 124, "inferenceParametersActiveBillions": 5.5, "sizeClass": "medium", "contextWindowTokens": 262144, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ling-3.0-flash-VL", "microevalsEnabled": false, "intelligenceIndex": 24.9673304077875, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 24.04972637030893, "strategyAndOps": 21.206383778602696, "legal": 26.585086589010878, "engineering": 27.866317330861914, "economics": 35.6569654386778}, "omniscience": -4.53333333333333, "omniscienceBreakdown": {"accuracy": 0.1435, "hallucinationRate": 0.2204709087371084}, "gdpPdfAllPass": 0.084, "gdpval": 1224.84, "gdpvalNormalized": 0.36241999999999996, "itBenchSre": null, "tau2": null, "tauBanking": 0.344329896907216, "terminalbenchHard": null, "terminalBench21": 0.644194756554307, "terminalBench40": 0, "scicode": 0.44212962962963, "lcr": 0.783333333333333, "ifbench": null, "hle": 0.219647822057461, "gpqa": 0.861616161616162, "critpt": 0.02, "apexAgents": null, "mmmuPro": 0.789595375722543, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.1568437535870999, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "intelligenceIndexTimePerTask": 323.0489200312263, "canonicalIntelligenceIndexTokenCount": {"input": 4096507673, "output": 160341964, "answer": 35863996, "reasoning": 124477968}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 29407.32629059241, "answer": 20773.10998476277, "output": 50180.43627535518}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 985.98, "lower95ci": 975.53, "upper95ci": 996.04}, "rubricPassRate": 0.2494824016563147, "analyticalQuality": {"elo": 906.87, "lower95ci": 887.07, "upper95ci": 926.4}, "presentation": {"elo": 1076.05, "lower95ci": 1057.59, "upper95ci": 1095.4}}, "timescaleData": {"medianOutputSpeed": 143.762257661986, "medianTimeToFirstChunk": 2.19250270900003}, "outputSpeedVariance": {"p05": 130.133660694283, "q25": 135.853384695618, "median": 143.762257661986, "q75": 145.855094011841, "p95": 149.415966896547}, "timeToFirstChunkVariance": {"p05": 1.71004177085009, "q25": 2.06401542075004, "median": 2.19250270900003, "q75": 2.39007954575007, "p95": 3.15168081229992}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 146.114208238102, "medianTimeToFirstChunk": 1.67375190199999, "medianTimeToFirstAnswerToken": 15.361674685942248, "medianEndToEndResponseTime": 18.78365538192781}, "long": {"medianOutputSpeed": 143.762257661986, "medianTimeToFirstChunk": 2.19250270900003, "medianTimeToFirstAnswerToken": 16.104359913568995, "medianEndToEndResponseTime": 19.58232421471124}, "hundredK": {"medianOutputSpeed": 127.94386134619, "medianTimeToFirstChunk": 7.70453826700003, "medianTimeToFirstAnswerToken": 23.336394136883523, "medianEndToEndResponseTime": 27.244358104354397}, "mediumParallel": {"medianOutputSpeed": 143.541463619868, "medianTimeToFirstChunk": 1.61776111599998, "medianTimeToFirstAnswerToken": 15.551017400027266, "medianEndToEndResponseTime": 19.034331471034086}}, "endToEndResponseTime": {"input": 2.19250270900003, "reasoning": 13.911857204568966, "answer": 3.4779643011422414, "total": 19.58232421471124}, "timeToFirstAnswerToken": {"input": 2.19250270900003, "reasoning": 13.911857204568966, "total": 16.104359913568995}, "performanceDataSource": {"type": "firstParty", "providerName": "InclusionAI"}, "hostModelCount": 1, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "433e410e-5170-4f03-b92f-7927c220b2fe", "slug": "minicpm-v4-6-1-3b", "name": "MiniCPM-V 4.6 1.3B", "shortName": "MiniCPM-V 4.6 1.3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-11", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "minicpm-v-4-6-1-3b", "name": "MiniCPM-V 4.6 1.3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1.3, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 262000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/openbmb/MiniCPM-V-4.6", "microevalsEnabled": false, "intelligenceIndex": 5.69026588282761, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -82.8666666666667, "omniscienceBreakdown": {"accuracy": 0.06733333333333333, "hallucinationRate": 0.9606862044317369}, "gdpval": -134.2, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.87719298245614, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": 0, "terminalBench40": null, "scicode": null, "lcr": 0.07, "ifbench": 0.26734693877551, "hle": 0.0505097312326228, "gpqa": 0.305050505050505, "critpt": 0, "apexAgents": null, "mmmuPro": 0.379190751445087, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "7399e4ac-f64d-4be6-b649-2fc20756839f", "slug": "openbmb", "name": "OpenBMB", "logo": "/img/logos/openbmb_small.svg", "color": "#3B62EC", "country": "cn", "url": "https://www.openbmb.cn/en/home"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4343afb1-c928-44c9-92e2-68fa1195b6f5", "slug": "gpt-4o-mini-realtime-dec-2024", "name": "GPT-4o mini Realtime (Dec '24)", "shortName": "GPT-4o mini Realtime (Dec)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-17", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4o-mini-realtime-dec-24", "name": "GPT-4o mini Realtime (Dec '24)"}, "deprecated": true, "deprecatedTo": "gpt-realtime-mini-oct-25", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": null, "intelligenceIndexIsEstimated": false, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": true, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": true, "outputModalityVideo": false}, {"id": "43573c57-2403-46fb-af4b-a93de9a0c3f5", "slug": "qwen3-235b-a22b-instruct", "name": "Qwen3 235B A22B (Non-reasoning)", "shortName": "Qwen3 235B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-235b-a22b-instruct", "name": "Qwen3 235B A22B"}, "deprecated": true, "deprecatedTo": "qwen3-235b-a22b-instruct-2507", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 235, "inferenceParametersActiveBillions": 22, "sizeClass": "large", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-235B-A22B", "microevalsEnabled": false, "intelligenceIndex": 8.29469219577047, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -52.3833333333333, "omniscienceBreakdown": {"accuracy": 0.18566666666666667, "hallucinationRate": 0.871264838313549}, "gdpval": null, "itBenchSre": null, "tau2": 0.271929824561404, "tauBanking": null, "terminalbenchHard": 0.0606060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.365986394557823, "hle": 0.0419, "gpqa": 0.613131313131313, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.342857142857143, "aime25": 0.236666666666667, "analystAgent": null, "price1mInputTokens": 0.7, "price1mOutputTokens": 2.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.2249999999999999, "price1mBlended7To2To1": 0.9099999999999998, "price1mBlended0To1To1": 1.75, "price1mBlended100To1To1": 0.7205882352941176, "price1mBlended0To100To1": 0.7207920792079208, "timescaleData": {"medianOutputSpeed": 56.3268335430051, "medianTimeToFirstChunk": 2.74429870849985}, "outputSpeedVariance": {"p05": 41.259513692613, "q25": 48.2000794753617, "median": 56.3268335430051, "q75": 64.2910023726763, "p95": 71.5990690212538}, "timeToFirstChunkVariance": {"p05": 2.61215261964991, "q25": 2.6596300095, "median": 2.74429870849985, "q75": 2.91297696125008, "p95": 3.10209720950004}, "performanceByPromptType": {"long": {"medianOutputSpeed": 56.3268335430051, "medianTimeToFirstChunk": 2.74429870849985, "medianTimeToFirstAnswerToken": 2.74429870849985, "medianEndToEndResponseTime": 11.621062562414235}}, "endToEndResponseTime": {"input": 2.74429870849985, "reasoning": 0, "answer": 8.876763853914385, "total": 11.621062562414235}, "timeToFirstAnswerToken": {"input": 2.74429870849985, "reasoning": 0, "total": 2.74429870849985}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4386585e-71b4-4a0c-8a63-afb333419cd6", "slug": "claude-opus-4-6", "name": "Claude Opus 4.6 (Non-reasoning, High Effort)", "shortName": "Claude Opus 4.6 (Non-reasoning, high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-05", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "claude-opus-4-6", "name": "Claude Opus 4.6"}, "deprecated": true, "deprecatedTo": "claude-opus-4-7-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 26.3534088054787, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 2.36666666666667, "omniscienceBreakdown": {"accuracy": 0.4578333333333333, "hallucinationRate": 0.8007992622194897}, "gdpval": null, "itBenchSre": null, "tau2": 0.847953216374269, "tauBanking": null, "terminalbenchHard": 0.484848484848485, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.67, "ifbench": 0.446258503401361, "hle": 0.190917516218721, "gpqa": 0.84040404040404, "critpt": 0.0284081632653061, "apexAgents": null, "mmmuPro": 0.725433526011561, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.67, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "timescaleData": {"medianOutputSpeed": 38.4428911419889, "medianTimeToFirstChunk": 2.20804692050001}, "outputSpeedVariance": {"p05": 32.6899296896113, "q25": 33.8931675855871, "median": 38.4428911419889, "q75": 48.1848259577381, "p95": 80.3102838695338}, "timeToFirstChunkVariance": {"p05": 1.15108753240003, "q25": 1.65522780499998, "median": 2.20804692050001, "q75": 3.25433961150017, "p95": 7.05532667365002}, "performanceByPromptType": {"long": {"medianOutputSpeed": 38.4428911419889, "medianTimeToFirstChunk": 2.20804692050001, "medianTimeToFirstAnswerToken": 2.20804692050001, "medianEndToEndResponseTime": 15.214352771775578}}, "endToEndResponseTime": {"input": 2.20804692050001, "reasoning": 0, "answer": 13.006305851275568, "total": 15.214352771775578}, "timeToFirstAnswerToken": {"input": 2.20804692050001, "reasoning": 0, "total": 2.20804692050001}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "43da3718-3d6e-40dd-901a-05664179ff7f", "slug": "mistral-small-3-2", "name": "Mistral Small 3.2", "shortName": "Mistral Small 3.2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-20", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-small-3-2", "name": "Mistral Small 3.2"}, "deprecated": true, "deprecatedTo": "mistral-small-4", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 24, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://choosealicense.com/licenses/apache-2.0/", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506", "microevalsEnabled": false, "intelligenceIndex": 6.96351219722855, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 6.475609740133939, "strategyAndOps": 4.063087172282996, "legal": 8.384923944863704, "engineering": 10.026431881371641, "economics": 11.677507723200492}, "omniscience": -50.5833333333333, "omniscienceBreakdown": {"accuracy": 0.14833333333333334, "hallucinationRate": 0.7681017612524462}, "gdpPdfAllPass": 0, "gdpval": 29.2, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.295321637426901, "tauBanking": 0.0618556701030928, "terminalbenchHard": 0.0681818181818182, "terminalBench21": 0.0561797752808989, "terminalBench40": 0, "scicode": 0.28587962962963, "lcr": 0.203333333333333, "ifbench": 0.33469387755102, "hle": 0.0430954587581094, "gpqa": 0.505050505050505, "critpt": 0, "apexAgents": null, "mmmuPro": 0.479768786127168, "livecodebench": 0.275132275132275, "aime25": 0.27, "analystAgent": null, "automationBenchPartialScore": 0.002854023922677291, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15000000000000002, "price1mBlended7To2To1": 0.12000000000000002, "price1mBlended0To1To1": 0.2, "price1mBlended100To1To1": 0.10196078431372549, "price1mBlended0To100To1": 0.10198019801980199, "intelligenceIndexTimePerTask": 46.093524950454174, "intelligenceIndexCost": {"total": 162.6755776, "input": 159.94906989999998, "nonCacheInput": 1.3907109000000002, "cacheRead": 0, "cacheWrite": 158.558359, "output": 2.7265077, "reasoning": 0, "answer": 2.7265077}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.1457840183584391, "input": 0.14363995148651176, "nonCacheInput": 0.0007480820514164351, "cacheRead": 0, "cacheWrite": 0.14289186943509535, "output": 0.0021440668719272986, "reasoning": 0, "answer": 0.0021440668719272986}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.09067681104395604}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.044771471863636364}, {"slug": "automationbench-aa", "weightedCostPerTask": 8.988414764079149e-05}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.009395417878787879}, {"slug": "scicode", "weightedCostPerTask": 3.584958333333333e-05}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 1.5907585727525488e-05}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00021143530000000002}, {"slug": "critpt", "weightedCostPerTask": 0.00010632114285714285}, {"slug": "omniscience", "weightedCostPerTask": 2.4067124999999998e-06}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00047851310000000005}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1599490699, "output": 9088359, "answer": 9088359, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 7146.8895730909935, "output": 7146.8895730909935}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "rubricPassRate": 0.034623217922606926, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 55.0105987, "timescaleData": {"medianOutputSpeed": 151.848105310117, "medianTimeToFirstChunk": 0.793325526999923}, "outputSpeedVariance": {"p05": 84.9706707401573, "q25": 134.388298592496, "median": 151.848105310117, "q75": 180.562689968106, "p95": 208.919849845032}, "timeToFirstChunkVariance": {"p05": 0.657377483399989, "q25": 0.70083809274999, "median": 0.793325526999923, "q75": 0.947997536999992, "p95": 1.68312728890004}, "performanceByPromptType": {"long": {"medianOutputSpeed": 151.848105310117, "medianTimeToFirstChunk": 0.793325526999923, "medianTimeToFirstAnswerToken": 0.793325526999923, "medianEndToEndResponseTime": 4.086089694052635}}, "endToEndResponseTime": {"input": 0.793325526999923, "reasoning": 0, "answer": 3.2927641670527126, "total": 4.086089694052635}, "timeToFirstAnswerToken": {"input": 0.793325526999923, "reasoning": 0, "total": 0.793325526999923}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 2, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "43fc5506-c5ed-4dee-9b85-962bf7ae3986", "slug": "deepseek-v3", "name": "DeepSeek V3 (Dec '24)", "shortName": "DeepSeek V3 (Dec)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-26", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v3", "name": "DeepSeek V3 (Dec '24)"}, "deprecated": true, "deprecatedTo": "deepseek-v3-1", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 671, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "DEEPSEEK LICENSE AGREEMENT", "licenseUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3/blob/main/LICENSE-MODEL", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3", "microevalsEnabled": false, "intelligenceIndex": 8.48686760841828, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 8.613998393297756, "strategyAndOps": 7.411258474359686, "legal": 10.166672099900032, "engineering": 10.515000000000002, "economics": 12.264166666666664}, "omniscience": -41.65, "omniscienceBreakdown": {"accuracy": 0.2545, "hallucinationRate": 0.9000670690811536}, "gdpPdfAllPass": 0.008, "gdpval": 183.26, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.228070175438596, "tauBanking": 0.0474226804123711, "terminalbenchHard": 0.0681818181818182, "terminalBench21": 0.168539325842697, "terminalBench40": 0, "scicode": 0.357638888888889, "lcr": 0.293333333333333, "ifbench": 0.347619047619048, "hle": 0.029, "gpqa": 0.556565656565657, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.358730158730159, "aime25": 0.26, "analystAgent": null, "automationBenchPartialScore": 0.005829479653698352, "price1mInputTokens": 0.32, "price1mOutputTokens": 0.89, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.4625, "price1mBlended7To2To1": 0.37700000000000006, "price1mBlended0To1To1": 0.605, "price1mBlended100To1To1": 0.3255882352941177, "price1mBlended0To100To1": 0.32564356435643566, "intelligenceIndexCost": {"total": 25.36593364, "input": 22.04685664, "nonCacheInput": 4.2730816, "cacheRead": 0, "cacheWrite": 17.77377504, "output": 3.319077, "reasoning": 0, "answer": 3.319077}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.019751793975774472, "input": 0.01795602901770688, "nonCacheInput": 0.002230295052421025, "cacheRead": 0, "cacheWrite": 0.015725733965285857, "output": 0.0017957649580675917, "reasoning": 0, "answer": 0.0017957649580675917}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.00831913064835165}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0007183640363636364}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0006291928622526637}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.007588902515151515}, {"slug": "scicode", "weightedCostPerTask": 0.00010633126388888891}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 4.969247312326228e-05}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0005805560899999999}, {"slug": "critpt", "weightedCostPerTask": 0.00023348065714285716}, {"slug": "omniscience", "weightedCostPerTask": 7.564384499999999e-06}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0015185790450000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 68896427, "output": 3729300, "answer": 3729300, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 2017.7134360310017, "output": 2017.7134360310017}, "briefcaseBreakdown": {"overall": {"elo": 99.91, "lower95ci": 87.6, "upper95ci": 111.12}, "rubricPassRate": 0.047474747474747475, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 21.66, "lower95ci": 0, "upper95ci": 43.44}}, "briefcaseTotalCost": 5.04693926, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 3, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "441734a9-8901-4850-9bae-b474c370291f", "slug": "kimi-k2", "name": "Kimi K2", "shortName": "Kimi K2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-11", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "kimi-k2", "name": "Kimi K2"}, "deprecated": true, "deprecatedTo": "kimi-k2-0905", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1000, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "Modified MIT License", "licenseUrl": "https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-K2-Instruct", "microevalsEnabled": false, "intelligenceIndex": 12.7154830817268, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -28.3166666666667, "omniscienceBreakdown": {"accuracy": 0.2735, "hallucinationRate": 0.7662307868777243}, "gdpval": null, "itBenchSre": null, "tau2": 0.611111111111111, "tauBanking": null, "terminalbenchHard": 0.159090909090909, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.53, "ifbench": 0.414965986394558, "hle": 0.0741427247451344, "gpqa": 0.765656565656566, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.555555555555556, "aime25": 0.57, "analystAgent": null, "price1mInputTokens": 0.57, "price1mOutputTokens": 2.3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.0025, "price1mBlended7To2To1": 0.743, "price1mBlended0To1To1": 1.4349999999999998, "price1mBlended100To1To1": 0.5869607843137254, "price1mBlended0To100To1": 0.587128712871287, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 4, "transparencyMethodology": 3, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 39.86203942042, "medianTimeToFirstChunk": 1.64962737449997}, "outputSpeedVariance": {"p05": 29.9540414254116, "q25": 38.1705562661127, "median": 39.86203942042, "q75": 40.9482742120873, "p95": 42.1515363795322}, "timeToFirstChunkVariance": {"p05": 1.19169277880001, "q25": 1.42253494475, "median": 1.64962737449997, "q75": 2.64816719975, "p95": 4.81604627625002}, "performanceByPromptType": {"long": {"medianOutputSpeed": 39.86203942042, "medianTimeToFirstChunk": 1.64962737449997, "medianTimeToFirstAnswerToken": 1.64962737449997, "medianEndToEndResponseTime": 14.19288926651111}}, "endToEndResponseTime": {"input": 1.64962737449997, "reasoning": 0, "answer": 12.54326189201114, "total": 14.19288926651111}, "timeToFirstAnswerToken": {"input": 1.64962737449997, "reasoning": 0, "total": 1.64962737449997}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "444cdb1e-bab8-42cd-938c-b2d7a93e2da1", "slug": "deepseek-r1-distill-qwen-1-5b", "name": "DeepSeek R1 Distill Qwen 1.5B", "shortName": "DeepSeek R1 Distill Qwen 1.5B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-r1-distill-qwen-1-5b", "name": "DeepSeek R1 Distill Qwen 1.5B"}, "deprecated": true, "deprecatedTo": "deepseek-v3-0324", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1.5, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "microevalsEnabled": false, "intelligenceIndex": 5.51106155192649, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.0166666666666667, "ifbench": 0.131972789115646, "hle": 0.0308, "gpqa": 0.097979797979798, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0698412698412698, "aime25": 0.22, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "44b19b51-5367-4ef9-a2ff-2f90b89a0867", "slug": "exaone-4-0-32b-reasoning", "name": "EXAONE 4.0 32B (Reasoning)", "shortName": "EXAONE 4.0 32B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-15", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "exaone-4-0-32b", "name": "EXAONE 4.0 32B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 32, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131000, "licenseName": "EXAONE AI Model License Agreement 1.2 - NC", "licenseUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B", "microevalsEnabled": false, "intelligenceIndex": 8.17836973273723, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -60.0666666666667, "omniscienceBreakdown": {"accuracy": 0.13866666666666666, "hallucinationRate": 0.858359133126935}, "gdpval": null, "itBenchSre": null, "tau2": 0.172514619883041, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.363265306122449, "hle": 0.114457831325301, "gpqa": 0.739393939393939, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.747089947089947, "aime25": 0.8, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 3, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "45157c16-fcbb-4110-b20f-7bca754b6554", "slug": "lg", "name": "LG AI Research", "logo": "/img/logos/lg_small.png", "color": "#df3b8a", "country": "kr", "url": "https://www.lgresearch.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "44db6283-aa82-4799-af4a-679fe0530845", "slug": "solar-pro-2", "name": "Solar Pro 2 (Non-reasoning)", "shortName": "Solar Pro 2 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-09", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "solar-pro-2", "name": "Solar Pro 2"}, "deprecated": true, "deprecatedTo": "solar-pro-3", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 65536, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.99835187746333, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -62.05, "omniscienceBreakdown": {"accuracy": 0.1605, "hallucinationRate": 0.9303156640857654}, "gdpval": null, "itBenchSre": null, "tau2": 0.318713450292398, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.337414965986395, "hle": 0.0370713623725672, "gpqa": 0.560606060606061, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.424338624338624, "aime25": 0.3, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "64ff7f06-c6fb-42ea-ba24-9cd103ab2d61", "slug": "upstage", "name": "Upstage", "logo": "/img/logos/upstage_small.svg", "color": "#7c59f5", "country": "kr", "url": "https://www.upstage.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4559e9f0-8aad-4681-89fb-68cb915e0f16", "slug": "qwen3-14b-instruct-reasoning", "name": "Qwen3 14B (Reasoning)", "shortName": "Qwen3 14B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-14b-instruct", "name": "Qwen3 14B"}, "deprecated": true, "deprecatedTo": "qwen3-30b-a3b-2507-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 14.8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-14B", "microevalsEnabled": false, "intelligenceIndex": 6.38695054929445, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 6.570724770642203, "strategyAndOps": 3.9401474356281763, "legal": 7.54620837867247, "engineering": 11.634500000000001, "economics": 11.543}, "omniscience": -48.95, "omniscienceBreakdown": {"accuracy": 0.15283333333333332, "hallucinationRate": 0.7582136533543183}, "gdpPdfAllPass": 0.012, "gdpval": 187.72, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.345029239766082, "tauBanking": 0.0556701030927835, "terminalbenchHard": 0.0378787878787879, "terminalBench21": 0.048689138576779, "terminalBench40": 0, "scicode": 0.306712962962963, "lcr": 0, "ifbench": 0.405442176870748, "hle": 0.0453, "gpqa": 0.604040404040404, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.522751322751323, "aime25": 0.556666666666667, "analystAgent": null, "automationBenchPartialScore": 0.0019111706206154657, "price1mInputTokens": 0.35, "price1mOutputTokens": 4.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.3125, "price1mBlended7To2To1": 0.735, "price1mBlended0To1To1": 2.275, "price1mBlended100To1To1": 0.38774509803921575, "price1mBlended0To100To1": 0.38811881188118813, "briefcaseBreakdown": {"overall": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "rubricPassRate": 0.02889576883384933, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 10.641456699999999, "timescaleData": {"medianOutputSpeed": 61.8394873221504, "medianTimeToFirstChunk": 2.73255001850001}, "outputSpeedVariance": {"p05": 55.2188192990043, "q25": 58.4205928866488, "median": 61.8394873221504, "q75": 63.7290250822893, "p95": 64.9441699935219}, "timeToFirstChunkVariance": {"p05": 2.62963685954991, "q25": 2.66339196974994, "median": 2.73255001850001, "q75": 2.87598054350002, "p95": 3.03465676335014}, "performanceByPromptType": {"long": {"medianOutputSpeed": 61.8394873221504, "medianTimeToFirstChunk": 2.73255001850001, "medianTimeToFirstAnswerToken": 35.07434466471171, "medianEndToEndResponseTime": 43.159793326264634}}, "endToEndResponseTime": {"input": 2.73255001850001, "reasoning": 32.3417946462117, "answer": 8.085448661552926, "total": 43.159793326264634}, "timeToFirstAnswerToken": {"input": 2.73255001850001, "reasoning": 32.3417946462117, "total": 35.07434466471171}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "45790612-02e3-4c42-b5bd-cd7ed2ea1f2f", "slug": "sarvam-105b", "name": "Sarvam 105B (high)", "shortName": "Sarvam 105B (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-06", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "sarvam-105b", "name": "Sarvam 105B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 106, "inferenceParametersActiveBillions": 10.3, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/sarvamai/sarvam-105b", "microevalsEnabled": false, "intelligenceIndex": 8.7905508357489, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -59.3833333333333, "omniscienceBreakdown": {"accuracy": 0.176, "hallucinationRate": 0.9342637540453075}, "gdpval": null, "itBenchSre": null, "tau2": 0.467836257309941, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.343537414965986, "hle": 0.110287303058387, "gpqa": 0.738383838383838, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.042, "price1mOutputTokens": 0.17, "cacheHitPrice": 0.026, "cacheHitDiscountPercent": 0.38095238095238104, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.07400000000000001, "price1mBlended7To2To1": 0.04360000000000001, "price1mBlended0To1To1": 0.10600000000000001, "price1mBlended100To1To1": 0.02756862745098039, "price1mBlended0To100To1": 0.04326732673267327, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "20273002-dc38-4ebc-8377-8f432aec9e7e", "slug": "sarvam", "name": "Sarvam", "logo": "/img/logos/sarvam.svg", "color": "#807D77", "country": "in", "url": "https://www.sarvam.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "45c87531-2d57-48e0-8012-202cd636189e", "slug": "llama-3-1-instruct-405b", "name": "Llama 3.1 Instruct 405B", "shortName": "Llama 3.1 405B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-07-23", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-1-instruct-405b", "name": "Llama 3.1 Instruct 405B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 405, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.1 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Meta-Llama-3.1-405B", "microevalsEnabled": false, "intelligenceIndex": 7.2893092121128, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -17.1, "omniscienceBreakdown": {"accuracy": 0.23183333333333334, "hallucinationRate": 0.5244087654588848}, "gdpval": null, "itBenchSre": null, "tau2": 0.190058479532164, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.253333333333333, "ifbench": 0.390476190476191, "hle": 0.0398, "gpqa": 0.515151515151515, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.304761904761905, "aime25": 0.03, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "466aecdb-3d96-4191-bc52-b3366db38851", "slug": "llama-3-1-instruct-70b", "name": "Llama 3.1 Instruct 70B", "shortName": "Llama 3.1 70B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-07-23", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-1-instruct-70b", "name": "Llama 3.1 Instruct 70B"}, "deprecated": true, "deprecatedTo": "llama-3-3-instruct-70b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.1 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Meta-Llama-3.1-70B", "microevalsEnabled": false, "intelligenceIndex": 6.60404957812628, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -43.1, "omniscienceBreakdown": {"accuracy": 0.197, "hallucinationRate": 0.7820672478206725}, "gdpval": null, "itBenchSre": null, "tau2": 0.152046783625731, "tauBanking": null, "terminalbenchHard": 0.0303030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.34421768707483, "hle": 0.0447, "gpqa": 0.409090909090909, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.231746031746032, "aime25": 0.04, "analystAgent": null, "price1mInputTokens": 0.56, "price1mOutputTokens": 0.56, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.56, "price1mBlended7To2To1": 0.5600000000000002, "price1mBlended0To1To1": 0.56, "price1mBlended100To1To1": 0.5600000000000002, "price1mBlended0To100To1": 0.56, "timescaleData": {"medianOutputSpeed": 69.958760158121, "medianTimeToFirstChunk": 1.49800963050001}, "outputSpeedVariance": {"p05": 18.1298676209875, "q25": 38.3881017859296, "median": 69.958760158121, "q75": 105.541064017917, "p95": 145.143064946991}, "timeToFirstChunkVariance": {"p05": 1.16234134299992, "q25": 1.25548832399999, "median": 1.49800963050001, "q75": 1.88247710625, "p95": 29.40332797025}, "performanceByPromptType": {"long": {"medianOutputSpeed": 69.958760158121, "medianTimeToFirstChunk": 1.49800963050001, "medianTimeToFirstAnswerToken": 1.49800963050001, "medianEndToEndResponseTime": 8.645077401139433}}, "endToEndResponseTime": {"input": 1.49800963050001, "reasoning": 0, "answer": 7.147067770639424, "total": 8.645077401139433}, "timeToFirstAnswerToken": {"input": 1.49800963050001, "reasoning": 0, "total": 1.49800963050001}, "performanceDataSource": {"type": "median"}, "hostModelCount": 4, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "46d8315e-1630-463f-ab62-84185fa0faab", "slug": "qwen3-5-35b-a3b", "name": "Qwen3.5 35B A3B (Reasoning)", "shortName": "Qwen3.5 35B A3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-5-35b-a3b", "name": "Qwen3.5 35B A3B"}, "deprecated": true, "deprecatedTo": "qwen3-6-35b-a3b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 36, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-35B-A3B", "microevalsEnabled": false, "intelligenceIndex": 19.3295292724173, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -48.1, "omniscienceBreakdown": {"accuracy": 0.20133333333333334, "hallucinationRate": 0.8543405676126878}, "gdpval": null, "itBenchSre": 0.215160075329567, "tau2": 0.891812865497076, "tauBanking": null, "terminalbenchHard": 0.265151515151515, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.72, "ifbench": 0.725170068027211, "hle": 0.210379981464319, "gpqa": 0.845454545454545, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": 0.726589595375723, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.25, "price1mOutputTokens": 2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.256, "price1mBlended0To3To1": 0.6875, "price1mBlended7To2To1": 0.425, "price1mBlended0To1To1": 1.125, "price1mBlended100To1To1": 0.26715686274509803, "price1mBlended0To100To1": 0.26732673267326734, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 149.369441370379, "medianTimeToFirstChunk": 2.11098884199998}, "outputSpeedVariance": {"p05": 127.654393135364, "q25": 139.699706745346, "median": 149.369441370379, "q75": 159.625706803266, "p95": 172.457865339918}, "timeToFirstChunkVariance": {"p05": 1.97571176229999, "q25": 2.01800944400002, "median": 2.11098884199998, "q75": 2.35120637249997, "p95": 2.5642978994}, "performanceByPromptType": {"long": {"medianOutputSpeed": 149.369441370379, "medianTimeToFirstChunk": 2.11098884199998, "medianTimeToFirstAnswerToken": 15.500608443246033, "medianEndToEndResponseTime": 18.848013343557547}}, "endToEndResponseTime": {"input": 2.11098884199998, "reasoning": 13.389619601246054, "answer": 3.3474049003115134, "total": 18.848013343557547}, "timeToFirstAnswerToken": {"input": 2.11098884199998, "reasoning": 13.389619601246054, "total": 15.500608443246033}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 6, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4764d31d-f4af-4297-8bd1-e993f26bcb64", "slug": "mimo-v2-5-pro-non-reasoning", "name": "MiMo-V2.5-Pro (Non-reasoning)", "shortName": "MiMo-V2.5-Pro (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-22", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mimo-v2-5-pro", "name": "MiMo-V2.5-Pro"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1023, "inferenceParametersActiveBillions": 41.7, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro", "microevalsEnabled": false, "intelligenceIndex": 18.2900328799708, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -37.8, "omniscienceBreakdown": {"accuracy": 0.2718333333333333, "hallucinationRate": 0.8924238956282903}, "gdpval": null, "itBenchSre": null, "tau2": 0.725146198830409, "tauBanking": null, "terminalbenchHard": 0.356060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.416666666666667, "ifbench": 0.427210884353741, "hle": 0.147822057460612, "gpqa": 0.761616161616162, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.435, "price1mOutputTokens": 0.87, "cacheHitPrice": 0.0036, "cacheHitDiscountPercent": 0.9917241379310345, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.54375, "price1mBlended7To2To1": 0.17652, "price1mBlended0To1To1": 0.6525, "price1mBlended100To1To1": 0.016323529411764705, "price1mBlended0To100To1": 0.4393069306930693, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 49.1900574612072, "medianTimeToFirstChunk": 4.40462807199998}, "outputSpeedVariance": {"p05": 24.4435936279359, "q25": 36.0771067156995, "median": 49.1900574612072, "q75": 55.6925780405445, "p95": 73.3904844666469}, "timeToFirstChunkVariance": {"p05": 2.45113250409991, "q25": 2.95790562250008, "median": 4.40462807199998, "q75": 6.10567277600002, "p95": 64.5810926914999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 46.4500673103666, "medianTimeToFirstChunk": 4.256590771, "medianTimeToFirstAnswerToken": 4.256590771, "medianEndToEndResponseTime": 15.020837820614314}, "long": {"medianOutputSpeed": 49.1900574612072, "medianTimeToFirstChunk": 4.40462807199998, "medianTimeToFirstAnswerToken": 4.40462807199998, "medianEndToEndResponseTime": 14.56928381354522}, "hundredK": {"medianOutputSpeed": 41.453889336721, "medianTimeToFirstChunk": 45.5672285515, "medianTimeToFirstAnswerToken": 45.5672285515, "medianEndToEndResponseTime": 57.62882296399548}, "mediumParallel": {"medianOutputSpeed": 45.1353005889118, "medianTimeToFirstChunk": 4.02831310900001, "medianTimeToFirstAnswerToken": 4.02831310900001, "medianEndToEndResponseTime": 15.106116812002996}}, "endToEndResponseTime": {"input": 4.40462807199998, "reasoning": 0, "answer": 10.16465574154524, "total": 14.56928381354522}, "timeToFirstAnswerToken": {"input": 4.40462807199998, "reasoning": 0, "total": 4.40462807199998}, "performanceDataSource": {"type": "firstParty", "providerName": "Xiaomi"}, "hostModelCount": 4, "creator": {"id": "5147c8b4-61d5-4070-9324-8adf8aa144c2", "slug": "xiaomi", "name": "Xiaomi", "logo": "/img/logos/xiaomi_small.svg", "color": "#ff6900", "country": "cn", "url": "https://huggingface.co/XiaomiMiMo"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "47b7df55-5804-40de-ba11-317de786710a", "slug": "ring-flash-2-0", "name": "Ring-flash-2.0", "shortName": "Ring-flash-2.0", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "ring-flash-2-0", "name": "Ring-flash-2.0"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 103, "inferenceParametersActiveBillions": 6.1, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ring-flash-2.0", "microevalsEnabled": false, "intelligenceIndex": 7.15340447175535, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -58.6166666666667, "omniscienceBreakdown": {"accuracy": 0.1655, "hallucinationRate": 0.9007389654483723}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.0757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.21, "ifbench": 0.43265306122449, "hle": 0.0963855421686747, "gpqa": 0.725252525252525, "critpt": 0.00277551020408163, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.627513227513227, "aime25": 0.836666666666667, "analystAgent": null, "price1mInputTokens": 0.14, "price1mOutputTokens": 0.57, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.2475, "price1mBlended7To2To1": 0.183, "price1mBlended0To1To1": 0.355, "price1mBlended100To1To1": 0.14421568627450984, "price1mBlended0To100To1": 0.14425742574257427, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "48194e0f-8226-4c57-8cb2-2a0fb68a84c9", "slug": "lfm2-5-1-2b-instruct", "name": "LFM2.5-1.2B-Instruct", "shortName": "LFM2.5-1.2B-Instruct", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-05", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "lfm2-5-1-2b-instruct", "name": "LFM2.5-1.2B-Instruct"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1.17, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "lfm 1.0", "licenseUrl": "https://huggingface.co/LiquidAI/LFM2-8B-A1B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 5.20951181661378, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -72.1, "omniscienceBreakdown": {"accuracy": 0.07016666666666667, "hallucinationRate": 0.8508693314214016}, "gdpval": null, "itBenchSre": null, "tau2": 0.108187134502924, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.438095238095238, "hle": 0.067191844300278, "gpqa": 0.326262626262626, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5b1886c4-43ba-4007-b840-9d21a2b7d42c", "slug": "liquidai", "name": "Liquid AI", "logo": "/img/logos/liquidai_small.svg", "color": "#000000", "country": "us", "url": "https://www.liquid.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "48e50f00-1fd1-4acc-b337-61078aa341e6", "slug": "gpt-5", "name": "GPT-5 (high)", "shortName": "GPT-5 (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-09-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5", "name": "GPT-5"}, "deprecated": true, "deprecatedTo": "gpt-5-1", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 22.9827995216189, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -8.73333333333333, "omniscienceBreakdown": {"accuracy": 0.4031666666666667, "hallucinationRate": 0.8218374755654845}, "gdpval": 1014.92, "gdpvalNormalized": 0.25745999999999997, "itBenchSre": null, "tau2": 0.847953216374269, "tauBanking": 0.220618556701031, "terminalbenchHard": 0.325757575757576, "terminalBench21": 0.352059925093633, "terminalBench40": null, "scicode": null, "lcr": 0.782, "ifbench": 0.730612244897959, "hle": 0.28498609823911, "gpqa": 0.853535353535353, "critpt": 0.0571428571428571, "apexAgents": null, "mmmuPro": 0.742196531791907, "livecodebench": 0.845502645502646, "aime25": 0.943333333333333, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.788, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 1.3375, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.3366336633663367, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 82.2032280639012, "medianTimeToFirstChunk": 65.0932860925001}, "outputSpeedVariance": {"p05": 54.7422371032933, "q25": 69.7537928459958, "median": 82.2032280639012, "q75": 117.037986492351, "p95": 137.221859248731}, "timeToFirstChunkVariance": {"p05": 31.9497435998, "q25": 46.5672383149999, "median": 65.0932860925001, "q75": 121.54043075425, "p95": 293.8640419593}, "performanceByPromptType": {"long": {"medianOutputSpeed": 82.2032280639012, "medianTimeToFirstChunk": 65.0932860925001, "medianTimeToFirstAnswerToken": 65.0932860925001, "medianEndToEndResponseTime": 71.17577228892199}}, "endToEndResponseTime": {"input": 65.0932860925001, "reasoning": 0, "answer": 6.082486196421896, "total": 71.17577228892199}, "timeToFirstAnswerToken": {"input": 65.0932860925001, "reasoning": 0, "total": 65.0932860925001}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4928e950-7f37-4475-b0dc-c5bad781a321", "slug": "mistral-large-3", "name": "Mistral Large 3", "shortName": "Mistral Large 3", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-large-3", "name": "Mistral Large 3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 675, "inferenceParametersActiveBillions": 41, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-Large-3-675B-Instruct-2512", "microevalsEnabled": true, "intelligenceIndex": 9.70803812860467, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 9.529595869977017, "strategyAndOps": 8.265185224106029, "legal": 11.597359764806972, "engineering": 12.372529240037071, "economics": 13.594622393419833}, "omniscience": -39.5666666666667, "omniscienceBreakdown": {"accuracy": 0.2495, "hallucinationRate": 0.8596491228070176}, "gdpPdfAllPass": 0.012, "gdpval": 588.39, "gdpvalNormalized": 0.04419499999999999, "itBenchSre": null, "tau2": 0.245614035087719, "tauBanking": 0.0577319587628866, "terminalbenchHard": 0.159090909090909, "terminalBench21": 0.119850187265918, "terminalBench40": 0, "scicode": 0.365740740740741, "lcr": 0.36, "ifbench": 0.361904761904762, "hle": 0.0417052826691381, "gpqa": 0.67979797979798, "critpt": 0, "apexAgents": null, "mmmuPro": 0.556647398843931, "livecodebench": 0.464550264550264, "aime25": 0.38, "analystAgent": null, "automationBenchPartialScore": 0.014974701708193462, "price1mInputTokens": 0.5, "price1mOutputTokens": 1.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.668, "price1mBlended0To3To1": 0.75, "price1mBlended7To2To1": 0.6, "price1mBlended0To1To1": 1, "price1mBlended100To1To1": 0.5098039215686274, "price1mBlended0To100To1": 0.5099009900990099, "intelligenceIndexTimePerTask": 69.34992811040337, "intelligenceIndexCost": {"total": 129.936832, "input": 115.2600985, "nonCacheInput": 8.736897, "cacheRead": 0, "cacheWrite": 106.5232015, "output": 14.676733500000001, "reasoning": 0, "answer": 14.676733500000001}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.10436844417697419, "input": 0.09601878053182233, "nonCacheInput": 0.00554880530410102, "cacheRead": 0, "cacheWrite": 0.0904699752277213, "output": 0.008349663645151875, "reasoning": 0, "answer": 0.008349663645151875}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.02879430741758242}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.010624625}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0029654771308980214}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.05544980227272728}, {"slug": "scicode", "weightedCostPerTask": 0.00019618020833333334}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00019588744207599628}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0028753405000000003}, {"slug": "critpt", "weightedCostPerTask": 0.0008778821428571427}, {"slug": "omniscience", "weightedCostPerTask": 1.2391562499999999e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0023765505}]}, "canonicalIntelligenceIndexTokenCount": {"input": 230520197, "output": 9784489, "answer": 9784489, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 5566.44243010125, "output": 5566.44243010125}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 245.84, "lower95ci": 236.76, "upper95ci": 254.53}, "rubricPassRate": 0.056179775280898875, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 221.65, "lower95ci": 204.17, "upper95ci": 239.71}}, "briefcaseTotalCost": 17.468546500000002, "timescaleData": {"medianOutputSpeed": 78.1157485120034, "medianTimeToFirstChunk": 1.05598212700005}, "outputSpeedVariance": {"p05": 54.0708680219846, "q25": 66.2874136989895, "median": 78.1157485120034, "q75": 86.1885003561897, "p95": 102.304152735862}, "timeToFirstChunkVariance": {"p05": 0.950534782850016, "q25": 1.01440743625006, "median": 1.05598212700005, "q75": 1.12113851000004, "p95": 2.1674605214998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 77.0000808163661, "medianTimeToFirstChunk": 0.950704230500005, "medianTimeToFirstAnswerToken": 0.950704230500005, "medianEndToEndResponseTime": 7.444203908668223}, "long": {"medianOutputSpeed": 78.1157485120034, "medianTimeToFirstChunk": 1.05598212700005, "medianTimeToFirstAnswerToken": 1.05598212700005, "medianEndToEndResponseTime": 7.456740098655011}, "hundredK": {"medianOutputSpeed": 58.2168636627574, "medianTimeToFirstChunk": 9.72931289349998, "medianTimeToFirstAnswerToken": 9.72931289349998, "medianEndToEndResponseTime": 18.31788961409479}, "mediumParallel": {"medianOutputSpeed": 80.6250810456398, "medianTimeToFirstChunk": 0.746573663500044, "medianTimeToFirstAnswerToken": 0.746573663500044, "medianEndToEndResponseTime": 6.948117817197859}}, "endToEndResponseTime": {"input": 1.05598212700005, "reasoning": 0, "answer": 6.400757971654961, "total": 7.456740098655011}, "timeToFirstAnswerToken": {"input": 1.05598212700005, "reasoning": 0, "total": 1.05598212700005}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 3, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "493f6a1e-7717-4e98-9d6f-548b92c4702d", "slug": "gpt-5-4-non-reasoning", "name": "GPT-5.4 (Non-reasoning)", "shortName": "GPT-5.4 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-05", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-5-4", "name": "GPT-5.4"}, "deprecated": true, "deprecatedTo": "gpt-5-5-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1050000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 18.1597022799287, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -15.6666666666667, "omniscienceBreakdown": {"accuracy": 0.37383333333333335, "hallucinationRate": 0.8472185254192175}, "gdpval": null, "itBenchSre": null, "tau2": 0.359649122807018, "tauBanking": null, "terminalbenchHard": 0.378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.583333333333333, "ifbench": 0.484353741496599, "hle": 0.112604263206673, "gpqa": 0.748484848484848, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": 0.705780346820809, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 2.5, "price1mOutputTokens": 15, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 1.91, "price1mBlended0To3To1": 5.625, "price1mBlended7To2To1": 2.175, "price1mBlended0To1To1": 8.75, "price1mBlended100To1To1": 0.4166666666666667, "price1mBlended0To100To1": 2.623762376237624, "timescaleData": {"medianOutputSpeed": 101.401342927653, "medianTimeToFirstChunk": 0.829912031000007}, "outputSpeedVariance": {"p05": 61.0334963352971, "q25": 83.745465791721, "median": 101.401342927653, "q75": 117.34434844872, "p95": 155.345602874882}, "timeToFirstChunkVariance": {"p05": 0.712686220500046, "q25": 0.798692924750042, "median": 0.829912031000007, "q75": 0.90432556250002, "p95": 1.12139425380003}, "performanceByPromptType": {"long": {"medianOutputSpeed": 101.401342927653, "medianTimeToFirstChunk": 0.829912031000007, "medianTimeToFirstAnswerToken": 0.829912031000007, "medianEndToEndResponseTime": 5.7608131962512}}, "endToEndResponseTime": {"input": 0.829912031000007, "reasoning": 0, "answer": 4.930901165251193, "total": 5.7608131962512}, "timeToFirstAnswerToken": {"input": 0.829912031000007, "reasoning": 0, "total": 0.829912031000007}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "498862c3-f9ac-49d2-852f-16a02bb0c38f", "slug": "gpt-5-2", "name": "GPT-5.2 (xhigh)", "shortName": "GPT-5.2 (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-11", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-2", "name": "GPT-5.2"}, "deprecated": true, "deprecatedTo": "gpt-5-4", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 30.448181916806, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -0.883333333333333, "omniscienceBreakdown": {"accuracy": 0.44316666666666665, "hallucinationRate": 0.8117330140676444}, "gdpval": null, "itBenchSre": null, "tau2": 0.847953216374269, "tauBanking": null, "terminalbenchHard": 0.46969696969697, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.826666666666667, "ifbench": 0.754421768707483, "hle": 0.376737720111214, "gpqa": 0.903030303030303, "critpt": 0.115510204081633, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.888888888888889, "aime25": 0.99, "analystAgent": null, "price1mInputTokens": 1.75, "price1mOutputTokens": 14, "cacheHitPrice": 0.175, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 2.15, "price1mBlended0To3To1": 4.8125, "price1mBlended7To2To1": 1.8725, "price1mBlended0To1To1": 7.875, "price1mBlended100To1To1": 0.32598039215686275, "price1mBlended0To100To1": 1.8712871287128714, "timescaleData": {"medianOutputSpeed": 79.5048977847546, "medianTimeToFirstChunk": 82.535192892}, "outputSpeedVariance": {"p05": 55.156258082021, "q25": 63.4425896602947, "median": 79.5048977847546, "q75": 95.8412209479384, "p95": 113.035502575752}, "timeToFirstChunkVariance": {"p05": 21.4852055984, "q25": 48.2812858725001, "median": 82.535192892, "q75": 133.504564254, "p95": 323.530835358}, "performanceByPromptType": {"long": {"medianOutputSpeed": 79.5048977847546, "medianTimeToFirstChunk": 82.535192892, "medianTimeToFirstAnswerToken": 82.535192892, "medianEndToEndResponseTime": 88.82411362432596}}, "endToEndResponseTime": {"input": 82.535192892, "reasoning": 0, "answer": 6.288920732325966, "total": 88.82411362432596}, "timeToFirstAnswerToken": {"input": 82.535192892, "reasoning": 0, "total": 82.535192892}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "49e70a38-4ac1-4659-b490-09b2c7ff21d6", "slug": "apertus-70b-instruct", "name": "Apertus 70B Instruct", "shortName": "Apertus 70B Instruct", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "apertus-70b-instruct", "name": "Apertus 70B Instruct"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 65536, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/swiss-ai/Apertus-70B-Instruct-2509", "microevalsEnabled": false, "intelligenceIndex": 5.11462775284761, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -61.55, "omniscienceBreakdown": {"accuracy": 0.11633333333333333, "hallucinationRate": 0.8281780460203697}, "gdpval": null, "itBenchSre": null, "tau2": 0.128654970760234, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.258503401360544, "hle": 0.0546802594995366, "gpqa": 0.271717171717172, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.82, "price1mOutputTokens": 2.92, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.345, "price1mBlended7To2To1": 1.0299999999999998, "price1mBlended0To1To1": 1.8699999999999999, "price1mBlended100To1To1": 0.8405882352941176, "price1mBlended0To100To1": 0.8407920792079208, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Swiss AI Initiative"}, "hostModelCount": 1, "creator": {"id": "fd857f01-736c-46f7-92f0-09490f4bbc8b", "slug": "swiss-ai-initiative", "name": "Swiss AI Initiative", "logo": "/img/logos/swiss-ai-initiative_small.png", "color": "#bee9fa", "country": "ch", "url": "https://www.swiss-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "49fd01f9-887d-4479-b8ce-771a81ecef4e", "slug": "grok-4-1-fast", "name": "Grok 4.1 Fast (Non-reasoning)", "shortName": "Grok 4.1 Fast (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-19", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "grok-4-1-fast", "name": "Grok 4.1 Fast"}, "deprecated": true, "deprecatedTo": "grok-4-3-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.2849071635465, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -50.8833333333333, "omniscienceBreakdown": {"accuracy": 0.17233333333333334, "hallucinationRate": 0.8229963753523963}, "gdpval": null, "itBenchSre": 0.178907721280603, "tau2": 0.637426900584795, "tauBanking": null, "terminalbenchHard": 0.143939393939394, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.313333333333333, "ifbench": 0.364625850340136, "hle": 0.0509731232622799, "gpqa": 0.637373737373737, "critpt": 0, "apexAgents": null, "mmmuPro": 0.484393063583815, "livecodebench": 0.398941798941799, "aime25": 0.343333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4a845d7b-a52d-43bb-80b7-b58c7a0c155e", "slug": "deepseek-r1-distill-llama-70b", "name": "DeepSeek R1 Distill Llama 70B", "shortName": "DeepSeek R1 Distill Llama 70B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-r1-distill-llama-70b", "name": "DeepSeek R1 Distill Llama 70B"}, "deprecated": true, "deprecatedTo": "deepseek-v3-0324", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.3 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "microevalsEnabled": false, "intelligenceIndex": 7.88824581191087, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -46.3833333333333, "omniscienceBreakdown": {"accuracy": 0.19166666666666668, "hallucinationRate": 0.8109278350515464}, "gdpval": null, "itBenchSre": null, "tau2": 0.219298245614035, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.1, "ifbench": 0.275510204081633, "hle": 0.0513, "gpqa": 0.402020202020202, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.265608465608466, "aime25": 0.536666666666667, "analystAgent": null, "price1mInputTokens": 0.7, "price1mOutputTokens": 1.1, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.7999999999999999, "price1mBlended7To2To1": 0.7399999999999999, "price1mBlended0To1To1": 0.9, "price1mBlended100To1To1": 0.7039215686274509, "price1mBlended0To100To1": 0.7039603960396039, "openness": {"opennessIndex": 36.111111111111114, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 24.4533522422812, "medianTimeToFirstChunk": 0.929216394000036}, "outputSpeedVariance": {"p05": 17.2543800283312, "q25": 20.9069775956214, "median": 24.4533522422812, "q75": 27.1373504242875, "p95": 37.3437877999508}, "timeToFirstChunkVariance": {"p05": 0.694984463799997, "q25": 0.741631291999994, "median": 0.929216394000036, "q75": 1.01844484599997, "p95": 1.3599830122}, "performanceByPromptType": {"long": {"medianOutputSpeed": 24.4533522422812, "medianTimeToFirstChunk": 0.929216394000036, "medianTimeToFirstAnswerToken": 82.71759371683962, "medianEndToEndResponseTime": 103.16468804754952}}, "endToEndResponseTime": {"input": 0.929216394000036, "reasoning": 81.78837732283958, "answer": 20.447094330709895, "total": 103.16468804754952}, "timeToFirstAnswerToken": {"input": 0.929216394000036, "reasoning": 81.78837732283958, "total": 82.71759371683962}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4ae6c88d-9e4a-4850-89fe-18a1c04a66cc", "slug": "qwen3-0.6b-instruct-reasoning", "name": "Qwen3 0.6B (Reasoning)", "shortName": "Qwen3 0.6B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-0.6b-instruct", "name": "Qwen3 0.6B"}, "deprecated": true, "deprecatedTo": "qwen3-5-0-8b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 0.752, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-0.6B", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -78.85, "omniscienceBreakdown": {"accuracy": 0.06333333333333334, "hallucinationRate": 0.9094306049822064}, "gdpval": null, "itBenchSre": null, "tau2": 0.210526315789474, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.233333333333333, "hle": 0.0564, "gpqa": 0.239393939393939, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.120634920634921, "aime25": 0.18, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4bbceacb-cf47-464b-b60f-e1d1fe016d67", "slug": "minimax-m2-7", "name": "MiniMax-M2.7", "shortName": "MiniMax-M2.7", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-18", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2462, "release": {"slug": "minimax-m2-7", "name": "MiniMax-M2.7"}, "deprecated": true, "deprecatedTo": "minimax-m3", "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 230, "inferenceParametersActiveBillions": 10, "sizeClass": "large", "contextWindowTokens": 204800, "licenseName": "NON-COMMERCIAL LICENSE", "licenseUrl": "https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/MiniMaxAI/MiniMax-M2.7", "microevalsEnabled": true, "intelligenceIndex": 23.2171400287271, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 24.20393453879323, "strategyAndOps": 17.074139622672494, "legal": 27.486472319443376, "healthcareAndMedical": 21.68123690275182, "engineering": 26.073676889977488, "economics": 36.46211690994746}, "omniscience": 0.766666666666667, "omniscienceBreakdown": {"accuracy": 0.268, "hallucinationRate": 0.35564663023679416}, "mlcrOverall": 0.0333333333333333, "gdpPdfAllPass": 0.06, "gdpval": 1087.02, "gdpvalNormalized": 0.29351, "itBenchSre": 0.264595103578154, "tau2": 0.847953216374269, "tauBanking": 0.0989690721649484, "terminalbenchHard": 0.393939393939394, "terminalBench21": 0.554307116104869, "terminalBench40": 0, "scicode": 0.501157407407407, "lcr": 0.783333333333333, "ifbench": 0.757142857142857, "hle": 0.29610750695088, "gpqa": 0.873737373737374, "critpt": 0.00571428571428571, "apexAgents": 0.106194690265487, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.1125, "automationBenchPartialScore": 0.044352902503728975, "price1mInputTokens": 0.3, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.06, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": 0.375, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5249999999999999, "price1mBlended7To2To1": 0.22199999999999998, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.07352941176470588, "price1mBlended0To100To1": 0.3089108910891089, "intelligenceIndexTimePerTask": 313.23425642654655, "intelligenceIndexCost": {"total": 235.95731720401176, "input": 125.20977080401175, "nonCacheInput": 4.3825977, "cacheRead": 60.92956943256919, "cacheWrite": 59.897603671442575, "output": 110.7475464, "reasoning": 85.668282, "answer": 25.0792644}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.10166685146353358, "input": 0.0764201384525941, "nonCacheInput": 0.0024833613821654754, "cacheRead": 0.038831575250112105, "cacheWrite": 0.03510520182031652, "output": 0.025246713010939482, "reasoning": 0.011725978083859454, "answer": 0.01352073492708003}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.02759770104848241}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.009405268319362298}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.00567935916912686}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.04638901820657845}, {"slug": "scicode", "weightedCostPerTask": 0.0007995238541666668}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.003021192539388323}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00207891}, {"slug": "critpt", "weightedCostPerTask": 0.004780538571428571}, {"slug": "omniscience", "weightedCostPerTask": 0.00043483315499999995}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0014805066000000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1189828426, "output": 92289622, "answer": 20899387, "reasoning": 71390235}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 9771.648403216212, "answer": 11267.279105900026, "output": 21038.927509116238}, "openness": {"opennessIndex": 22.22222222222222, "modelAvailability": 3, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 715.25, "lower95ci": 706.19, "upper95ci": 724.8}, "rubricPassRate": 0.1414141414141414, "analyticalQuality": {"elo": 553.1, "lower95ci": 535.52, "upper95ci": 571.04}, "presentation": {"elo": 816.73, "lower95ci": 799.97, "upper95ci": 834.11}}, "briefcaseTotalCost": 16.742605302745996, "timescaleData": {"medianOutputSpeed": 63.14228117202, "medianTimeToFirstChunk": 1.69999944100004}, "outputSpeedVariance": {"p05": 37.531411056266, "q25": 57.5734668549088, "median": 63.14228117202, "q75": 81.6564192020528, "p95": 97.3933405381319}, "timeToFirstChunkVariance": {"p05": 1.27899624675002, "q25": 1.38588731274993, "median": 1.69999944100004, "q75": 1.91466276450012, "p95": 2.27323315409998}, "performanceByPromptType": {"long": {"medianOutputSpeed": 63.14228117202, "medianTimeToFirstChunk": 1.69999944100004, "medianTimeToFirstAnswerToken": 40.691305334632794, "medianEndToEndResponseTime": 48.60992960222677}}, "endToEndResponseTime": {"input": 1.69999944100004, "reasoning": 38.991305893632756, "answer": 7.918624267593979, "total": 48.60992960222677}, "timeToFirstAnswerToken": {"input": 1.69999944100004, "reasoning": 38.991305893632756, "total": 40.691305334632794}, "performanceDataSource": {"type": "firstParty", "providerName": "MiniMax"}, "hostModelCount": 4, "creator": {"id": "a31a9071-6144-4dbb-92dc-2e02d653ecea", "slug": "minimax", "name": "MiniMax", "logo": "/img/logos/minimax_small.svg", "color": "#EB3568", "country": "cn", "url": "https://minimaxi.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4c111fbc-d13a-42b4-858c-1dc17fe3c1d1", "slug": "grok-1", "name": "Grok-1", "shortName": "Grok-1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-03-17", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "grok-1", "name": "Grok-1"}, "deprecated": true, "deprecatedTo": "grok-beta", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 314, "inferenceParametersActiveBillions": 78, "sizeClass": "large", "contextWindowTokens": 8192, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/xai-org/grok-1", "microevalsEnabled": false, "intelligenceIndex": 6.33793271707089, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4d6dd5ce-08cb-4e87-9288-1dd2f022aa35", "slug": "doubao-seed-code", "name": "Doubao Seed Code", "shortName": "Doubao Seed Code", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "doubao-seed-code", "name": "Doubao Seed Code"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 16.9467715940932, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -35.2, "omniscienceBreakdown": {"accuracy": 0.24883333333333332, "hallucinationRate": 0.7998668737519414}, "gdpval": null, "itBenchSre": null, "tau2": 0.58187134502924, "tauBanking": null, "terminalbenchHard": 0.265151515151515, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.716666666666667, "ifbench": 0.514285714285714, "hle": 0.140871177015755, "gpqa": 0.763636363636364, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.68092485549133, "livecodebench": 0.766137566137566, "aime25": 0.793333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "2354746c-4775-4a06-b64d-0ba4137785b8", "slug": "bytedance_seed", "name": "ByteDance Seed", "logo": "/img/logos/bytedance_small.svg", "color": "#3c8bff", "country": "cn", "url": ""}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "4dc12a38-b18f-4c43-8e1b-678f8434b5b1", "slug": "gpt-5-1", "name": "GPT-5.1 (high)", "shortName": "GPT-5.1 (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-13", "knowledgeCutoffDate": "2024-09-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5-1", "name": "GPT-5.1"}, "deprecated": true, "deprecatedTo": "gpt-5-2", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 272000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 24.7357540558308, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 5.4, "omniscienceBreakdown": {"accuracy": 0.37716666666666665, "hallucinationRate": 0.5188654000535189}, "gdpval": 929.53, "gdpvalNormalized": 0.21476499999999998, "itBenchSre": null, "tau2": 0.818713450292398, "tauBanking": 0.158762886597938, "terminalbenchHard": 0.454545454545455, "terminalBench21": 0.524344569288389, "terminalBench40": null, "scicode": null, "lcr": 0.8, "ifbench": 0.728571428571429, "hle": 0.28498609823911, "gpqa": 0.872727272727273, "critpt": 0.0485714285714286, "apexAgents": null, "mmmuPro": 0.754913294797688, "livecodebench": 0.867724867724868, "aime25": 0.94, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.788, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 1.3375, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.3366336633663367, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 105.482574205404, "medianTimeToFirstChunk": 43.4228267199999}, "outputSpeedVariance": {"p05": 54.7491867166, "q25": 79.8164496491259, "median": 105.482574205404, "q75": 137.045104785451, "p95": 152.077203057262}, "timeToFirstChunkVariance": {"p05": 16.65980013735, "q25": 20.5552749925, "median": 43.4228267199999, "q75": 73.87572647275, "p95": 236.0654587638}, "performanceByPromptType": {"long": {"medianOutputSpeed": 105.482574205404, "medianTimeToFirstChunk": 43.4228267199999, "medianTimeToFirstAnswerToken": 43.4228267199999, "medianEndToEndResponseTime": 48.16294615457456}}, "endToEndResponseTime": {"input": 43.4228267199999, "reasoning": 0, "answer": 4.740119434574667, "total": 48.16294615457456}, "timeToFirstAnswerToken": {"input": 43.4228267199999, "reasoning": 0, "total": 43.4228267199999}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5016ea75-7b0e-4737-a7e6-1062c6d90fd4", "slug": "gemini-3-5-flash-medium", "name": "Gemini 3.5 Flash (medium)", "shortName": "Gemini 3.5 Flash (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gemini-3-5-flash", "name": "Gemini 3.5 Flash"}, "deprecated": true, "deprecatedTo": "gemini-3-7-flash-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 33.6325871590289, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 20.8166666666667, "omniscienceBreakdown": {"accuracy": 0.5105, "hallucinationRate": 0.6176370446033368}, "gdpval": null, "itBenchSre": null, "tau2": 0.956140350877193, "tauBanking": null, "terminalbenchHard": 0.393939393939394, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.743333333333333, "ifbench": 0.745578231292517, "hle": 0.413345690454124, "gpqa": 0.921212121212121, "critpt": 0.108571428571429, "apexAgents": null, "mmmuPro": 0.838728323699422, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.5, "price1mOutputTokens": 9, "cacheHitPrice": 0.15, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3.375, "price1mBlended7To2To1": 1.3050000000000002, "price1mBlended0To1To1": 5.25, "price1mBlended100To1To1": 0.25, "price1mBlended0To100To1": 1.5742574257425743, "briefcaseBreakdown": {"overall": {"elo": 870.71, "lower95ci": 863.89, "upper95ci": 877.68}, "rubricPassRate": 0.27635619242579323, "analyticalQuality": {"elo": 715.39, "lower95ci": 702.87, "upper95ci": 729.38}, "presentation": {"elo": 900.32, "lower95ci": 887.36, "upper95ci": 912.52}}, "briefcaseTotalCost": 441.38532832554034, "timescaleData": {"medianOutputSpeed": 218.593820740313, "medianTimeToFirstChunk": 14.3351155175001}, "outputSpeedVariance": {"p05": 157.90902758255, "q25": 189.166122497744, "median": 218.593820740313, "q75": 246.095303395593, "p95": 280.496127700768}, "timeToFirstChunkVariance": {"p05": 9.79334477104999, "q25": 11.57860554175, "median": 14.3351155175001, "q75": 23.24451381125, "p95": 106.1242746187}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 250.055353682864, "medianTimeToFirstChunk": 11.960372903, "medianTimeToFirstAnswerToken": 11.960372903, "medianEndToEndResponseTime": 13.95993017156435}, "long": {"medianOutputSpeed": 218.593820740313, "medianTimeToFirstChunk": 14.3351155175001, "medianTimeToFirstAnswerToken": 14.3351155175001, "medianEndToEndResponseTime": 16.62246288306902}, "hundredK": {"medianOutputSpeed": 236.165065606762, "medianTimeToFirstChunk": 15.530255947, "medianTimeToFirstAnswerToken": 15.530255947, "medianEndToEndResponseTime": 17.647419206161068}, "mediumParallel": {"medianOutputSpeed": 239.090088081997, "medianTimeToFirstChunk": 8.58592588100001, "medianTimeToFirstAnswerToken": 8.58592588100001, "medianEndToEndResponseTime": 10.677187814989189}}, "endToEndResponseTime": {"input": 14.3351155175001, "reasoning": 0, "answer": 2.2873473655689214, "total": 16.62246288306902}, "timeToFirstAnswerToken": {"input": 14.3351155175001, "reasoning": 0, "total": 14.3351155175001}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "504412c2-2ada-499b-aebf-7e0a35c9d286", "slug": "claude-4-opus", "name": "Claude 4 Opus (Non-reasoning)", "shortName": "Claude 4 Opus (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-22", "knowledgeCutoffDate": "2025-03-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-4-opus", "name": "Claude 4 Opus"}, "deprecated": true, "deprecatedTo": "claude-4-1-opus", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 16.6142232043434, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.43265306122449, "hle": 0.061631139944393, "gpqa": 0.701010101010101, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.541798941798942, "aime25": 0.363333333333333, "analystAgent": null, "price1mInputTokens": 15, "price1mOutputTokens": 75, "cacheHitPrice": 1.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 18.75, "pricePer1k1mpImages": 20.01, "price1mBlended0To3To1": 30, "price1mBlended7To2To1": 11.55, "price1mBlended0To1To1": 45, "price1mBlended100To1To1": 2.3529411764705883, "price1mBlended0To100To1": 15.594059405940595, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 2, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "508943e4-e9e1-4d10-9c0e-a7650e9d7315", "slug": "exaone-4-5-33b", "name": "EXAONE 4.5 33B", "shortName": "EXAONE 4.5 33B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "exaone-4-5-33b", "name": "EXAONE 4.5 33B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 34.4, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "EXAONE AI Model License Agreement 1.2 - NC", "licenseUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B", "microevalsEnabled": false, "intelligenceIndex": 13.2058394009382, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -50.7166666666667, "omniscienceBreakdown": {"accuracy": 0.16233333333333333, "hallucinationRate": 0.7992439315559092}, "gdpval": 627.65, "gdpvalNormalized": 0.06382499999999999, "itBenchSre": null, "tau2": 0.780701754385965, "tauBanking": null, "terminalbenchHard": 0.204545454545455, "terminalBench21": 0.213483146067416, "terminalBench40": null, "scicode": null, "lcr": 0.546666666666667, "ifbench": 0.579591836734694, "hle": 0.128822984244671, "gpqa": 0.793939393939394, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.673410404624277, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 3, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "45157c16-fcbb-4110-b20f-7bca754b6554", "slug": "lg", "name": "LG AI Research", "logo": "/img/logos/lg_small.png", "color": "#df3b8a", "country": "kr", "url": "https://www.lgresearch.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "509e94e3-f1cb-43fb-98ff-e0e9872cfd1f", "slug": "qwen3-5-27b-non-reasoning", "name": "Qwen3.5 27B (Non-reasoning)", "shortName": "Qwen3.5 27B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-24", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-5-27b", "name": "Qwen3.5 27B"}, "deprecated": true, "deprecatedTo": "qwen3-6-35b-a3b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 27.8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-27B", "microevalsEnabled": false, "intelligenceIndex": 19.3684268009412, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -47.6666666666667, "omniscienceBreakdown": {"accuracy": 0.15683333333333332, "hallucinationRate": 0.751334255781775}, "gdpval": null, "itBenchSre": null, "tau2": 0.871345029239766, "tauBanking": null, "terminalbenchHard": 0.318181818181818, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.64, "ifbench": 0.469387755102041, "hle": 0.139481000926784, "gpqa": 0.842424242424242, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.7, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.307, "price1mBlended0To3To1": 0.825, "price1mBlended7To2To1": 0.51, "price1mBlended0To1To1": 1.3499999999999999, "price1mBlended100To1To1": 0.3205882352941177, "price1mBlended0To100To1": 0.3207920792079208, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 85.8042484300455, "medianTimeToFirstChunk": 5.7458963985}, "outputSpeedVariance": {"p05": 72.1255363116312, "q25": 79.1407466399353, "median": 85.8042484300455, "q75": 91.3460701587383, "p95": 97.4054941610915}, "timeToFirstChunkVariance": {"p05": 5.51549527284998, "q25": 5.54696055599999, "median": 5.7458963985, "q75": 6.33346807650001, "p95": 6.78372728414983}, "performanceByPromptType": {"long": {"medianOutputSpeed": 85.8042484300455, "medianTimeToFirstChunk": 5.7458963985, "medianTimeToFirstAnswerToken": 5.7458963985, "medianEndToEndResponseTime": 11.573113688418227}}, "endToEndResponseTime": {"input": 5.7458963985, "reasoning": 0, "answer": 5.827217289918226, "total": 11.573113688418227}, "timeToFirstAnswerToken": {"input": 5.7458963985, "reasoning": 0, "total": 5.7458963985}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "50f92d5f-f413-4c97-8dab-331101622a28", "slug": "mistral-large-2", "name": "Mistral Large 2 (Nov '24)", "shortName": "Mistral Large 2 (Nov)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-11-18", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-large-2", "name": "Mistral Large 2 (Nov '24)"}, "deprecated": true, "deprecatedTo": "mistral-large-3", "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 123, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "Mistral Research License", "licenseUrl": "https://mistral.ai/licenses/MRL-0.1.md", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-Large-Instruct-2411", "microevalsEnabled": false, "intelligenceIndex": 7.55559683895193, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -34.3666666666667, "omniscienceBreakdown": {"accuracy": 0.19866666666666666, "hallucinationRate": 0.6767886855241264}, "gdpval": null, "itBenchSre": null, "tau2": 0.307017543859649, "tauBanking": null, "terminalbenchHard": 0.0606060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.312244897959184, "hle": 0.0334, "gpqa": 0.485858585858586, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.293121693121693, "aime25": 0.14, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "512d17ef-13d2-4f65-bf9b-154b0dec7e8d", "slug": "kimi-k3-low", "name": "Kimi K3 (low)", "shortName": "Kimi K3 (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "kimi-k3", "name": "Kimi K3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 2780, "inferenceParametersActiveBillions": 104, "sizeClass": "large", "contextWindowTokens": 1048576, "licenseName": "Kimi K3", "licenseUrl": "https://huggingface.co/moonshotai/Kimi-K3/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-K3", "microevalsEnabled": false, "intelligenceIndex": 30.4810237529068, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 32.774242628858815, "strategyAndOps": 39.50242588847528, "legal": 34.74954427059773, "engineering": 30.004642525145528, "economics": 37.45129973607757}, "omniscience": 3.91666666666667, "omniscienceBreakdown": {"accuracy": 0.4575, "hallucinationRate": 0.7711213517665131}, "gdpPdfAllPass": 0.186, "gdpval": 1185.27, "gdpvalNormalized": 0.34263499999999997, "itBenchSre": null, "tau2": null, "tauBanking": 0.416494845360825, "terminalbenchHard": null, "terminalBench21": 0.823970037453184, "terminalBench40": 0.126262626262626, "scicode": 0.52662037037037, "lcr": 0.793333333333333, "ifbench": null, "hle": 0.249768303985171, "gpqa": 0.842424242424242, "critpt": 0.0314285714285714, "apexAgents": null, "mmmuPro": 0.784971098265896, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.492568024921068, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 2.31, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 0.47058823529411764, "price1mBlended0To100To1": 3.118811881188119, "intelligenceIndexTimePerTask": 327.01596835102, "intelligenceIndexCost": {"total": 1190.4222394286637, "input": 865.4225794286638, "nonCacheInput": 83.782092, "cacheRead": 409.487482285704, "cacheWrite": 372.15300514295967, "output": 324.99966, "reasoning": 151.38012, "answer": 173.61954}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.1463056165227514, "input": 0.96298041064786, "nonCacheInput": 0.0624549368749636, "cacheRead": 0.5139825966207331, "cacheWrite": 0.3865428771521632, "output": 0.18332520587489112, "reasoning": 0.08837259626885861, "answer": 0.0949526096060325}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.08106436144304005}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.02095735394459475}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.022815322139343747}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.9471263256022237}, {"slug": "scicode", "weightedCostPerTask": 0.0018565968750000003}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0024208126042632064}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.049628196000000006}, {"slug": "critpt", "weightedCostPerTask": 0.0050264957142857145}, {"slug": "omniscience", "weightedCostPerTask": 0.0007548717}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0146552805}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1516936640, "output": 21666644, "answer": 11574636, "reasoning": 10092008}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 5891.506417923906, "answer": 6330.173973735501, "output": 12221.680391659407}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 4, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 984.78, "lower95ci": 976.65, "upper95ci": 993.18}, "rubricPassRate": 0.2606060606060606, "analyticalQuality": {"elo": 1000.24, "lower95ci": 985.83, "upper95ci": 1014.03}, "presentation": {"elo": 954.39, "lower95ci": 940.24, "upper95ci": 969.16}}, "briefcaseTotalCost": 49.17904594211097, "timescaleData": {"medianOutputSpeed": 35.3303331123151, "medianTimeToFirstChunk": 3.85322284700001}, "outputSpeedVariance": {"p05": 28.2681949250759, "q25": 30.8634941801771, "median": 35.3303331123151, "q75": 37.1011739241896, "p95": 46.4980328016139}, "timeToFirstChunkVariance": {"p05": 3.15444829050003, "q25": 3.496300614, "median": 3.85322284700001, "q75": 5.83020735350006, "p95": 14.3983359362}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 38.1513592731833, "medianTimeToFirstChunk": 3.47838859300003, "medianTimeToFirstAnswerToken": 55.90116036579517, "medianEndToEndResponseTime": 69.00685330899397}, "long": {"medianOutputSpeed": 35.3303331123151, "medianTimeToFirstChunk": 3.85322284700001, "medianTimeToFirstAnswerToken": 60.46180317490129, "medianEndToEndResponseTime": 74.61394825687661}, "hundredK": {"medianOutputSpeed": 46.2477330964227, "medianTimeToFirstChunk": 12.7844083915001, "medianTimeToFirstAnswerToken": 56.029771268641895, "medianEndToEndResponseTime": 66.84111198792735}, "mediumParallel": {"medianOutputSpeed": 35.745280160755, "medianTimeToFirstChunk": 3.445647054, "medianTimeToFirstAnswerToken": 59.39708990199352, "medianEndToEndResponseTime": 73.3849506139919}}, "endToEndResponseTime": {"input": 3.85322284700001, "reasoning": 56.60858032790128, "answer": 14.15214508197532, "total": 74.61394825687661}, "timeToFirstAnswerToken": {"input": 3.85322284700001, "reasoning": 56.60858032790128, "total": 60.46180317490129}, "performanceDataSource": {"type": "firstParty", "providerName": "Kimi"}, "hostModelCount": 3, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "515852e7-ba9c-4571-8cf9-82ad6b45f22f", "slug": "palm-2", "name": "PALM-2", "shortName": "PALM-2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-05-10", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "palm-2", "name": "PALM-2"}, "deprecated": true, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 8000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.36921134713752, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "51d0b717-953d-4b44-af61-406c6b7dff39", "slug": "qwen3-vl-30b-a3b-instruct", "name": "Qwen3 VL 30B A3B Instruct", "shortName": "Qwen3 VL 30B A3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-03", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-vl-30b-a3b-instruct", "name": "Qwen3 VL 30B A3B Instruct"}, "deprecated": true, "deprecatedTo": "qwen3-5-35b-a3b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 7.9263607036835, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -63.4166666666667, "omniscienceBreakdown": {"accuracy": 0.15616666666666668, "hallucinationRate": 0.9365988544341299}, "gdpval": null, "itBenchSre": null, "tau2": 0.190058479532164, "tauBanking": null, "terminalbenchHard": 0.0606060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.331292517006803, "hle": 0.0630213160333642, "gpqa": 0.694949494949495, "critpt": 0, "apexAgents": null, "mmmuPro": 0.621387283236994, "livecodebench": 0.476190476190476, "aime25": 0.723333333333333, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.204, "price1mBlended0To3To1": 0.35000000000000003, "price1mBlended7To2To1": 0.26000000000000006, "price1mBlended0To1To1": 0.5, "price1mBlended100To1To1": 0.20588235294117646, "price1mBlended0To100To1": 0.20594059405940596, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 112.493060309298, "medianTimeToFirstChunk": 2.18933042049997}, "outputSpeedVariance": {"p05": 97.1472429594626, "q25": 109.009252878154, "median": 112.493060309298, "q75": 115.121833083125, "p95": 116.25073819701}, "timeToFirstChunkVariance": {"p05": 2.06392067635, "q25": 2.118527027, "median": 2.18933042049997, "q75": 2.44674529849995, "p95": 2.96879674724999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 112.493060309298, "medianTimeToFirstChunk": 2.18933042049997, "medianTimeToFirstAnswerToken": 2.18933042049997, "medianEndToEndResponseTime": 6.6340490424776934}}, "endToEndResponseTime": {"input": 2.18933042049997, "reasoning": 0, "answer": 4.4447186219777235, "total": 6.6340490424776934}, "timeToFirstAnswerToken": {"input": 2.18933042049997, "reasoning": 0, "total": 2.18933042049997}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 3, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "523125f4-a1da-4990-9abd-dd08a069100e", "slug": "grok-4-20-0309-non-reasoning", "name": "Grok 4.20 0309 (Non-reasoning)", "shortName": "Grok 4.20 0309 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-10", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "grok-4-20-0309", "name": "Grok 4.20 0309"}, "deprecated": true, "deprecatedTo": "grok-4-20-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 14.606641173969, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -42.5833333333333, "omniscienceBreakdown": {"accuracy": 0.2605, "hallucinationRate": 0.9281045751633987}, "gdpval": null, "itBenchSre": null, "tau2": 0.695906432748538, "tauBanking": null, "terminalbenchHard": 0.21969696969697, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.253333333333333, "ifbench": 0.478231292517007, "hle": 0.245134383688601, "gpqa": 0.784848484848485, "critpt": 0, "apexAgents": null, "mmmuPro": 0.640462427745665, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.514, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.1400000000000001, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 0.27450980392156865, "price1mBlended0To100To1": 2.0396039603960396, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "527e943a-adc6-4e69-93af-d1608e1b5fed", "slug": "deepseek-v3-2-speciale", "name": "DeepSeek V3.2 Speciale", "shortName": "DeepSeek V3.2 Speciale", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-v3-2-speciale", "name": "DeepSeek V3.2 Speciale"}, "deprecated": true, "deprecatedTo": "deepseek-v4-pro-0424", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Speciale", "microevalsEnabled": false, "intelligenceIndex": 14.4560679389612, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -17.7166666666667, "omniscienceBreakdown": {"accuracy": 0.37766666666666665, "hallucinationRate": 0.8915372254954472}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.348484848484849, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.7, "ifbench": 0.638775510204082, "hle": 0.287303058387396, "gpqa": 0.870707070707071, "critpt": 0.0742857142857143, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.896296296296296, "aime25": 0.966666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5303601c-8133-4f52-bc4e-5241ee6b3c10", "slug": "gemma-4-e4b-non-reasoning", "name": "Gemma 4 E4B (Non-reasoning)", "shortName": "Gemma 4 E4B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-03", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-4-e4b", "name": "Gemma 4 E4B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8, "inferenceParametersActiveBillions": 4.5, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-4-E4B-it", "microevalsEnabled": false, "intelligenceIndex": 7.45765296912625, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -40.9833333333333, "omniscienceBreakdown": {"accuracy": 0.08316666666666667, "hallucinationRate": 0.5377204144700963}, "gdpval": null, "itBenchSre": null, "tau2": 0.260233918128655, "tauBanking": null, "terminalbenchHard": 0.0757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.24, "ifbench": 0.405442176870748, "hle": 0.0481927710843374, "gpqa": 0.549494949494949, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.512138728323699, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.02, "price1mOutputTokens": 0.1, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.04, "price1mBlended7To2To1": 0.028000000000000004, "price1mBlended0To1To1": 0.060000000000000005, "price1mBlended100To1To1": 0.020784313725490198, "price1mBlended0To100To1": 0.020792079207920793, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 40.730585015161, "medianTimeToFirstChunk": 0.751175947999996}, "outputSpeedVariance": {"p05": 21.5029703786406, "q25": 35.4381478544519, "median": 40.730585015161, "q75": 44.9448283619512, "p95": 51.2753713667705}, "timeToFirstChunkVariance": {"p05": 0.69167675880001, "q25": 0.732088264750018, "median": 0.751175947999996, "q75": 0.836499657499951, "p95": 1.48393641440001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 38.2354138406813, "medianTimeToFirstChunk": 0.347711874499993, "medianTimeToFirstAnswerToken": 0.347711874499993, "medianEndToEndResponseTime": 13.424594004856733}, "long": {"medianOutputSpeed": 40.730585015161, "medianTimeToFirstChunk": 0.751175947999996, "medianTimeToFirstAnswerToken": 0.751175947999996, "medianEndToEndResponseTime": 13.026963290948467}, "hundredK": {"medianOutputSpeed": 19.9105367173593, "medianTimeToFirstChunk": 11.309287824, "medianTimeToFirstAnswerToken": 11.309287824, "medianEndToEndResponseTime": 36.42161940489945}, "mediumParallel": {"medianOutputSpeed": 35.09431635328, "medianTimeToFirstChunk": 0.521015658500005, "medianTimeToFirstAnswerToken": 0.521015658500005, "medianEndToEndResponseTime": 14.768336933167571}}, "endToEndResponseTime": {"input": 0.751175947999996, "reasoning": 0, "answer": 12.27578734294847, "total": 13.026963290948467}, "timeToFirstAnswerToken": {"input": 0.751175947999996, "reasoning": 0, "total": 0.751175947999996}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "538e945c-6c27-4fd3-995d-ded80a36cd10", "slug": "gpt-5-4-low", "name": "GPT-5.4 (low)", "shortName": "GPT-5.4 (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-05", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gpt-5-4", "name": "GPT-5.4"}, "deprecated": true, "deprecatedTo": "gpt-5-5-low", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1050000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 27.5773176863368, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 4.78333333333333, "omniscienceBreakdown": {"accuracy": 0.4785, "hallucinationRate": 0.8258229466283158}, "gdpval": null, "itBenchSre": null, "tau2": 0.745614035087719, "tauBanking": null, "terminalbenchHard": 0.431818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.766666666666667, "ifbench": 0.659183673469388, "hle": 0.308155699721965, "gpqa": 0.870707070707071, "critpt": 0.0742857142857143, "apexAgents": null, "mmmuPro": 0.779768786127168, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 2.5, "price1mOutputTokens": 15, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 1.91, "price1mBlended0To3To1": 5.625, "price1mBlended7To2To1": 2.175, "price1mBlended0To1To1": 8.75, "price1mBlended100To1To1": 0.4166666666666667, "price1mBlended0To100To1": 2.623762376237624, "timescaleData": {"medianOutputSpeed": 97.5831226555531, "medianTimeToFirstChunk": 1.84821935800016}, "outputSpeedVariance": {"p05": 61.1559062758165, "q25": 81.3233743831202, "median": 97.5831226555531, "q75": 114.679430725413, "p95": 141.205010089071}, "timeToFirstChunkVariance": {"p05": 1.01114204710012, "q25": 1.44296307600001, "median": 1.84821935800016, "q75": 2.56351127124998, "p95": 4.85349176504991}, "performanceByPromptType": {"long": {"medianOutputSpeed": 97.5831226555531, "medianTimeToFirstChunk": 1.84821935800016, "medianTimeToFirstAnswerToken": 1.84821935800016, "medianEndToEndResponseTime": 6.97205621004362}}, "endToEndResponseTime": {"input": 1.84821935800016, "reasoning": 0, "answer": 5.12383685204346, "total": 6.97205621004362}, "timeToFirstAnswerToken": {"input": 1.84821935800016, "reasoning": 0, "total": 1.84821935800016}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "53b9e276-e360-4a39-9076-1a19d72c25fe", "slug": "k2-mova-36b-mid5", "name": "K2 Horizon MoVA 36B A4B", "shortName": "K2 Horizon MoVA 36B A4B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-03", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "k2-horizon-mova-36b-a4b", "name": "K2 Horizon MoVA 36B A4B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 36, "inferenceParametersActiveBillions": 4, "sizeClass": "small", "contextWindowTokens": 524288, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/IFM/K2-Horizon-MoVA-36B-A4B", "microevalsEnabled": false, "intelligenceIndex": 25.6692040731435, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 26.211562825977403, "strategyAndOps": 25.846290170064425, "legal": 26.60692765511986, "engineering": 28.952602647954453, "economics": 36.47950617856038}, "omniscience": -10.95, "omniscienceBreakdown": {"accuracy": 0.15, "hallucinationRate": 0.3052941176470588}, "gdpPdfAllPass": 0.042, "gdpval": 1243.11, "gdpvalNormalized": 0.37155499999999997, "itBenchSre": null, "tau2": null, "tauBanking": 0.319587628865979, "terminalbenchHard": null, "terminalBench21": 0.565543071161049, "terminalBench40": 0, "scicode": 0.400462962962963, "lcr": 0.716666666666667, "ifbench": null, "hle": 0.234476367006487, "gpqa": 0.822222222222222, "critpt": 0.0228571428571429, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.2610203199558987, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "canonicalIntelligenceIndexTokenCount": {"input": 5208669169, "output": 113698036, "answer": 21623247, "reasoning": 92074789}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 37842.38186264047, "answer": 17160.094457061008, "output": 55002.476319701476}, "briefcaseBreakdown": {"overall": {"elo": 1170.41, "lower95ci": 1160.16, "upper95ci": 1181.44}, "rubricPassRate": 0.35454545454545455, "analyticalQuality": {"elo": 1218.99, "lower95ci": 1199.76, "upper95ci": 1238.52}, "presentation": {"elo": 1141.96, "lower95ci": 1123.73, "upper95ci": 1161.39}}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "8b8b84fb-4b24-45be-b9e2-74ed50d00ff7", "slug": "mbzuai", "name": "MBZUAI Institute of Foundation Models", "logo": "/img/logos/mbzuai_small.svg", "color": "#1521a9", "country": "ae", "url": "https://mbzuai.ac.ae/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "53c98840-47af-49aa-94e6-469fb17e9a1b", "slug": "claude-opus-4-6-adaptive", "name": "Claude Opus 4.6 (Adaptive Reasoning, Max Effort)", "shortName": "Claude Opus 4.6 (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-05", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "claude-opus-4-6", "name": "Claude Opus 4.6"}, "deprecated": true, "deprecatedTo": "claude-opus-4-7", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 31.9457397504366, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 13.6666666666667, "omniscienceBreakdown": {"accuracy": 0.4698333333333333, "hallucinationRate": 0.6284187362464634}, "gdpval": null, "itBenchSre": null, "tau2": 0.921052631578947, "tauBanking": null, "terminalbenchHard": 0.462121212121212, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.78, "ifbench": 0.531292517006803, "hle": 0.399443929564411, "gpqa": 0.895959595959596, "critpt": 0.125714285714286, "apexAgents": 0.3303834808259587, "mmmuPro": 0.754335260115607, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.67, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "timescaleData": {"medianOutputSpeed": 39.5778227617065, "medianTimeToFirstChunk": 20.236485618}, "outputSpeedVariance": {"p05": 33.1719932924156, "q25": 35.4112004618814, "median": 39.5778227617065, "q75": 56.7024123624515, "p95": 66.162253187307}, "timeToFirstChunkVariance": {"p05": 3.48379422799996, "q25": 8.86580950449996, "median": 20.236485618, "q75": 31.7768062204999, "p95": 102.029433982}, "performanceByPromptType": {"long": {"medianOutputSpeed": 39.5778227617065, "medianTimeToFirstChunk": 20.236485618, "medianTimeToFirstAnswerToken": 20.236485618, "medianEndToEndResponseTime": 32.869823308414205}}, "endToEndResponseTime": {"input": 20.236485618, "reasoning": 0, "answer": 12.633337690414207, "total": 32.869823308414205}, "timeToFirstAnswerToken": {"input": 20.236485618, "reasoning": 0, "total": 20.236485618}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "540ebc58-a2d8-4dc9-ba6b-973efa52fab1", "slug": "jamba-1-5-mini", "name": "Jamba 1.5 Mini", "shortName": "Jamba 1.5 Mini", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-08-22", "knowledgeCutoffDate": "2024-03-05", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "jamba-1-5-mini", "name": "Jamba 1.5 Mini"}, "deprecated": true, "deprecatedTo": "jamba-1-6-mini", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 52, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": "Jamba Open Model License Agreement", "licenseUrl": "https://www.ai21.com/licenses/jamba-open-model-license", "modelWeightsSourceUrl": "https://huggingface.co/ai21labs/AI21-Jamba-1.5-Mini", "microevalsEnabled": false, "intelligenceIndex": 5.20641262573048, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0514, "gpqa": 0.302020202020202, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0624338624338624, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.25, "price1mBlended7To2To1": 0.22000000000000003, "price1mBlended0To1To1": 0.30000000000000004, "price1mBlended100To1To1": 0.20196078431372547, "price1mBlended0To100To1": 0.20198019801980197, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "6216c686-bc60-4dbb-9f25-83e9dba803d1", "slug": "ai21-labs", "name": "AI21 Labs", "logo": "/img/logos/ai21_small.svg", "color": "#d63864", "country": "il", "url": "https://www.ai21.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "54442579-2a4d-40cc-b264-bc4ff29e311a", "slug": "olmo-2-32b", "name": "OLMo 2 32B", "shortName": "OLMo 2 32B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-13", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "olmo-2-32b", "name": "OLMo 2 32B"}, "deprecated": true, "deprecatedTo": "olmo-3-32b-think", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32.2, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 4096, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 5.9708764479062, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.380952380952381, "hle": 0.036144578313253, "gpqa": 0.328282828282828, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0677248677248677, "aime25": 0.0333333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "ab6c5270-d7b9-4c09-92fe-62662618c631", "slug": "ai2", "name": "Allen Institute for AI", "logo": "/img/logos/ai2_small.svg", "color": "#F0529C", "country": "us", "url": "https://allenai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "546ec53f-273c-4af7-b13f-b88c41f45905", "slug": "nova-pro", "name": "Nova Pro", "shortName": "Nova Pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-03", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "nova-pro", "name": "Nova Pro"}, "deprecated": true, "deprecatedTo": "nova-2-0-pro", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 300000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.95832302287488, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -47.7333333333333, "omniscienceBreakdown": {"accuracy": 0.16866666666666666, "hallucinationRate": 0.7770649558941459}, "gdpval": null, "itBenchSre": null, "tau2": 0.140350877192982, "tauBanking": null, "terminalbenchHard": 0.0606060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.21, "ifbench": 0.380952380952381, "hle": 0.0319, "gpqa": 0.498989898989899, "critpt": 0, "apexAgents": null, "mmmuPro": 0.443352601156069, "livecodebench": 0.232804232804233, "aime25": 0.07, "analystAgent": null, "price1mInputTokens": 0.8, "price1mOutputTokens": 3.2, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.4000000000000001, "price1mBlended7To2To1": 0.62, "price1mBlended0To1To1": 2, "price1mBlended100To1To1": 0.23529411764705882, "price1mBlended0To100To1": 0.8237623762376238, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "54c7f3fc-7078-442a-b472-e8691257a88c", "slug": "granite-4-0-350m", "name": "Granite 4.0 350M", "shortName": "Granite 4.0 350M", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "granite-4-0-350m", "name": "Granite 4.0 350M"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 0.35, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.0-350m", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -69.35, "omniscienceBreakdown": {"accuracy": 0.0385, "hallucinationRate": 0.7613104524180967}, "gdpval": null, "itBenchSre": null, "tau2": 0.131578947368421, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.159183673469388, "hle": 0.0551436515291937, "gpqa": 0.260606060606061, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0243386243386243, "aime25": 0, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 55.55555555555556, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "55a3ebf6-6117-4cc1-8596-c6de6e552fd4", "slug": "gemini-2-5-flash-04-2025", "name": "Gemini 2.5 Flash Preview (Non-reasoning)", "shortName": "Gemini 2.5 Flash (Apr) (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-17", "knowledgeCutoffDate": "2025-01-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-flash-04-2025", "name": "Gemini 2.5 Flash Preview"}, "deprecated": true, "deprecatedTo": "gemini-2-5-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.65865427868212, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.038, "gpqa": 0.593939393939394, "critpt": null, "apexAgents": null, "mmmuPro": 0.619653179190751, "livecodebench": 0.406349206349206, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "573bbd93-114c-4b71-9ede-a73a7d4bdf84", "slug": "grok-4-fast-reasoning", "name": "Grok 4 Fast (Reasoning)", "shortName": "Grok 4 Fast", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "grok-4-fast", "name": "Grok 4 Fast"}, "deprecated": true, "deprecatedTo": "grok-4-1-fast-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 17.9399302586701, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -29.9333333333333, "omniscienceBreakdown": {"accuracy": 0.22783333333333333, "hallucinationRate": 0.6827109864018994}, "gdpval": null, "itBenchSre": null, "tau2": 0.657894736842105, "tauBanking": null, "terminalbenchHard": 0.189393939393939, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.736666666666667, "ifbench": 0.505442176870748, "hle": 0.190917516218721, "gpqa": 0.847474747474747, "critpt": 0.0285714285714286, "apexAgents": null, "mmmuPro": 0.617919075144509, "livecodebench": 0.831746031746032, "aime25": 0.896666666666667, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.275, "price1mBlended7To2To1": 0.23000000000000004, "price1mBlended0To1To1": 0.35, "price1mBlended100To1To1": 0.20294117647058824, "price1mBlended0To100To1": 0.20297029702970298, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "575498d6-60ec-466b-9372-fea19911fd07", "slug": "gpt-4o-chatgpt-03-25", "name": "GPT-4o (March 2025, chatgpt-4o-latest)", "shortName": "GPT-4o (Mar)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-27", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4o-chatgpt-03-25", "name": "GPT-4o (March 2025, chatgpt-4o-latest)"}, "deprecated": true, "deprecatedTo": "gpt-4o-chatgpt-04-25", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.96179172361777, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0397, "gpqa": 0.654545454545455, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.425396825396825, "aime25": 0.256666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "583f98fb-c4b8-4df3-8d40-60ac0ed69882", "slug": "muse-glimmer", "name": "Muse Glimmer (high)", "shortName": "Muse Glimmer (high)", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-08-10", "knowledgeCutoffDate": "2026-01-04", "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "muse-glimmer", "name": "Muse Glimmer"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/meta-models/Muse-Glimmer-30B", "microevalsEnabled": false, "intelligenceIndex": 18.0678176089465, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 18.396278445360384, "strategyAndOps": 15.551338056891499, "legal": 19.049438102030035, "healthcareAndMedical": 18.338532130231634, "engineering": 20.454789192333777, "economics": 25.7188404386778}, "omniscience": -32.85, "omniscienceBreakdown": {"accuracy": 0.2698333333333333, "hallucinationRate": 0.8194476146998402}, "mlcrOverall": 0.2, "gdpPdfAllPass": 0.1, "gdpval": 892.72, "gdpvalNormalized": 0.19636, "itBenchSre": null, "tau2": null, "tauBanking": 0.235051546391753, "terminalbenchHard": null, "terminalBench21": 0.51685393258427, "terminalBench40": 0.00505050505050505, "scicode": 0.449074074074074, "lcr": 0.833333333333333, "ifbench": null, "hle": 0.219647822057461, "gpqa": 0.835353535353535, "critpt": 0.0257142857142857, "apexAgents": null, "mmmuPro": 0.743352601156069, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.06831776269647931, "enterpriseOpsGym": 0.34735899731423453, "price1mInputTokens": 0.35, "price1mOutputTokens": 1.5, "cacheHitPrice": 0.04, "cacheHitDiscountPercent": 0.8857142857142857, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.6375, "price1mBlended7To2To1": 0.248, "price1mBlended0To1To1": 0.925, "price1mBlended100To1To1": 0.057352941176470586, "price1mBlended0To100To1": 0.3613861386138614, "intelligenceIndexTimePerTask": 142.3160540947418, "intelligenceIndexCost": {"total": 151.6760252, "input": 63.7115717, "nonCacheInput": 5.788350749999999, "cacheRead": 44.4366384, "cacheWrite": 13.48658255, "output": 87.96445349999999, "reasoning": 72.169056, "answer": 15.7953975}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.05509175451443994, "input": 0.03420395904812494, "nonCacheInput": 0.0037622817395946604, "cacheRead": 0.024630028652023166, "cacheWrite": 0.005811648656507115, "output": 0.020887795466314998, "reasoning": 0.014321796430512256, "answer": 0.0065659990358027465}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.01033286797252747}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.003991740481818181}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.004028989737442923}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.024825156318181815}, {"slug": "scicode", "weightedCostPerTask": 0.0007761901736111112}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.001698591777108434}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0026958000000000004}, {"slug": "critpt", "weightedCostPerTask": 0.0044444785}, {"slug": "omniscience", "weightedCostPerTask": 0.0004738476037499999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0018240919499999998}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1165987198, "output": 58642969, "answer": 10530265, "reasoning": 48112704}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 9547.864287008168, "answer": 4377.332690535162, "output": 13925.19697754333}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 481.02, "lower95ci": 472.05, "upper95ci": 489.21}, "rubricPassRate": 0.11514522821576763, "analyticalQuality": {"elo": 370.61, "lower95ci": 353.64, "upper95ci": 387.12}, "presentation": {"elo": 356.08, "lower95ci": 339.38, "upper95ci": 372.75}}, "briefcaseTotalCost": 6.268606569999999, "timescaleData": {"medianOutputSpeed": 99.4819610243102, "medianTimeToFirstChunk": 1.01768508700002}, "outputSpeedVariance": {"p05": 54.8456244805245, "q25": 63.3564253207542, "median": 99.4819610243102, "q75": 116.088531575505, "p95": 181.214744140684}, "timeToFirstChunkVariance": {"p05": 0.698740726699913, "q25": 0.783786701000025, "median": 1.01768508700002, "q75": 1.14991275349997, "p95": 1.51177399375005}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 100.512735821727, "medianTimeToFirstChunk": 0.327510732000008, "medianTimeToFirstAnswerToken": 20.225486681508254, "medianEndToEndResponseTime": 25.199980668885317}, "long": {"medianOutputSpeed": 99.4819610243102, "medianTimeToFirstChunk": 1.01768508700002, "medianTimeToFirstAnswerToken": 21.12183240584172, "medianEndToEndResponseTime": 26.147869235552143}, "hundredK": {"medianOutputSpeed": 107.196962544958, "medianTimeToFirstChunk": 6.67946504250003, "medianTimeToFirstAnswerToken": 25.33671010353623, "medianEndToEndResponseTime": 30.00102136879528}, "mediumParallel": {"medianOutputSpeed": 62.285214375191, "medianTimeToFirstChunk": 0.631768760500108, "medianTimeToFirstAnswerToken": 32.742118224057954, "medianEndToEndResponseTime": 40.76970558994742}}, "endToEndResponseTime": {"input": 1.01768508700002, "reasoning": 20.104147318841697, "answer": 5.026036829710424, "total": 26.147869235552143}, "timeToFirstAnswerToken": {"input": 1.01768508700002, "reasoning": 20.104147318841697, "total": 21.12183240584172}, "performanceDataSource": {"type": "median"}, "hostModelCount": 3, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "58b812bf-8498-46db-b834-f43ccc614b61", "slug": "gpt-5-6-luna-medium", "name": "GPT-5.6 Luna (medium)", "shortName": "GPT-5.6 Luna (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-5-6-luna", "name": "GPT-5.6 Luna"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 25.4773991440784, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 27.455789476862787, "strategyAndOps": 28.97358839819329, "legal": 28.07244544061949, "healthcareAndMedical": 24.605995933157192, "engineering": 26.52956853166914, "economics": 32.33204639712697}, "omniscience": -13.1833333333333, "omniscienceBreakdown": {"accuracy": 0.407, "hallucinationRate": 0.9086565486228219}, "mlcrOverall": 0.0833333333333333, "gdpPdfAllPass": 0.152, "gdpval": 1168.94, "gdpvalNormalized": 0.33447000000000005, "itBenchSre": null, "tau2": null, "tauBanking": 0.177319587628866, "terminalbenchHard": null, "terminalBench21": 0.531835205992509, "terminalBench40": 0.00505050505050505, "scicode": 0.467592592592593, "lcr": 0.75, "ifbench": null, "hle": 0.257645968489342, "gpqa": 0.858585858585859, "critpt": 0.0485714285714286, "apexAgents": null, "mmmuPro": 0.758381502890173, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.23074538803075942, "price1mInputTokens": 0.2, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.02, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.25, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.45, "price1mBlended7To2To1": 0.174, "price1mBlended0To1To1": 0.7, "price1mBlended100To1To1": 0.03333333333333334, "price1mBlended0To100To1": 0.2099009900990099, "intelligenceIndexTimePerTask": 40.269918985632614, "intelligenceIndexCost": {"total": 44.32203816705559, "input": 22.818096967055588, "nonCacheInput": 5.649718200000001, "cacheRead": 7.810298389821253, "cacheWrite": 9.358080377234336, "output": 21.5039412, "reasoning": 12.8777892, "answer": 8.626152}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.015598049609820011, "input": 0.010214462049439143, "nonCacheInput": 0.004338524249296821, "cacheRead": 0.0026256678843229173, "cacheWrite": 0.003250269915819403, "output": 0.0053835875603808715, "reasoning": 0.0018589358761784895, "answer": 0.0035246516842023803}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.004400681040018142}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0014815766091229893}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.001456399197816973}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.0025121391970590636}, {"slug": "scicode", "weightedCostPerTask": 0.00017958319444444444}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0002899292956441149}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0035335562}, {"slug": "critpt", "weightedCostPerTask": 0.0006590282857142858}, {"slug": "omniscience", "weightedCostPerTask": 0.00012259638999999998}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0009625602000000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 456195832, "output": 17919951, "answer": 7188460, "reasoning": 10731491}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 1549.1132301487414, "answer": 2937.209736835318, "output": 4486.322966984059}, "briefcaseBreakdown": {"overall": {"elo": 934.17, "lower95ci": 926.28, "upper95ci": 941.67}, "rubricPassRate": 0.20202020202020202, "analyticalQuality": {"elo": 825.87, "lower95ci": 810.9, "upper95ci": 840.68}, "presentation": {"elo": 1087.8, "lower95ci": 1073.33, "upper95ci": 1100.94}}, "briefcaseTotalCost": 2.6697464976110057, "timescaleData": {"medianOutputSpeed": 109.692253042769, "medianTimeToFirstChunk": 2.68806423600006}, "outputSpeedVariance": {"p05": 80.3938097771654, "q25": 95.9672631122462, "median": 109.692253042769, "q75": 118.618324427329, "p95": 137.315083238145}, "timeToFirstChunkVariance": {"p05": 1.47024466970002, "q25": 1.85257733625008, "median": 2.68806423600006, "q75": 4.06026396400017, "p95": 5.28518655620005}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 112.130438850629, "medianTimeToFirstChunk": 2.4932808525, "medianTimeToFirstAnswerToken": 2.4932808525, "medianEndToEndResponseTime": 6.952373362305113}, "long": {"medianOutputSpeed": 109.692253042769, "medianTimeToFirstChunk": 2.68806423600006, "medianTimeToFirstAnswerToken": 2.68806423600006, "medianEndToEndResponseTime": 7.246271275516789}, "hundredK": {"medianOutputSpeed": 111.275165472732, "medianTimeToFirstChunk": 2.98394770850007, "medianTimeToFirstAnswerToken": 2.98394770850007, "medianEndToEndResponseTime": 7.477313302483617}, "mediumParallel": {"medianOutputSpeed": 115.067717333951, "medianTimeToFirstChunk": 6.36823328950001, "medianTimeToFirstAnswerToken": 6.36823328950001, "medianEndToEndResponseTime": 10.713500681473153}}, "endToEndResponseTime": {"input": 2.68806423600006, "reasoning": 0, "answer": 4.558207039516729, "total": 7.246271275516789}, "timeToFirstAnswerToken": {"input": 2.68806423600006, "reasoning": 0, "total": 2.68806423600006}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5962d643-0a6f-4630-bb08-ab5720d80056", "slug": "qwen3-1.7b-instruct-reasoning", "name": "Qwen3 1.7B (Reasoning)", "shortName": "Qwen3 1.7B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-1.7b-instruct", "name": "Qwen3 1.7B"}, "deprecated": true, "deprecatedTo": "qwen3-5-2b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 2.03, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-1.7B", "microevalsEnabled": false, "intelligenceIndex": 5.1865756338608, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -77.5333333333333, "omniscienceBreakdown": {"accuracy": 0.08866666666666667, "hallucinationRate": 0.9480614484272128}, "gdpval": null, "itBenchSre": null, "tau2": 0.260233918128655, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.268707482993197, "hle": 0.0464, "gpqa": 0.355555555555556, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.307936507936508, "aime25": 0.386666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "598190f8-dc9c-4fea-a7ea-4b81c402ab18", "slug": "gemini-3-1-flash-lite-preview", "name": "Gemini 3.1 Flash-Lite", "shortName": "Gemini 3.1 Flash-Lite", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-03", "knowledgeCutoffDate": "2025-01-01", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gemini-3-1-flash-lite", "name": "Gemini 3.1 Flash-Lite"}, "deprecated": true, "deprecatedTo": "gemini-3-5-flash-lite", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 16.034238713025, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 17.39449224586656, "strategyAndOps": 14.580321490908483, "legal": 22.728837944120748, "healthcareAndMedical": 14.221688954470622, "engineering": 18.96841279222785, "economics": 24.00124967176396}, "omniscience": -16.4166666666667, "omniscienceBreakdown": {"accuracy": 0.3626666666666667, "hallucinationRate": 0.8266213389121339}, "mlcrOverall": 0.0611111111111111, "harveyLab": 0.311477782602403, "gdpPdfAllPass": 0.078, "gdpval": 595.99, "gdpvalNormalized": 0.047995, "itBenchSre": null, "tau2": 0.312865497076023, "tauBanking": 0.0969072164948454, "terminalbenchHard": 0.242424242424242, "terminalBench21": 0.310861423220974, "terminalBench40": 0.00505050505050505, "scicode": 0.434027777777778, "lcr": 0.743333333333333, "ifbench": 0.772108843537415, "hle": 0.17191844300278, "gpqa": 0.822222222222222, "critpt": 0.0114285714285714, "apexAgents": 0.121681415929204, "mmmuPro": 0.755491329479769, "livecodebench": null, "aime25": null, "analystAgent": 0.0875, "automationBenchPartialScore": 0.06796182033119545, "enterpriseOpsGym": 0.2802148612354521, "price1mInputTokens": 0.25, "price1mOutputTokens": 1.5, "cacheHitPrice": 0.025, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.28, "price1mBlended0To3To1": 0.5625, "price1mBlended7To2To1": 0.21749999999999997, "price1mBlended0To1To1": 0.875, "price1mBlended100To1To1": 0.041666666666666664, "price1mBlended0To100To1": 0.2623762376237624, "intelligenceIndexTimePerTask": 36.58673634554027, "intelligenceIndexCost": {"total": 119.06256231808575, "input": 38.16189681808576, "nonCacheInput": 5.113962, "cacheRead": 8.565709325768252, "cacheWrite": 24.482225492317507, "output": 80.9006655, "reasoning": 73.905912, "answer": 6.9947535}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.03940671951220252, "input": 0.021463075276670646, "nonCacheInput": 0.0034912966234355927, "cacheRead": 0.004834764004585495, "cacheWrite": 0.013137014648649557, "output": 0.017943644235531873, "reasoning": 0.014776309875403761, "answer": 0.0031673343601281117}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.0037803290406929393}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0016603811193285105}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0022028320501273507}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.016536334240711003}, {"slug": "scicode", "weightedCostPerTask": 0.001818731857638889}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002245038357275255}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00265434025}, {"slug": "critpt", "weightedCostPerTask": 0.006913496071428571}, {"slug": "omniscience", "weightedCostPerTask": 0.00023386827500000002}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00136136825}]}, "canonicalIntelligenceIndexTokenCount": {"input": 461013123, "output": 53933777, "answer": 4663169, "reasoning": 49270608}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 9850.873250269173, "answer": 2111.5562400854083, "output": 11962.429490354582}, "briefcaseBreakdown": {"overall": {"elo": 226.15, "lower95ci": 217.33, "upper95ci": 234.6}, "rubricPassRate": 0.06332992849846783, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 154.07, "lower95ci": 136.99, "upper95ci": 170.53}}, "briefcaseTotalCost": 2.2933996180203833, "timescaleData": {"medianOutputSpeed": 332.009600187563, "medianTimeToFirstChunk": 5.39444307300007}, "outputSpeedVariance": {"p05": 227.328623355786, "q25": 266.796147539199, "median": 332.009600187563, "q75": 375.169725020115, "p95": 422.744666584949}, "timeToFirstChunkVariance": {"p05": 3.85833032850002, "q25": 4.73364928974993, "median": 5.39444307300007, "q75": 6.494809434, "p95": 7.70809837955006}, "performanceByPromptType": {"long": {"medianOutputSpeed": 332.009600187563, "medianTimeToFirstChunk": 5.39444307300007, "medianTimeToFirstAnswerToken": 5.39444307300007, "medianEndToEndResponseTime": 6.900423622109294}}, "endToEndResponseTime": {"input": 5.39444307300007, "reasoning": 0, "answer": 1.5059805491092237, "total": 6.900423622109294}, "timeToFirstAnswerToken": {"input": 5.39444307300007, "reasoning": 0, "total": 5.39444307300007}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "598de97d-029e-47b6-96ec-dbc1e0f9045a", "slug": "kimi-linear-48b-a3b-instruct", "name": "Kimi Linear 48B A3B Instruct", "shortName": "Kimi Linear 48B A3B Instruct", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "kimi-linear-48b-a3b-instruct", "name": "Kimi Linear 48B A3B Instruct"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 49.1, "inferenceParametersActiveBillions": 3, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-Linear-48B-A3B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 7.30037362771236, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.113636363636364, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.28, "ifbench": 0.280952380952381, "hle": 0.0245597775718258, "gpqa": 0.412121212121212, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.377777777777778, "aime25": 0.363333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 61.111111111111114, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "599da8e0-bd9c-4b38-a127-b50e371fbcf8", "slug": "llama-2-chat-70b", "name": "Llama 2 Chat 70B", "shortName": "Llama 2 Chat 70B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-07-18", "knowledgeCutoffDate": "2023-07-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-2-chat-70b", "name": "Llama 2 Chat 70B"}, "deprecated": true, "deprecatedTo": "llama-3-instruct-70b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 4096, "licenseName": "Llama 2 Community License Agreement", "licenseUrl": "https://ai.meta.com/llama/license/", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Llama-2-70b-chat-hf", "microevalsEnabled": false, "intelligenceIndex": 5.3045047203477, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0521, "gpqa": 0.327272727272727, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0984126984126984, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "59a1bb20-9170-4dc2-ba9c-12d326cf068e", "slug": "solar-open-100b-reasoning", "name": "Solar Open 100B (Reasoning)", "shortName": "Solar Open 100B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-17", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "solar-open-100b", "name": "Solar Open 100B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 102, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "Upstage Solar License", "licenseUrl": "https://huggingface.co/upstage/Solar-Open-100B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/upstage/Solar-Open-100B", "microevalsEnabled": false, "intelligenceIndex": 10.3644352600556, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.5, "omniscienceBreakdown": {"accuracy": 0.18533333333333332, "hallucinationRate": 0.896481178396072}, "gdpval": null, "itBenchSre": null, "tau2": 0.482456140350877, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.41, "ifbench": 0.57687074829932, "hle": 0.104263206672845, "gpqa": 0.656565656565657, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "64ff7f06-c6fb-42ea-ba24-9cd103ab2d61", "slug": "upstage", "name": "Upstage", "logo": "/img/logos/upstage_small.svg", "color": "#7c59f5", "country": "kr", "url": "https://www.upstage.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "59b5b14b-5365-4ee7-824a-18a8e6309644", "slug": "gpt-5-3-codex", "name": "GPT-5.3 Codex (xhigh)", "shortName": "GPT-5.3 Codex (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-05", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-3-codex", "name": "GPT-5.3 Codex"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 32.5028174368983, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 10.8666666666667, "omniscienceBreakdown": {"accuracy": 0.5288333333333334, "hallucinationRate": 0.8917580474000707}, "gdpval": null, "itBenchSre": null, "tau2": 0.859649122807018, "tauBanking": null, "terminalbenchHard": 0.53030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.833333333333333, "ifbench": 0.753741496598639, "hle": 0.424930491195551, "gpqa": 0.915151515151515, "critpt": 0.168571428571429, "apexAgents": null, "mmmuPro": 0.784971098265896, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.75, "price1mOutputTokens": 14, "cacheHitPrice": 0.175, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4.8125, "price1mBlended7To2To1": 1.8725, "price1mBlended0To1To1": 7.875, "price1mBlended100To1To1": 0.32598039215686275, "price1mBlended0To100To1": 1.8712871287128714, "briefcaseBreakdown": {"overall": {"elo": 865.74, "lower95ci": 859.19, "upper95ci": 872.11}, "rubricPassRate": 0.21818181818181817, "analyticalQuality": {"elo": 850, "lower95ci": 838.51, "upper95ci": 861.57}, "presentation": {"elo": 839.26, "lower95ci": 826.5, "upper95ci": 851.1}}, "briefcaseTotalCost": 214.25174706176713, "timescaleData": {"medianOutputSpeed": 138.183579311104, "medianTimeToFirstChunk": 60.19348069}, "outputSpeedVariance": {"p05": 98.9926613297153, "q25": 114.7556333191, "median": 138.183579311104, "q75": 174.726518174165, "p95": 193.573908213546}, "timeToFirstChunkVariance": {"p05": 30.3406412129, "q25": 39.90440722725, "median": 60.19348069, "q75": 108.40236825625, "p95": 186.07505130185}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 135.104443364705, "medianTimeToFirstChunk": 36.077433005, "medianTimeToFirstAnswerToken": 36.077433005, "medianEndToEndResponseTime": 39.778273536575156}, "long": {"medianOutputSpeed": 138.183579311104, "medianTimeToFirstChunk": 60.19348069, "medianTimeToFirstAnswerToken": 60.19348069, "medianEndToEndResponseTime": 63.811855626390305}, "hundredK": {"medianOutputSpeed": 146.966047389934, "medianTimeToFirstChunk": 36.0885620025, "medianTimeToFirstAnswerToken": 36.0885620025, "medianEndToEndResponseTime": 39.49070834092188}, "mediumParallel": {"medianOutputSpeed": 135.532191279437, "medianTimeToFirstChunk": 50.290782932, "medianTimeToFirstAnswerToken": 50.290782932, "medianEndToEndResponseTime": 53.9799433836975}}, "endToEndResponseTime": {"input": 60.19348069, "reasoning": 0, "answer": 3.6183749363903, "total": 63.811855626390305}, "timeToFirstAnswerToken": {"input": 60.19348069, "reasoning": 0, "total": 60.19348069}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "59e22326-1bca-4432-a5fa-147fbe8854e7", "slug": "mistral-medium-3", "name": "Mistral Medium 3", "shortName": "Mistral Medium 3", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-07", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-medium-3", "name": "Mistral Medium 3"}, "deprecated": true, "deprecatedTo": "mistral-medium-3-1", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.04757819034062, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -31.4, "omniscienceBreakdown": {"accuracy": 0.18333333333333332, "hallucinationRate": 0.6089795918367347}, "gdpval": null, "itBenchSre": null, "tau2": 0.242690058479532, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.313333333333333, "ifbench": 0.392517006802721, "hle": 0.0405, "gpqa": 0.577777777777778, "critpt": 0, "apexAgents": null, "mmmuPro": 0.530057803468208, "livecodebench": 0.4, "aime25": 0.303333333333333, "analystAgent": null, "price1mInputTokens": 0.4, "price1mOutputTokens": 2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.535, "price1mBlended0To3To1": 0.8, "price1mBlended7To2To1": 0.56, "price1mBlended0To1To1": 1.2, "price1mBlended100To1To1": 0.4156862745098039, "price1mBlended0To100To1": 0.4158415841584158, "timescaleData": {"medianOutputSpeed": 142.308592656022, "medianTimeToFirstChunk": 2.26579135199998}, "outputSpeedVariance": {"p05": 86.4901063669034, "q25": 105.117358782786, "median": 142.308592656022, "q75": 156.153746439493, "p95": 180.328519519521}, "timeToFirstChunkVariance": {"p05": 2.1307558080499, "q25": 2.17296027174993, "median": 2.26579135199998, "q75": 2.83253474575, "p95": 4.18679460154997}, "performanceByPromptType": {"long": {"medianOutputSpeed": 142.308592656022, "medianTimeToFirstChunk": 2.26579135199998, "medianTimeToFirstAnswerToken": 2.26579135199998, "medianEndToEndResponseTime": 5.779282636455049}}, "endToEndResponseTime": {"input": 2.26579135199998, "reasoning": 0, "answer": 3.5134912844550694, "total": 5.779282636455049}, "timeToFirstAnswerToken": {"input": 2.26579135199998, "reasoning": 0, "total": 2.26579135199998}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 2, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5a088cde-18e2-4dfa-98dd-d283e1c19654", "slug": "lfm2-5-1-2b-thinking", "name": "LFM2.5-1.2B-Thinking", "shortName": "LFM2.5-1.2B-Thinking", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "lfm2-5-1-2b-thinking", "name": "LFM2.5-1.2B-Thinking"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1.17, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "lfm 1.0", "licenseUrl": "https://huggingface.co/LiquidAI/LFM2-8B-A1B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking", "microevalsEnabled": false, "intelligenceIndex": 5.22188553175398, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -79.95, "omniscienceBreakdown": {"accuracy": 0.07416666666666667, "hallucinationRate": 0.9436543654365437}, "gdpval": null, "itBenchSre": null, "tau2": 0.195906432748538, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.418367346938776, "hle": 0.06209453197405, "gpqa": 0.339393939393939, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5b1886c4-43ba-4007-b840-9d21a2b7d42c", "slug": "liquidai", "name": "Liquid AI", "logo": "/img/logos/liquidai_small.svg", "color": "#000000", "country": "us", "url": "https://www.liquid.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5a49ef80-3af5-404b-8ac0-e1b230ae95de", "slug": "k2-think-v2", "name": "K2 Think V2", "shortName": "K2 Think V2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-15", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "k2-think-v2", "name": "K2 Think V2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/LLM360/K2-Think-V2", "microevalsEnabled": false, "intelligenceIndex": 11.4956908518183, "intelligenceIndexIsEstimated": true, "capabilities": {"economics": 16.76318118628361}, "omniscience": -40.3333333333333, "omniscienceBreakdown": {"accuracy": 0.18016666666666667, "hallucinationRate": 0.7117300264281358}, "gdpval": 328.05, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.254385964912281, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": 0.149812734082397, "terminalBench40": null, "scicode": null, "lcr": 0.57, "ifbench": 0.627891156462585, "hle": 0.101019462465246, "gpqa": 0.713131313131313, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "briefcaseBreakdown": {"overall": {"elo": 34, "lower95ci": 24.77, "upper95ci": 42.85}, "rubricPassRate": 0.0411946446961895, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "8b8b84fb-4b24-45be-b9e2-74ed50d00ff7", "slug": "mbzuai", "name": "MBZUAI Institute of Foundation Models", "logo": "/img/logos/mbzuai_small.svg", "color": "#1521a9", "country": "ae", "url": "https://mbzuai.ac.ae/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5aa1c578-af76-4b91-8699-cdd43582b3af", "slug": "glm-5-1", "name": "GLM-5.1 (Reasoning)", "shortName": "GLM-5.1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-07", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 3791, "release": {"slug": "glm-5-1", "name": "GLM-5.1"}, "deprecated": true, "deprecatedTo": "glm-5-2", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 744, "inferenceParametersActiveBillions": 40, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-5.1", "microevalsEnabled": true, "intelligenceIndex": 26.4455412980095, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 26.85174227203978, "strategyAndOps": 23.95841835748204, "legal": 29.319967750350706, "engineering": 30.57682285431321, "economics": 38.052795060541214}, "omniscience": 0.85, "omniscienceBreakdown": {"accuracy": 0.237, "hallucinationRate": 0.299475753604194}, "gdpPdfAllPass": 0.084, "gdpval": 1180.01, "gdpvalNormalized": 0.340005, "itBenchSre": 0.402542372881356, "tau2": 0.976608187134503, "tauBanking": 0.136082474226804, "terminalbenchHard": 0.431818181818182, "terminalBench21": 0.617977528089888, "terminalBench40": 0.0202020202020202, "scicode": 0.447916666666667, "lcr": 0.736666666666667, "ifbench": 0.762585034013605, "hle": 0.300741427247451, "gpqa": 0.867676767676768, "critpt": 0.0457142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.20308354687857075, "price1mInputTokens": 1.2, "price1mOutputTokens": 4.4, "cacheHitPrice": 0.26, "cacheHitDiscountPercent": 0.8081780538302277, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2, "price1mBlended7To2To1": 0.8620000000000001, "price1mBlended0To1To1": 2.8000000000000003, "price1mBlended100To1To1": 0.30980392156862746, "price1mBlended0To100To1": 1.2316831683168317, "intelligenceIndexTimePerTask": 850.1587361881225, "intelligenceIndexCost": {"total": 1418.3239535005598, "input": 789.8675227005598, "nonCacheInput": 16.3946676, "cacheRead": 380.1903072360153, "cacheWrite": 393.2825478645445, "output": 628.4564308, "reasoning": 542.1069896, "answer": 86.34944120000002}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.9217822401466147, "input": 0.740085104651642, "nonCacheInput": 0.008654570304905336, "cacheRead": 0.3740546519316983, "cacheWrite": 0.3573758824150383, "output": 0.18169713549497293, "reasoning": 0.1183878539043737, "answer": 0.06330928159059918}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.11576673165836036}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.04447589871004177}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.025265407549241514}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.6621933392960039}, {"slug": "scicode", "weightedCostPerTask": 0.0047307761111111115}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.016677680518999077}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.005273657200000001}, {"slug": "critpt", "weightedCostPerTask": 0.03904900914285715}, {"slug": "omniscience", "weightedCostPerTask": 0.00153614936}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0068135906}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1803668092, "output": 142831007, "answer": 19624873, "reasoning": 123206134}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 26906.330432812203, "answer": 14388.473088772542, "output": 41294.80352158475}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 964.01, "lower95ci": 957.61, "upper95ci": 970.45}, "rubricPassRate": 0.25757575757575757, "analyticalQuality": {"elo": 933.78, "lower95ci": 921.52, "upper95ci": 945.45}, "presentation": {"elo": 966.54, "lower95ci": 954.42, "upper95ci": 978.79}}, "briefcaseTotalCost": 70.23181720607195, "timescaleData": {"medianOutputSpeed": 47.3542604128075, "medianTimeToFirstChunk": 1.83741385899998}, "outputSpeedVariance": {"p05": 21.1349422801805, "q25": 29.4170762104097, "median": 47.3542604128075, "q75": 79.25684371799, "p95": 135.950644941716}, "timeToFirstChunkVariance": {"p05": 0.715994490799991, "q25": 0.982157474500013, "median": 1.83741385899998, "q75": 2.83707645799996, "p95": 15.8744485846}, "performanceByPromptType": {"long": {"medianOutputSpeed": 47.3542604128075, "medianTimeToFirstChunk": 1.83741385899998, "medianTimeToFirstAnswerToken": 81.89356861576778, "medianEndToEndResponseTime": 92.45228066493262}}, "endToEndResponseTime": {"input": 1.83741385899998, "reasoning": 80.0561547567678, "answer": 10.558712049164837, "total": 92.45228066493262}, "timeToFirstAnswerToken": {"input": 1.83741385899998, "reasoning": 80.0561547567678, "total": 81.89356861576778}, "performanceDataSource": {"type": "median"}, "hostModelCount": 7, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5ad2f60f-ee05-49fd-85a0-cef69aa7cb7b", "slug": "o1", "name": "o1", "shortName": "o1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-05", "knowledgeCutoffDate": "2023-10-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "o1", "name": "o1"}, "deprecated": true, "deprecatedTo": "o3", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 15.2309422339403, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -11.05, "omniscienceBreakdown": {"accuracy": 0.3453333333333333, "hallucinationRate": 0.6962830957230143}, "gdpval": null, "itBenchSre": null, "tau2": 0.625730994152047, "tauBanking": null, "terminalbenchHard": 0.128787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.65, "ifbench": 0.703401360544218, "hle": 0.0701, "gpqa": 0.747474747474747, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.679365079365079, "aime25": null, "analystAgent": null, "price1mInputTokens": 15, "price1mOutputTokens": 60, "cacheHitPrice": 7.5, "cacheHitDiscountPercent": 0.5, "cacheWritePrice": null, "pricePer1k1mpImages": 10.125, "price1mBlended0To3To1": 26.25, "price1mBlended7To2To1": 14.25, "price1mBlended0To1To1": 37.5, "price1mBlended100To1To1": 8.088235294117647, "price1mBlended0To100To1": 15.445544554455445, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5b2beb12-81a9-47a1-8a2a-d0a727185b50", "slug": "qwen3-max-preview", "name": "Qwen3 Max (Preview)", "shortName": "Qwen3 Max (Preview)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-05", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-max-preview", "name": "Qwen3 Max (Preview)"}, "deprecated": true, "deprecatedTo": "qwen3-max", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.5883955174617, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -42.7833333333333, "omniscienceBreakdown": {"accuracy": 0.242, "hallucinationRate": 0.8836851363236587}, "gdpval": null, "itBenchSre": null, "tau2": 0.327485380116959, "tauBanking": null, "terminalbenchHard": 0.196969696969697, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.43, "ifbench": 0.480272108843537, "hle": 0.101482854494903, "gpqa": 0.763636363636364, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.650793650793651, "aime25": 0.75, "analystAgent": null, "price1mInputTokens": 1.2, "price1mOutputTokens": 6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2.4, "price1mBlended7To2To1": 1.6800000000000002, "price1mBlended0To1To1": 3.6, "price1mBlended100To1To1": 1.2470588235294118, "price1mBlended0To100To1": 1.2475247524752475, "timescaleData": {"medianOutputSpeed": 59.8019815304255, "medianTimeToFirstChunk": 4.0779478340001}, "outputSpeedVariance": {"p05": 50.3788493252264, "q25": 54.7254209901429, "median": 59.8019815304255, "q75": 67.8289214313635, "p95": 73.3983222882052}, "timeToFirstChunkVariance": {"p05": 3.89583719459992, "q25": 3.98767207975001, "median": 4.0779478340001, "q75": 4.2975602244997, "p95": 5.38467845615002}, "performanceByPromptType": {"long": {"medianOutputSpeed": 59.8019815304255, "medianTimeToFirstChunk": 4.0779478340001, "medianTimeToFirstAnswerToken": 4.0779478340001, "medianEndToEndResponseTime": 12.438874800034071}}, "endToEndResponseTime": {"input": 4.0779478340001, "reasoning": 0, "answer": 8.36092696603397, "total": 12.438874800034071}, "timeToFirstAnswerToken": {"input": 4.0779478340001, "reasoning": 0, "total": 4.0779478340001}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5b52def2-ac9b-4465-ad80-91ea8079e253", "slug": "nvidia-nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra 550B A55B (Reasoning)", "shortName": "Nemotron 3 Ultra", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-06-04", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2275, "release": {"slug": "nemotron-3-ultra-550b-a55b", "name": "Nemotron 3 Ultra 550B A55B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 550, "inferenceParametersActiveBillions": 55, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "OpenMDW", "licenseUrl": "https://openmdw.ai/license/1-1/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "microevalsEnabled": true, "intelligenceIndex": 23.4145123422858, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 24.651468477961735, "strategyAndOps": 17.187507504053038, "legal": 27.038960029420384, "healthcareAndMedical": 23.598235038313582, "engineering": 27.66107585988309, "economics": 37.20311766295953}, "omniscience": -0.4, "omniscienceBreakdown": {"accuracy": 0.22583333333333333, "hallucinationRate": 0.2968783638320775}, "mlcrOverall": 0.111111111111111, "harveyLab": 0.81719496309162, "gdpPdfAllPass": 0.05, "gdpval": 1090.88, "gdpvalNormalized": 0.29544000000000004, "itBenchSre": null, "tau2": 0.833333333333333, "tauBanking": 0.142268041237113, "terminalbenchHard": 0.363636363636364, "terminalBench21": 0.539325842696629, "terminalBench40": 0.00505050505050505, "scicode": 0.402777777777778, "lcr": 0.793333333333333, "ifbench": 0.813605442176871, "hle": 0.284059314179796, "gpqa": 0.866666666666667, "critpt": 0.0314285714285714, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.0625, "automationBenchPartialScore": 0.02986349541593992, "enterpriseOpsGym": 0.28886899433005075, "price1mInputTokens": 0.6, "price1mOutputTokens": 2.4, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.0499999999999998, "price1mBlended7To2To1": 0.5, "price1mBlended0To1To1": 1.5, "price1mBlended100To1To1": 0.22549019607843138, "price1mBlended0To100To1": 0.6178217821782178, "intelligenceIndexTimePerTask": 149.4695305728089, "intelligenceIndexCost": {"total": 778.138151269166, "input": 508.26264166916604, "nonCacheInput": 10.235647199999999, "cacheRead": 65.97175986541694, "cacheWrite": 432.0552346037491, "output": 269.8755096, "reasoning": 225.03150960000002, "answer": 44.843999999999994}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.5791367685781732, "input": 0.5110581364742596, "nonCacheInput": 0.005870212508347456, "cacheRead": 0.06764191580025615, "cacheWrite": 0.43754600816565603, "output": 0.06807863210391353, "reasoning": 0.03612064386791989, "answer": 0.03195798823599364}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.1938230505037092}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.04073683171706976}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.01039766734376408}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.29693760821560966}, {"slug": "scicode", "weightedCostPerTask": 0.0011098904166666668}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.008939191890639481}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0030197058}, {"slug": "critpt", "weightedCostPerTask": 0.019968208285714287}, {"slug": "omniscience", "weightedCostPerTask": 0.00044252740499999986}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0037620869999999995}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1067010269, "output": 112448129, "answer": 18685000, "reasoning": 93763129}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 15050.268278299955, "answer": 13315.828431664018, "output": 28366.096709963975}, "openness": {"opennessIndex": 83.33333333333333, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "briefcaseBreakdown": {"overall": {"elo": 878.22, "lower95ci": 871.64, "upper95ci": 885.37}, "rubricPassRate": 0.2202020202020202, "analyticalQuality": {"elo": 833.68, "lower95ci": 821.8, "upper95ci": 846.41}, "presentation": {"elo": 881.57, "lower95ci": 868.68, "upper95ci": 894.19}}, "briefcaseTotalCost": 117.58598397225026, "timescaleData": {"medianOutputSpeed": 180.429890606177, "medianTimeToFirstChunk": 2.12633852850001}, "outputSpeedVariance": {"p05": 16.632626592157, "q25": 85.0879737664074, "median": 180.429890606177, "q75": 290.689723741357, "p95": 424.551786094899}, "timeToFirstChunkVariance": {"p05": 0.655595312749985, "q25": 1.00642935625004, "median": 2.12633852850001, "q75": 3.61182564374997, "p95": 21.56944998825}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 167.751268389402, "medianTimeToFirstChunk": 1.19368559999998, "medianTimeToFirstAnswerToken": 14.755431045161261, "medianEndToEndResponseTime": 17.736034439702202}, "long": {"medianOutputSpeed": 180.429890606177, "medianTimeToFirstChunk": 2.12633852850001, "medianTimeToFirstAnswerToken": 14.735114116385423, "medianEndToEndResponseTime": 17.506273586250348}, "hundredK": {"medianOutputSpeed": 194.880472712175, "medianTimeToFirstChunk": 5.33569895300002, "medianTimeToFirstAnswerToken": 17.00952121101567, "medianEndToEndResponseTime": 19.575196432557572}, "mediumParallel": {"medianOutputSpeed": 139.933565862559, "medianTimeToFirstChunk": 2.06241028799997, "medianTimeToFirstAnswerToken": 18.32012505412318, "medianEndToEndResponseTime": 21.89324917854586}}, "endToEndResponseTime": {"input": 2.12633852850001, "reasoning": 12.608775587885413, "answer": 2.771159469864926, "total": 17.506273586250348}, "timeToFirstAnswerToken": {"input": 2.12633852850001, "reasoning": 12.608775587885413, "total": 14.735114116385423}, "performanceDataSource": {"type": "median"}, "hostModelCount": 9, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5bb1f426-2d64-4d03-99fb-8041ee85c33b", "slug": "gpt-5-4-pro", "name": "GPT-5.4 Pro (xhigh)", "shortName": "GPT-5.4 Pro (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-05", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-4-pro", "name": "GPT-5.4 Pro"}, "deprecated": true, "deprecatedTo": "gpt-5-5-pro", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1050000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": null, "intelligenceIndexIsEstimated": false, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": 0.3, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 30, "price1mOutputTokens": 180, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 67.5, "price1mBlended7To2To1": 45, "price1mBlended0To1To1": 105, "price1mBlended100To1To1": 31.470588235294116, "price1mBlended0To100To1": 31.485148514851485, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5c3bdc0d-abab-4526-8079-34de4089bb4a", "slug": "longcat-2-0", "name": "LongCat 2.0", "shortName": "LongCat 2.0", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-29", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "longcat-2-0", "name": "LongCat 2.0"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1600, "inferenceParametersActiveBillions": 48, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/meituan-longcat/LongCat-2.0", "microevalsEnabled": true, "intelligenceIndex": 19.6877756610623, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 22.71335897574086, "strategyAndOps": 16.834457665681967, "legal": 23.49753778534509, "engineering": 24.63230707453567, "economics": 31.804565061992008}, "omniscience": -23.4166666666667, "omniscienceBreakdown": {"accuracy": 0.29633333333333334, "hallucinationRate": 0.7539081004263383}, "gdpPdfAllPass": 0.064, "gdpval": 964.51, "gdpvalNormalized": 0.232255, "itBenchSre": null, "tau2": null, "tauBanking": 0.131958762886598, "terminalbenchHard": null, "terminalBench21": 0.50187265917603, "terminalBench40": 0, "scicode": 0.363425925925926, "lcr": 0.65, "ifbench": null, "hle": 0.336886005560704, "gpqa": 0.77979797979798, "critpt": 0.0257142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.045339131570294025, "price1mInputTokens": 0.3, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.006, "cacheHitDiscountPercent": 0.98, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5249999999999999, "price1mBlended7To2To1": 0.1842, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.020588235294117643, "price1mBlended0To100To1": 0.3089108910891089, "intelligenceIndexCost": {"total": 220.74910559739726, "input": 49.67296559739729, "nonCacheInput": 6.0267918, "cacheRead": 11.453311377604138, "cacheWrite": 32.19286241979315, "output": 171.07613999999998, "reasoning": 152.04214199999998, "answer": 19.033998}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.05898990881433253, "input": 0.02955960854015911, "nonCacheInput": 0.00355728640657807, "cacheRead": 0.008116554630439778, "cacheWrite": 0.01788576750314126, "output": 0.029430300274173423, "reasoning": 0.017277123724919363, "answer": 0.012153176549254055}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.021922110835634796}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.00859964074171894}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.002600732353506777}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.007791087778158789}, {"slug": "scicode", "weightedCostPerTask": 0.0019957313541666666}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0034930429240037073}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0023088144}, {"slug": "critpt", "weightedCostPerTask": 0.007217721857142857}, {"slug": "omniscience", "weightedCostPerTask": 0.00143694462}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00162408195}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2036284077, "output": 142563450, "answer": 15861665, "reasoning": 126701785}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 14397.603104099471, "answer": 10127.64712437838, "output": 24525.250228477853}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 738.88, "lower95ci": 729.33, "upper95ci": 749.03}, "rubricPassRate": 0.16873706004140787, "analyticalQuality": {"elo": 581.11, "lower95ci": 562.25, "upper95ci": 599.33}, "presentation": {"elo": 798.26, "lower95ci": 780.94, "upper95ci": 815.98}}, "briefcaseTotalCost": 13.299413906951775, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "LongCat"}, "hostModelCount": 2, "creator": {"id": "45d124a1-e1be-402d-97be-7adf239b9988", "slug": "longcat", "name": "LongCat", "logo": "/img/logos/longcat_small.svg", "color": "#2adb65", "country": "cn", "url": "https://longcat.chat/platform/docs/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5c3dd927-48a3-4f3c-8045-9b135f62dfbb", "slug": "nova-lite", "name": "Nova Lite", "shortName": "Nova Lite", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-03", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "nova-lite", "name": "Nova Lite"}, "deprecated": true, "deprecatedTo": "nova-2-0-lite", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 300000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.66571545482029, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -42.1666666666667, "omniscienceBreakdown": {"accuracy": 0.098, "hallucinationRate": 0.5761271249076128}, "mlcrOverall": 0, "gdpval": null, "itBenchSre": null, "tau2": 0.175438596491228, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.19, "ifbench": 0.341496598639456, "hle": 0.0429, "gpqa": 0.433333333333333, "critpt": 0, "apexAgents": null, "mmmuPro": 0.378034682080925, "livecodebench": 0.167195767195767, "aime25": 0.07, "analystAgent": null, "price1mInputTokens": 0.06, "price1mOutputTokens": 0.24, "cacheHitPrice": 0.015, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.105, "price1mBlended7To2To1": 0.0465, "price1mBlended0To1To1": 0.15, "price1mBlended100To1To1": 0.01764705882352941, "price1mBlended0To100To1": 0.06178217821782178, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 169.579728140012, "medianTimeToFirstChunk": 0.937357919000007}, "outputSpeedVariance": {"p05": 103.327945116726, "q25": 156.156504240741, "median": 169.579728140012, "q75": 183.036573573953, "p95": 188.812232022412}, "timeToFirstChunkVariance": {"p05": 0.832147066200122, "q25": 0.892589598499967, "median": 0.937357919000007, "q75": 0.955586641000138, "p95": 1.07371312915009}, "performanceByPromptType": {"long": {"medianOutputSpeed": 169.579728140012, "medianTimeToFirstChunk": 0.937357919000007, "medianTimeToFirstAnswerToken": 0.937357919000007, "medianEndToEndResponseTime": 3.8858235492030424}}, "endToEndResponseTime": {"input": 0.937357919000007, "reasoning": 0, "answer": 2.9484656302030356, "total": 3.8858235492030424}, "timeToFirstAnswerToken": {"input": 0.937357919000007, "reasoning": 0, "total": 0.937357919000007}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5c6533f3-75a2-4109-b9a9-3623afc6b86a", "slug": "seed-oss-36b-instruct", "name": "Seed-OSS-36B-Instruct", "shortName": "Seed-OSS-36B-Instruct", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "seed-oss-36b-instruct", "name": "Seed-OSS-36B-Instruct"}, "deprecated": true, "deprecatedTo": "doubao-seed-code", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 36.2, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 512000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 12.099257907924, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -52.4666666666667, "omniscienceBreakdown": {"accuracy": 0.182, "hallucinationRate": 0.8638956805215974}, "gdpval": null, "itBenchSre": null, "tau2": 0.494152046783626, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.613333333333333, "ifbench": 0.419047619047619, "hle": 0.0987025023169602, "gpqa": 0.726262626262626, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.765079365079365, "aime25": 0.846666666666667, "analystAgent": null, "price1mInputTokens": 0.21, "price1mOutputTokens": 0.57, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.3, "price1mBlended7To2To1": 0.246, "price1mBlended0To1To1": 0.38999999999999996, "price1mBlended100To1To1": 0.21352941176470588, "price1mBlended0To100To1": 0.21356435643564356, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 35.7044252911927, "medianTimeToFirstChunk": 2.951834195}, "outputSpeedVariance": {"p05": 33.2622192408945, "q25": 34.0699239738926, "median": 35.7044252911927, "q75": 39.3597618862628, "p95": 41.7970872635789}, "timeToFirstChunkVariance": {"p05": 2.52683596870003, "q25": 2.7339094190001, "median": 2.951834195, "q75": 3.11260582899999, "p95": 3.69598805899988}, "performanceByPromptType": {"long": {"medianOutputSpeed": 35.7044252911927, "medianTimeToFirstChunk": 2.951834195, "medianTimeToFirstAnswerToken": 58.967299608284364, "medianEndToEndResponseTime": 72.97116596160545}}, "endToEndResponseTime": {"input": 2.951834195, "reasoning": 56.01546541328436, "answer": 14.00386635332109, "total": 72.97116596160545}, "timeToFirstAnswerToken": {"input": 2.951834195, "reasoning": 56.01546541328436, "total": 58.967299608284364}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "2354746c-4775-4a06-b64d-0ba4137785b8", "slug": "bytedance_seed", "name": "ByteDance Seed", "logo": "/img/logos/bytedance_small.svg", "color": "#3c8bff", "country": "cn", "url": ""}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5ce30d25-5353-45bb-bef9-6b87480ba3a2", "slug": "gpt-4-5", "name": "GPT-4.5 (Preview)", "shortName": "GPT-4.5 (Preview)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-27", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4-5-preview", "name": "GPT-4.5 (Preview)"}, "deprecated": true, "deprecatedTo": "gpt-4-1", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.57619358566713, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5d11e7a1-4f70-4e5a-9364-e193761d6757", "slug": "gpt-5-codex", "name": "GPT-5 Codex (high)", "shortName": "GPT-5 Codex (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-23", "knowledgeCutoffDate": "2024-09-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5-codex", "name": "GPT-5 Codex"}, "deprecated": true, "deprecatedTo": "gpt-5-1-codex", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 24.8818938471151, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -7.53333333333333, "omniscienceBreakdown": {"accuracy": 0.387, "hallucinationRate": 0.7542142468733007}, "gdpval": null, "itBenchSre": null, "tau2": 0.868421052631579, "tauBanking": null, "terminalbenchHard": 0.378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.716666666666667, "ifbench": 0.741496598639456, "hle": 0.278498609823911, "gpqa": 0.837373737373737, "critpt": 0.0514285714285714, "apexAgents": null, "mmmuPro": 0.738150289017341, "livecodebench": 0.84021164021164, "aime25": 0.986666666666667, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 1.3375, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.3366336633663367, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5d303dc9-c027-401f-9803-4e9aa3331007", "slug": "glm-4-5-air", "name": "GLM-4.5-Air", "shortName": "GLM-4.5-Air", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "glm-4-5-air", "name": "GLM-4.5-Air"}, "deprecated": true, "deprecatedTo": "glm-4-7-flash", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 106, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://huggingface.co/zai-org/GLM-4.5-Air", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-4.5-Air", "microevalsEnabled": false, "intelligenceIndex": 11.0889137659922, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -61.5333333333333, "omniscienceBreakdown": {"accuracy": 0.1625, "hallucinationRate": 0.9287562189054727}, "gdpval": null, "itBenchSre": null, "tau2": 0.464912280701754, "tauBanking": null, "terminalbenchHard": 0.204545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.466666666666667, "ifbench": 0.375510204081633, "hle": 0.0704355885078777, "gpqa": 0.733333333333333, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.683597883597884, "aime25": 0.806666666666667, "analystAgent": null, "price1mInputTokens": 0.17, "price1mOutputTokens": 0.98, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.3725, "price1mBlended7To2To1": 0.251, "price1mBlended0To1To1": 0.575, "price1mBlended100To1To1": 0.17794117647058827, "price1mBlended0To100To1": 0.178019801980198, "openness": {"opennessIndex": 55.55555555555556, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 62.7393094919473, "medianTimeToFirstChunk": 2.47437118799997}, "outputSpeedVariance": {"p05": 43.6853174620295, "q25": 57.9481624977008, "median": 62.7393094919473, "q75": 67.0354997049873, "p95": 79.3156869432852}, "timeToFirstChunkVariance": {"p05": 2.24149517640018, "q25": 2.33024130175005, "median": 2.47437118799997, "q75": 2.564269653, "p95": 3.16305454170003}, "performanceByPromptType": {"long": {"medianOutputSpeed": 62.7393094919473, "medianTimeToFirstChunk": 2.47437118799997, "medianTimeToFirstAnswerToken": 34.35231208654785, "medianEndToEndResponseTime": 42.32179731118482}}, "endToEndResponseTime": {"input": 2.47437118799997, "reasoning": 31.877940898547877, "answer": 7.969485224636969, "total": 42.32179731118482}, "timeToFirstAnswerToken": {"input": 2.47437118799997, "reasoning": 31.877940898547877, "total": 34.35231208654785}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5d4acc80-7a88-4e84-bfe7-99071b84e6a4", "slug": "qwen3-5-2b", "name": "Qwen3.5 2B (Reasoning)", "shortName": "Qwen3.5 2B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-5-2b", "name": "Qwen3.5 2B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 2.27, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-2B", "microevalsEnabled": false, "intelligenceIndex": 6.94413664133259, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -60.1833333333333, "omniscienceBreakdown": {"accuracy": 0.08066666666666666, "hallucinationRate": 0.7423857868020305}, "gdpval": 165.7, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.690058479532164, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": 0.0299625468164794, "terminalBench40": null, "scicode": null, "lcr": 0.21, "ifbench": 0.314965986394558, "hle": 0.025949953660797, "gpqa": 0.455555555555556, "critpt": 0, "apexAgents": null, "mmmuPro": 0.430057803468208, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5d8183dc-24f4-46c5-a1d0-d937de149364", "slug": "mimo-v2-pro", "name": "MiMo-V2-Pro", "shortName": "MiMo-V2-Pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-18", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2926, "release": {"slug": "mimo-v2-pro", "name": "MiMo-V2-Pro"}, "deprecated": true, "deprecatedTo": "mimo-v2-5-pro", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 28.6442401425214, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 4.61666666666667, "omniscienceBreakdown": {"accuracy": 0.26616666666666666, "hallucinationRate": 0.29979559391324095}, "gdpval": null, "itBenchSre": null, "tau2": 0.950292397660819, "tauBanking": null, "terminalbenchHard": 0.409090909090909, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.683333333333333, "ifbench": 0.68843537414966, "hle": 0.304448563484708, "gpqa": 0.86969696969697, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5147c8b4-61d5-4070-9324-8adf8aa144c2", "slug": "xiaomi", "name": "Xiaomi", "logo": "/img/logos/xiaomi_small.svg", "color": "#ff6900", "country": "cn", "url": "https://huggingface.co/XiaomiMiMo"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5d891609-fe1c-4e8d-b9f0-5b0ff6d9f439", "slug": "tri-21b-think-v0-5", "name": "Tri-21B-Think", "shortName": "Tri-21B-Think", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "tri-21b-think-v0-5", "name": "Tri-21B-Think"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 21, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/trillionlabs/Tri-21B-Think", "microevalsEnabled": false, "intelligenceIndex": 8.98704047108094, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -62.55, "omniscienceBreakdown": {"accuracy": 0.12333333333333334, "hallucinationRate": 0.8541825095057034}, "gdpval": null, "itBenchSre": null, "tau2": 0.809941520467836, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.156666666666667, "ifbench": 0.546258503401361, "hle": 0.0593141797961075, "gpqa": 0.601010101010101, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "75f52ad3-a524-4b44-a734-cf1f388b0b03", "slug": "trillionlabs", "name": "Trillion Labs", "logo": "/img/logos/trillionlabs_small.svg", "color": "#1f2120", "country": "kr", "url": "https://trillionlabs.co/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5da3c0e2-65d2-4bff-a410-cb2132ddafb6", "slug": "deepseek-v4-pro-0424-high", "name": "DeepSeek V4 Pro 0424 (Reasoning, High Effort)", "shortName": "DeepSeek V4 Pro (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 1992, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "deepseek-v4-pro-0424", "name": "DeepSeek V4 Pro 0424"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1600, "inferenceParametersActiveBillions": 49, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro", "microevalsEnabled": false, "intelligenceIndex": 30.1054806103209, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -10.5666666666667, "omniscienceBreakdown": {"accuracy": 0.414, "hallucinationRate": 0.8868031854379977}, "gdpval": 1218.72, "gdpvalNormalized": 0.35936, "itBenchSre": null, "tau2": 0.941520467836257, "tauBanking": 0.261855670103093, "terminalbenchHard": 0.416666666666667, "terminalBench21": 0.647940074906367, "terminalBench40": null, "scicode": null, "lcr": 0.703333333333333, "ifbench": 0.712925170068027, "hle": 0.352177942539388, "gpqa": 0.905050505050505, "critpt": 0.1, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.435, "price1mOutputTokens": 0.87, "cacheHitPrice": 0.0036, "cacheHitDiscountPercent": 0.9917241379310345, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.54375, "price1mBlended7To2To1": 0.17652, "price1mBlended0To1To1": 0.6525, "price1mBlended100To1To1": 0.016323529411764705, "price1mBlended0To100To1": 0.4393069306930693, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 86.9034577636376, "medianTimeToFirstChunk": 1.68566609049992}, "outputSpeedVariance": {"p05": 49.9209828076286, "q25": 67.0873167470682, "median": 86.9034577636376, "q75": 119.131093413273, "p95": 137.617073566683}, "timeToFirstChunkVariance": {"p05": 1.29026407374997, "q25": 1.51382536575002, "median": 1.68566609049992, "q75": 2.12455503249999, "p95": 3.24989932610001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 77.4438535081184, "medianTimeToFirstChunk": 1.06905364999997, "medianTimeToFirstAnswerToken": 26.790914194958255, "medianEndToEndResponseTime": 33.247204492387546}, "long": {"medianOutputSpeed": 86.9034577636376, "medianTimeToFirstChunk": 1.68566609049992, "medianTimeToFirstAnswerToken": 24.60765390619646, "medianEndToEndResponseTime": 30.361164904112258}, "hundredK": {"medianOutputSpeed": 86.1185317760908, "medianTimeToFirstChunk": 9.16764652900002, "medianTimeToFirstAnswerToken": 32.298556437905845, "medianEndToEndResponseTime": 38.10450772026172}, "mediumParallel": {"medianOutputSpeed": 62.7912164460723, "medianTimeToFirstChunk": 1.14490786500017, "medianTimeToFirstAnswerToken": 32.86909020682201, "medianEndToEndResponseTime": 40.831987380974084}}, "endToEndResponseTime": {"input": 1.68566609049992, "reasoning": 22.92198781569654, "answer": 5.753510997915798, "total": 30.361164904112258}, "timeToFirstAnswerToken": {"input": 1.68566609049992, "reasoning": 22.92198781569654, "total": 24.60765390619646}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 8, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5dba8d07-9992-483c-81db-dac97cb15ba8", "slug": "granite-4-0-h-small", "name": "Granite 4.0 H Small", "shortName": "Granite 4.0 H Small", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-22", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "granite-4-0-h-small", "name": "Granite 4.0 H Small"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32, "inferenceParametersActiveBillions": 9, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.0-h-small", "microevalsEnabled": false, "intelligenceIndex": 6.04930220974964, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -61.0166666666667, "omniscienceBreakdown": {"accuracy": 0.14283333333333334, "hallucinationRate": 0.8784755979000584}, "gdpval": null, "itBenchSre": null, "tau2": 0.172514619883041, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.113333333333333, "ifbench": 0.314965986394558, "hle": 0.0379981464318814, "gpqa": 0.416161616161616, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.250793650793651, "aime25": 0.136666666666667, "analystAgent": null, "price1mInputTokens": 0.06, "price1mOutputTokens": 0.25, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.1075, "price1mBlended7To2To1": 0.079, "price1mBlended0To1To1": 0.155, "price1mBlended100To1To1": 0.06186274509803921, "price1mBlended0To100To1": 0.06188118811881188, "openness": {"opennessIndex": 55.55555555555556, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {"medianOutputSpeed": 33.4289455741993, "medianTimeToFirstChunk": 15.076754332}, "outputSpeedVariance": {"p05": 12.7536945625599, "q25": 17.0241896233549, "median": 33.4289455741993, "q75": 39.9681649014209, "p95": 43.3057870948446}, "timeToFirstChunkVariance": {"p05": 11.7060112712001, "q25": 12.8405941690001, "median": 15.076754332, "q75": 29.135819968, "p95": 30.0655647108999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 14.8203327109033, "medianTimeToFirstChunk": 32.5514994915, "medianTimeToFirstAnswerToken": 32.5514994915, "medianEndToEndResponseTime": 66.28893371469735}, "long": {"medianOutputSpeed": 33.4289455741993, "medianTimeToFirstChunk": 15.076754332, "medianTimeToFirstAnswerToken": 15.076754332, "medianEndToEndResponseTime": 30.03385188358726}}, "endToEndResponseTime": {"input": 15.076754332, "reasoning": 0, "answer": 14.957097551587259, "total": 30.03385188358726}, "timeToFirstAnswerToken": {"input": 15.076754332, "reasoning": 0, "total": 15.076754332}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5e0164b3-d902-4bcb-a1b2-83b4f4cd6143", "slug": "qwen3-30b-a3b-2507-reasoning", "name": "Qwen3 30B A3B 2507 (Reasoning)", "shortName": "Qwen3 30B A3B 2507", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-30b-a3b-2507", "name": "Qwen3 30B A3B 2507"}, "deprecated": true, "deprecatedTo": "qwen3-5-35b-a3b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30.5, "inferenceParametersActiveBillions": 3.3, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-30B-A3B-Thinking-2507", "microevalsEnabled": false, "intelligenceIndex": 9.80537532870426, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 8.616337290554158, "strategyAndOps": 5.581875651288327, "legal": 9.396861568031294, "engineering": 11.735952601615253, "economics": 14.507222737102254}, "omniscience": -56.1333333333333, "omniscienceBreakdown": {"accuracy": 0.163, "hallucinationRate": 0.8653922739944245}, "gdpPdfAllPass": 0.004, "gdpval": 273.6, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.280701754385965, "tauBanking": 0.0536082474226804, "terminalbenchHard": 0.053030303030303, "terminalBench21": 0.0149812734082397, "terminalBench40": 0, "scicode": 0.329861111111111, "lcr": 0.613333333333333, "ifbench": 0.506802721088435, "hle": 0.102873030583874, "gpqa": 0.707070707070707, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.706878306878307, "aime25": 0.563333333333333, "analystAgent": null, "automationBenchPartialScore": 0.00795143729768833, "price1mInputTokens": 0.2, "price1mOutputTokens": 2.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.75, "price1mBlended7To2To1": 0.42000000000000004, "price1mBlended0To1To1": 1.3, "price1mBlended100To1To1": 0.22156862745098038, "price1mBlended0To100To1": 0.22178217821782176, "intelligenceIndexTimePerTask": 137.21477927696378, "intelligenceIndexCost": {"total": 188.3060294, "input": 27.0230558, "nonCacheInput": 2.9839604000000004, "cacheRead": 0, "cacheWrite": 24.0390954, "output": 161.2829736, "reasoning": 151.89048, "answer": 9.3924936}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.0765560533905436, "input": 0.019455053985206885, "nonCacheInput": 0.0017156023678288248, "cacheRead": 0, "cacheWrite": 0.017739451617378058, "output": 0.05710099940533671, "reasoning": 0.05205984485536595, "answer": 0.005041154549970753}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.025813394835164837}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.017175351636363637}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0022725822374429225}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.018101407575757577}, {"slug": "scicode", "weightedCostPerTask": 0.001293020138888889}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.003001851594068582}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0017238798}, {"slug": "critpt", "weightedCostPerTask": 0.005503965142857142}, {"slug": "omniscience", "weightedCostPerTask": 0.00041130942999999996}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.001259291}]}, "canonicalIntelligenceIndexTokenCount": {"input": 135115279, "output": 67201239, "answer": 3913539, "reasoning": 63287700}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 21691.602023069147, "answer": 2100.481062487814, "output": 23792.083085556962}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 31.59, "lower95ci": 20.06, "upper95ci": 42.53}, "rubricPassRate": 0.04081632653061224, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 15.6601262, "timescaleData": {"medianOutputSpeed": 155.070295238739, "medianTimeToFirstChunk": 2.39792179550001}, "outputSpeedVariance": {"p05": 111.166722560202, "q25": 135.406565865108, "median": 155.070295238739, "q75": 175.514300156886, "p95": 201.712272297493}, "timeToFirstChunkVariance": {"p05": 2.26116077185005, "q25": 2.29041782649989, "median": 2.39792179550001, "q75": 2.53114412724996, "p95": 3.06309354815001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 155.070295238739, "medianTimeToFirstChunk": 2.39792179550001, "medianTimeToFirstAnswerToken": 15.295298413767831, "medianEndToEndResponseTime": 18.519642568334785}}, "endToEndResponseTime": {"input": 2.39792179550001, "reasoning": 12.89737661826782, "answer": 3.224344154566955, "total": 18.519642568334785}, "timeToFirstAnswerToken": {"input": 2.39792179550001, "reasoning": 12.89737661826782, "total": 15.295298413767831}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5e4e4590-a77e-4b66-95f8-f3960a1a7c68", "slug": "mistral-large", "name": "Mistral Large (Feb '24)", "shortName": "Mistral Large (Feb)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-02-26", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-large", "name": "Mistral Large (Feb '24)"}, "deprecated": true, "deprecatedTo": "mistral-large-2407", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 32768, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.76443460315821, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.035, "gpqa": 0.350505050505051, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.177777777777778, "aime25": null, "analystAgent": null, "price1mInputTokens": 4, "price1mOutputTokens": 12, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 4.8, "price1mBlended0To1To1": 8, "price1mBlended100To1To1": 4.078431372549019, "price1mBlended0To100To1": 4.079207920792079, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5e5b4ce7-bc54-47b2-b911-21b9cad8394c", "slug": "qwen3-8-max-0803", "name": "Qwen3.8 Max", "shortName": "Qwen3.8 Max", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-03", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-8-max", "name": "Qwen3.8 Max"}, "deprecated": true, "deprecatedTo": "qwen3-8-max", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 40.3048623585941, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 40.570777674929936, "strategyAndOps": 42.4355139819066, "legal": 41.72842312782469, "healthcareAndMedical": 38.56583509287266, "engineering": 40.91929823630186, "economics": 48.713108510966954}, "omniscience": 3.4, "omniscienceBreakdown": {"accuracy": 0.3185, "hallucinationRate": 0.417461482024945}, "mlcrOverall": 0.194444444444444, "gdpPdfAllPass": 0.202, "gdpval": 1630.39, "gdpvalNormalized": 0.565195, "itBenchSre": null, "tau2": null, "tauBanking": 0.51340206185567, "terminalbenchHard": null, "terminalBench21": 0.812734082397004, "terminalBench40": 0.186868686868687, "scicode": 0.532407407407407, "lcr": 0.783333333333333, "ifbench": null, "hle": 0.430491195551437, "gpqa": 0.927272727272727, "critpt": 0.2, "apexAgents": null, "mmmuPro": 0.823121387283237, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.4923210407553669, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.875, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.175, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 0.3235294117647059, "price1mBlended0To100To1": 2.0396039603960396, "intelligenceIndexTimePerTask": 1203.093758691901, "intelligenceIndexCost": {"total": 3172.372633045391, "input": 2091.885265045391, "nonCacheInput": 54.3953, "cacheRead": 1216.4002678506583, "cacheWrite": 821.0896971947328, "output": 1080.487368, "reasoning": 905.3541180000001, "answer": 175.13325}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.6699848505343478, "input": 2.2932952115870577, "nonCacheInput": 0.039074993621839, "cacheRead": 1.3993773418729452, "cacheWrite": 0.8548428760922733, "output": 0.3766896389472899, "reasoning": 0.26157414335246226, "answer": 0.1151154955948277}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.6383096946279455}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.2744154760597994}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.026633172307731216}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.5983454376504405}, {"slug": "scicode", "weightedCostPerTask": 0.011063102083333333}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.02234424550509731}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.032558765999999996}, {"slug": "critpt", "weightedCostPerTask": 0.05092279999999999}, {"slug": "omniscience", "weightedCostPerTask": 0.0043028923}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.011089264}]}, "canonicalIntelligenceIndexTokenCount": {"input": 5303343570, "output": 180081228, "answer": 29188875, "reasoning": 150892353}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 43595.69055874371, "answer": 19185.915932471282, "output": 62781.60649121499}, "briefcaseBreakdown": {"overall": {"elo": 1387.89, "lower95ci": 1381.72, "upper95ci": 1394.93}, "rubricPassRate": 0.49595959595959593, "analyticalQuality": {"elo": 1525.04, "lower95ci": 1512.66, "upper95ci": 1537.58}, "presentation": {"elo": 1266.38, "lower95ci": 1253.82, "upper95ci": 1278.93}}, "briefcaseTotalCost": 387.24121474095364, "timescaleData": {"medianOutputSpeed": 40.6266932270713, "medianTimeToFirstChunk": 2.5874327235}, "outputSpeedVariance": {"p05": 36.1393950802554, "q25": 37.9911862804479, "median": 40.6266932270713, "q75": 43.5725003120541, "p95": 45.1582500781828}, "timeToFirstChunkVariance": {"p05": 2.30834535675, "q25": 2.4290673695001, "median": 2.5874327235, "q75": 2.74120736774998, "p95": 3.10945515345006}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 40.2592323108317, "medianTimeToFirstChunk": 1.78817239, "medianTimeToFirstAnswerToken": 51.466218522586146, "medianEndToEndResponseTime": 63.88573005573269}, "long": {"medianOutputSpeed": 40.6266932270713, "medianTimeToFirstChunk": 2.5874327235, "medianTimeToFirstAnswerToken": 51.816150129112394, "medianEndToEndResponseTime": 64.1233294805155}, "hundredK": {"medianOutputSpeed": 55.4139732388495, "medianTimeToFirstChunk": 8.58474387449985, "medianTimeToFirstAnswerToken": 44.67672362443492, "medianEndToEndResponseTime": 53.69971856191869}, "mediumParallel": {"medianOutputSpeed": 37.7456922150427, "medianTimeToFirstChunk": 1.78022524999994, "medianTimeToFirstAnswerToken": 54.766404139122145, "medianEndToEndResponseTime": 68.0129488614027}}, "endToEndResponseTime": {"input": 2.5874327235, "reasoning": 49.22871740561239, "answer": 12.307179351403098, "total": 64.1233294805155}, "timeToFirstAnswerToken": {"input": 2.5874327235, "reasoning": 49.22871740561239, "total": 51.816150129112394}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5e8b0d98-a3b4-42b5-93d8-ecb748788754", "slug": "grok-4-3-medium", "name": "Grok 4.3 (medium)", "shortName": "Grok 4.3 (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "grok-4-3", "name": "Grok 4.3"}, "deprecated": true, "deprecatedTo": "grok-4-6-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 24.7816938151637, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 16.7, "omniscienceBreakdown": {"accuracy": 0.2876666666666667, "hallucinationRate": 0.16939635002339729}, "gdpval": null, "itBenchSre": null, "tau2": 0.912280701754386, "tauBanking": null, "terminalbenchHard": 0.303030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.75, "ifbench": 0.833333333333333, "hle": 0.299814643188137, "gpqa": 0.88989898989899, "critpt": 0.0485714285714286, "apexAgents": null, "mmmuPro": 0.758381502890173, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 2.5, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.84, "cacheWritePrice": 1.25, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5625, "price1mBlended7To2To1": 0.64, "price1mBlended0To1To1": 1.875, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.2623762376237624, "timescaleData": {"medianOutputSpeed": 108.038592545934, "medianTimeToFirstChunk": 14.06724794}, "outputSpeedVariance": {"p05": 86.2777199959833, "q25": 96.9869812220019, "median": 108.038592545934, "q75": 133.905400467141, "p95": 163.408202814033}, "timeToFirstChunkVariance": {"p05": 4.78441682610006, "q25": 6.81592673225001, "median": 14.06724794, "q75": 19.9848804640001, "p95": 32.97836336545}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 124.331565464599, "medianTimeToFirstChunk": 21.950410419, "medianTimeToFirstAnswerToken": 21.950410419, "medianEndToEndResponseTime": 25.971915321086716}, "long": {"medianOutputSpeed": 108.038592545934, "medianTimeToFirstChunk": 14.06724794, "medianTimeToFirstAnswerToken": 14.06724794, "medianEndToEndResponseTime": 18.695223816189042}, "hundredK": {"medianOutputSpeed": 104.993767653121, "medianTimeToFirstChunk": 14.2821292655, "medianTimeToFirstAnswerToken": 14.2821292655, "medianEndToEndResponseTime": 19.044316690299375}, "mediumParallel": {"medianOutputSpeed": 107.222651320066, "medianTimeToFirstChunk": 19.0582816484999, "medianTimeToFirstAnswerToken": 19.0582816484999, "medianEndToEndResponseTime": 23.721475421870323}}, "endToEndResponseTime": {"input": 14.06724794, "reasoning": 0, "answer": 4.627975876189044, "total": 18.695223816189042}, "timeToFirstAnswerToken": {"input": 14.06724794, "reasoning": 0, "total": 14.06724794}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 3, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5e965af0-ca5c-4f47-9ba9-06000508b84a", "slug": "gpt-5-medium", "name": "GPT-5 (medium)", "shortName": "GPT-5 (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-09-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-5", "name": "GPT-5"}, "deprecated": true, "deprecatedTo": "gpt-5-1", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 22.869335846124, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -10.8666666666667, "omniscienceBreakdown": {"accuracy": 0.3948333333333333, "hallucinationRate": 0.8320022032497935}, "gdpval": null, "itBenchSre": null, "tau2": 0.865497076023392, "tauBanking": null, "terminalbenchHard": 0.378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.76, "ifbench": 0.706122448979592, "hle": 0.253938832252085, "gpqa": 0.841750841750842, "critpt": 0, "apexAgents": null, "mmmuPro": 0.743352601156069, "livecodebench": 0.702645502645503, "aime25": 0.916666666666667, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.788, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 1.3375, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.3366336633663367, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 80.4823761914574, "medianTimeToFirstChunk": 30.7901045305}, "outputSpeedVariance": {"p05": 35.8279199983425, "q25": 53.0150784417169, "median": 80.4823761914574, "q75": 99.977800761417, "p95": 139.126689761926}, "timeToFirstChunkVariance": {"p05": 11.8854215534, "q25": 21.81720218575, "median": 30.7901045305, "q75": 61.6814221199999, "p95": 118.6151625315}, "performanceByPromptType": {"long": {"medianOutputSpeed": 80.4823761914574, "medianTimeToFirstChunk": 30.7901045305, "medianTimeToFirstAnswerToken": 30.7901045305, "medianEndToEndResponseTime": 37.002644761799374}}, "endToEndResponseTime": {"input": 30.7901045305, "reasoning": 0, "answer": 6.212540231299374, "total": 37.002644761799374}, "timeToFirstAnswerToken": {"input": 30.7901045305, "reasoning": 0, "total": 30.7901045305}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5ea94a4a-55ac-4ea1-8898-2b3971e94af6", "slug": "grok-4", "name": "Grok 4", "shortName": "Grok 4", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "grok-4", "name": "Grok 4"}, "deprecated": true, "deprecatedTo": "grok-4-20-0309", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 22.4866809354881, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 2.1, "omniscienceBreakdown": {"accuracy": 0.4048333333333333, "hallucinationRate": 0.6449173900868104}, "gdpval": null, "itBenchSre": null, "tau2": 0.7485380117, "tauBanking": null, "terminalbenchHard": 0.378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.68, "ifbench": 0.536734693877551, "hle": 0.266913809082484, "gpqa": 0.876767676767677, "critpt": 0.02, "apexAgents": null, "mmmuPro": 0.688439306358381, "livecodebench": 0.819047619047619, "aime25": 0.926666666666667, "analystAgent": null, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 4.2, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 3.1176470588235294, "price1mBlended0To100To1": 3.118811881188119, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5ec4a0db-da66-4e46-9682-fceeed755ef8", "slug": "sonar", "name": "Sonar", "shortName": "Sonar", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-21", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "sonar", "name": "Sonar"}, "deprecated": true, "deprecatedTo": "sonar-reasoning-pro", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 127000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.70971507200974, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0488, "gpqa": 0.470707070707071, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.295238095238095, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "941fc0f0-1d4e-405a-95b2-2d49494e0e6c", "slug": "perplexity", "name": "Perplexity", "logo": "/img/logos/perplexity.svg", "color": "#1B818E", "country": "us", "url": "https://perplexity.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "5fb47ff6-a30e-4c2c-96f2-55e95a13390f", "slug": "llama-3-2-instruct-11b-vision", "name": "Llama 3.2 Instruct 11B (Vision)", "shortName": "Llama 3.2 11B (Vision)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-25", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-2-instruct-11b-vision", "name": "Llama 3.2 Instruct 11B (Vision)"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 11, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.2 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Llama-3.2-11B-Vision-Instruct", "microevalsEnabled": false, "intelligenceIndex": 5.40802026647316, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -62.6, "omniscienceBreakdown": {"accuracy": 0.106, "hallucinationRate": 0.8187919463087249}, "gdpval": null, "itBenchSre": null, "tau2": 0.146198830409357, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.126666666666667, "ifbench": 0.304081632653061, "hle": 0.0553, "gpqa": 0.221212121212121, "critpt": 0, "apexAgents": null, "mmmuPro": 0.293063583815029, "livecodebench": 0.11005291005291, "aime25": 0.0166666666666667, "analystAgent": null, "price1mInputTokens": 0.345, "price1mOutputTokens": 0.345, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.352, "price1mBlended0To3To1": 0.345, "price1mBlended7To2To1": 0.34500000000000003, "price1mBlended0To1To1": 0.345, "price1mBlended100To1To1": 0.345, "price1mBlended0To100To1": 0.345, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 18.6919866388856, "medianTimeToFirstChunk": 1.266159182}, "outputSpeedVariance": {"p05": 6.20866092993068, "q25": 11.7137494464891, "median": 18.6919866388856, "q75": 28.4442736972956, "p95": 52.8867207552694}, "timeToFirstChunkVariance": {"p05": 0.978960801350019, "q25": 1.09364508399997, "median": 1.266159182, "q75": 1.71900051950007, "p95": 2.89116004325001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 20.0828863680989, "medianTimeToFirstChunk": 0.568297918000013, "medianTimeToFirstAnswerToken": 0.568297918000013, "medianEndToEndResponseTime": 25.465117570091255}, "long": {"medianOutputSpeed": 18.6919866388856, "medianTimeToFirstChunk": 1.266159182, "medianTimeToFirstAnswerToken": 1.266159182, "medianEndToEndResponseTime": 28.015589815543915}, "hundredK": {"medianOutputSpeed": 14.7664629480694, "medianTimeToFirstChunk": 20.244961144, "medianTimeToFirstAnswerToken": 20.244961144, "medianEndToEndResponseTime": 54.105473424997605}, "mediumParallel": {"medianOutputSpeed": 18.0007902257725, "medianTimeToFirstChunk": 0.656325162999792, "medianTimeToFirstAnswerToken": 0.656325162999792, "medianEndToEndResponseTime": 28.4328835100955}}, "endToEndResponseTime": {"input": 1.266159182, "reasoning": 0, "answer": 26.749430633543916, "total": 28.015589815543915}, "timeToFirstAnswerToken": {"input": 1.266159182, "reasoning": 0, "total": 1.266159182}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6000145b-0e3d-4fef-a55f-bcaac84803b2", "slug": "deepseek-r1-qwen3-8b", "name": "DeepSeek R1 0528 Qwen3 8B", "shortName": "DeepSeek R1 0528 Qwen3 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-29", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-r1-qwen3-8b", "name": "DeepSeek R1 0528 Qwen3 8B"}, "deprecated": true, "deprecatedTo": "deepseek-v3-0324", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8.19, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B", "microevalsEnabled": false, "intelligenceIndex": 8.07891570839329, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -63.6166666666667, "omniscienceBreakdown": {"accuracy": 0.122, "hallucinationRate": 0.8635155656795748}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.15, "ifbench": 0.198639455782313, "hle": 0.0593141797961075, "gpqa": 0.612121212121212, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.513227513227513, "aime25": 0.636666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 47.22222222222222, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6000692c-f9a6-47f8-a5c0-e0874ac488bb", "slug": "qwen3-6-max", "name": "Qwen3.6 Max Preview", "shortName": "Qwen3.6 Max Preview", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-6-max", "name": "Qwen3.6 Max Preview"}, "deprecated": true, "deprecatedTo": "qwen3-7-max", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 28.3748690464685, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 9.16666666666667, "omniscienceBreakdown": {"accuracy": 0.37866666666666665, "hallucinationRate": 0.4619098712446352}, "gdpval": null, "itBenchSre": null, "tau2": 0.95906432748538, "tauBanking": null, "terminalbenchHard": 0.439393939393939, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.806666666666667, "ifbench": 0.765986394557823, "hle": 0.308155699721965, "gpqa": 0.887878787878788, "critpt": 0.0370612244897959, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.3, "price1mOutputTokens": 7.8, "cacheHitPrice": 0.13, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 1.625, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2.925, "price1mBlended7To2To1": 1.131, "price1mBlended0To1To1": 4.55, "price1mBlended100To1To1": 0.21666666666666667, "price1mBlended0To100To1": 1.3643564356435645, "timescaleData": {"medianOutputSpeed": 63.5867848388054, "medianTimeToFirstChunk": 3.36654492449998}, "outputSpeedVariance": {"p05": 49.7542477936829, "q25": 59.0690142947904, "median": 63.5867848388054, "q75": 67.7332346211239, "p95": 74.1805532665297}, "timeToFirstChunkVariance": {"p05": 2.85206778549983, "q25": 2.97313451300006, "median": 3.36654492449998, "q75": 3.94769556999988, "p95": 8.59988861304999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 63.5867848388054, "medianTimeToFirstChunk": 3.36654492449998, "medianTimeToFirstAnswerToken": 34.81962129988311, "medianEndToEndResponseTime": 42.68289039372888}}, "endToEndResponseTime": {"input": 3.36654492449998, "reasoning": 31.453076375383127, "answer": 7.863269093845782, "total": 42.68289039372888}, "timeToFirstAnswerToken": {"input": 3.36654492449998, "reasoning": 31.453076375383127, "total": 34.81962129988311}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6056731b-c705-455b-aa0d-43cbf29b1054", "slug": "longcat-flash-lite", "name": "LongCat Flash Lite", "shortName": "LongCat Flash Lite", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "longcat-flash-lite", "name": "LongCat Flash Lite"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 68.5, "inferenceParametersActiveBillions": 3, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/meituan-longcat/LongCat-Flash-Lite", "microevalsEnabled": false, "intelligenceIndex": 11.4709079965186, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -70.0666666666667, "omniscienceBreakdown": {"accuracy": 0.133, "hallucinationRate": 0.9615532487504805}, "gdpval": null, "itBenchSre": null, "tau2": 0.795321637426901, "tauBanking": null, "terminalbenchHard": 0.106060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.283333333333333, "ifbench": 0.430612244897959, "hle": 0.0583873957367933, "gpqa": 0.636363636363636, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "45d124a1-e1be-402d-97be-7adf239b9988", "slug": "longcat", "name": "LongCat", "logo": "/img/logos/longcat_small.svg", "color": "#2adb65", "country": "cn", "url": "https://longcat.chat/platform/docs/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "60cff809-05fb-4439-afe7-8b1476439f49", "slug": "tri-21b-think-preview", "name": "Tri-21B-think Preview", "shortName": "Tri-21B-think Preview", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "tri-21b-think-preview", "name": "Tri-21B-think Preview"}, "deprecated": true, "deprecatedTo": "tri-21b-think-v0-5", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 21, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/trillionlabs/Tri-21B-Think-Preview", "microevalsEnabled": false, "intelligenceIndex": 9.59191548491904, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -62.3, "omniscienceBreakdown": {"accuracy": 0.101, "hallucinationRate": 0.8053392658509455}, "gdpval": null, "itBenchSre": null, "tau2": 0.932748538011696, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.216666666666667, "ifbench": 0.471428571428571, "hle": 0.0579240037071362, "gpqa": 0.538383838383838, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "75f52ad3-a524-4b44-a734-cf1f388b0b03", "slug": "trillionlabs", "name": "Trillion Labs", "logo": "/img/logos/trillionlabs_small.svg", "color": "#1f2120", "country": "kr", "url": "https://trillionlabs.co/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "61bd9367-e520-4ec8-989e-5fbf50e61610", "slug": "nova-2-0-lite-reasoning", "name": "Nova 2.0 Lite (high)", "shortName": "Nova 2.0 Lite (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-29", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "nova-2-0-lite", "name": "Nova 2.0 Lite"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 13.3740793005281, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.9833333333333, "omniscienceBreakdown": {"accuracy": 0.19033333333333333, "hallucinationRate": 0.9141622066694113}, "gdpval": 535.99, "gdpvalNormalized": 0.017995000000000004, "itBenchSre": null, "tau2": 0.728070175438596, "tauBanking": null, "terminalbenchHard": 0.166666666666667, "terminalBench21": 0.161048689138577, "terminalBench40": null, "scicode": null, "lcr": 0.603333333333333, "ifbench": 0.707482993197279, "hle": 0.11631139944393, "gpqa": 0.811111111111111, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.63757225433526, "livecodebench": 0.711111111111111, "aime25": 0.943333333333333, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.52, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.32156862745098036, "price1mBlended0To100To1": 0.3217821782178218, "timescaleData": {"medianOutputSpeed": 161.912843733664, "medianTimeToFirstChunk": 14.6159058965}, "outputSpeedVariance": {"p05": 120.485570926928, "q25": 141.170499263182, "median": 161.912843733664, "q75": 185.038409653695, "p95": 233.690425061929}, "timeToFirstChunkVariance": {"p05": 6.9679448576, "q25": 10.13920775125, "median": 14.6159058965, "q75": 19.55506971675, "p95": 26.4903237765999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 188.37688540784, "medianTimeToFirstChunk": 12.3104042295, "medianTimeToFirstAnswerToken": 22.92741807209516, "medianEndToEndResponseTime": 25.581671532743954}, "long": {"medianOutputSpeed": 161.912843733664, "medianTimeToFirstChunk": 14.6159058965, "medianTimeToFirstAnswerToken": 26.968230479779315, "medianEndToEndResponseTime": 30.056311625599143}, "hundredK": {"medianOutputSpeed": 197.923883459221, "medianTimeToFirstChunk": 13.1337428105, "medianTimeToFirstAnswerToken": 23.2386375055966, "medianEndToEndResponseTime": 25.764861179370747}, "mediumParallel": {"medianOutputSpeed": 198.842273278376, "medianTimeToFirstChunk": 17.0659065035, "medianTimeToFirstAnswerToken": 27.124129873336614, "medianEndToEndResponseTime": 29.638685715795766}}, "endToEndResponseTime": {"input": 14.6159058965, "reasoning": 12.352324583279314, "answer": 3.0880811458198285, "total": 30.056311625599143}, "timeToFirstAnswerToken": {"input": 14.6159058965, "reasoning": 12.352324583279314, "total": 26.968230479779315}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 2, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "62de31e8-a1a3-429c-b634-a2afccfd9363", "slug": "gemini-2-5-pro-03-25", "name": "Gemini 2.5 Pro Preview (Mar' 25)", "shortName": "Gemini 2.5 Pro (Mar)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-25", "knowledgeCutoffDate": "2025-01-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-pro-03-25", "name": "Gemini 2.5 Pro Preview (Mar' 25)"}, "deprecated": true, "deprecatedTo": "gemini-2-5-pro", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 14.9609881454387, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.180259499536608, "gpqa": 0.836363636363636, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.777777777777778, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "63872e9c-3377-4a6b-b477-7bba244c38e9", "slug": "nvidia-nemotron-3-super-120b-a12b", "name": "Nemotron 3 Super 120B A12B (Reasoning)", "shortName": "Nemotron 3 Super", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "nvidia-nemotron-3-super-120b-a12b", "name": "Nemotron 3 Super 120B A12B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 120.6, "inferenceParametersActiveBillions": 12.7, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": "Nvidia Nemotron Open Model License", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "microevalsEnabled": false, "intelligenceIndex": 13.5508075290979, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 14.239587197292305, "strategyAndOps": 10.378287986271417, "legal": 13.698990451439318, "healthcareAndMedical": 11.667046805563352, "engineering": 17.747473010724214, "economics": 21.461882858356493}, "omniscience": -41.5, "omniscienceBreakdown": {"accuracy": 0.24316666666666667, "hallucinationRate": 0.869632239594803}, "mlcrOverall": 0.0333333333333333, "gdpPdfAllPass": 0.026, "gdpval": 644.41, "gdpvalNormalized": 0.07220499999999998, "itBenchSre": 0.0112994350282486, "tau2": 0.678362573099415, "tauBanking": 0.103092783505155, "terminalbenchHard": 0.287878787878788, "terminalBench21": 0.385767790262172, "terminalBench40": 0, "scicode": 0.362268518518519, "lcr": 0.656666666666667, "ifbench": 0.714965986394558, "hle": 0.207599629286376, "gpqa": 0.8, "critpt": 0.0314285714285714, "apexAgents": 0.0184365781710914, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.037790306947452605, "enterpriseOpsGym": 0.23545210384959714, "price1mInputTokens": 0.1925, "price1mOutputTokens": 0.65, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.306875, "price1mBlended7To2To1": 0.23825000000000002, "price1mBlended0To1To1": 0.42125, "price1mBlended100To1To1": 0.19698529411764704, "price1mBlended0To100To1": 0.197029702970297, "intelligenceIndexTimePerTask": 781.8006046602013, "intelligenceIndexCost": {"total": 858.61137775, "input": 746.54243895, "nonCacheInput": 2.548870555, "cacheRead": 0, "cacheWrite": 743.993568395, "output": 112.06893880000001, "reasoning": 89.50399250000001, "answer": 22.564946300000003}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.0599863852193983, "input": 0.9860017454872753, "nonCacheInput": 0.0013185307891178497, "cacheRead": 0, "cacheWrite": 0.9846832146981574, "output": 0.07398463973212283, "reasoning": 0.04358856306238122, "answer": 0.030396076669741624}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.8757007478324177}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.035141771905681816}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0072908509391171996}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.13318761489015152}, {"slug": "scicode", "weightedCostPerTask": 0.00017847222135416668}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002358565922729379}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0007497548274999999}, {"slug": "critpt", "weightedCostPerTask": 0.003953039903571429}, {"slug": "omniscience", "weightedCostPerTask": 0.00022514604687500002}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0012004207300000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 3878142540, "output": 172413752, "answer": 34715302, "reasoning": 137698450}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 67059.32778827878, "answer": 46763.194876525566, "output": 113822.52266480435}, "openness": {"opennessIndex": 83.33333333333333, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "briefcaseBreakdown": {"overall": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "rubricPassRate": 0.006060606060606061, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 531.2584536850001, "timescaleData": {"medianOutputSpeed": 139.862192380659, "medianTimeToFirstChunk": 2.38062433200002}, "outputSpeedVariance": {"p05": 66.6146584303371, "q25": 88.244836282376, "median": 139.862192380659, "q75": 233.376154462607, "p95": 442.99093390962}, "timeToFirstChunkVariance": {"p05": 1.68717639549997, "q25": 1.82220850200002, "median": 2.38062433200002, "q75": 8.02351742049995, "p95": 71.9580463367999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 138.967895073696, "medianTimeToFirstChunk": 2.1012446095, "medianTimeToFirstAnswerToken": 16.49305790522115, "medianEndToEndResponseTime": 20.091011229151437}, "long": {"medianOutputSpeed": 139.862192380659, "medianTimeToFirstChunk": 2.38062433200002, "medianTimeToFirstAnswerToken": 16.6804144751193, "medianEndToEndResponseTime": 20.255362010899123}, "hundredK": {"medianOutputSpeed": 266.642619756842, "medianTimeToFirstChunk": 8.15067493050003, "medianTimeToFirstAnswerToken": 15.651351310832062, "medianEndToEndResponseTime": 17.52652040591507}, "mediumParallel": {"medianOutputSpeed": 208.697339912368, "medianTimeToFirstChunk": 1.82421562699983, "medianTimeToFirstAnswerToken": 11.407471459775657, "medianEndToEndResponseTime": 13.803285417969615}}, "endToEndResponseTime": {"input": 2.38062433200002, "reasoning": 14.29979014311928, "answer": 3.57494753577982, "total": 20.255362010899123}, "timeToFirstAnswerToken": {"input": 2.38062433200002, "reasoning": 14.29979014311928, "total": 16.6804144751193}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "641a073a-41c9-4773-9b02-d965c16607c5", "slug": "minicpm5-2b", "name": "MiniCPM5-2B", "shortName": "MiniCPM5-2B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-07", "knowledgeCutoffDate": "2025-12-31", "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "minicpm5-2b", "name": "MiniCPM5-2B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 2.6, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/openbmb/MiniCPM5-2B", "microevalsEnabled": false, "intelligenceIndex": 13.137054831996, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 11.969005445652371, "strategyAndOps": 7.044485628623033, "legal": 16.70502521757874, "engineering": 19.209427068714422, "economics": 24.138817327000307}, "omniscience": -11.65, "omniscienceBreakdown": {"accuracy": 0.08416666666666667, "hallucinationRate": 0.21910828025477708}, "gdpPdfAllPass": 0.014, "gdpval": 827.51, "gdpvalNormalized": 0.16375499999999998, "itBenchSre": null, "tau2": null, "tauBanking": 0.208247422680412, "terminalbenchHard": null, "terminalBench21": 0.0861423220973783, "terminalBench40": 0, "scicode": 0.262731481481481, "lcr": 0.593333333333333, "ifbench": null, "hle": 0.0894346617238184, "gpqa": 0.702020202020202, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.018006007862431707, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "canonicalIntelligenceIndexTokenCount": {"input": 1578977833, "output": 74075934, "answer": 13416585, "reasoning": 60659349}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 12481.48011270575, "answer": 9334.660691818219, "output": 21816.14080452397}, "openness": {"opennessIndex": 66.66666666666667, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "briefcaseBreakdown": {"overall": {"elo": 433.52, "lower95ci": 422.33, "upper95ci": 444.66}, "rubricPassRate": 0.07272727272727272, "analyticalQuality": {"elo": 168.81, "lower95ci": 146.72, "upper95ci": 191.21}, "presentation": {"elo": 499.07, "lower95ci": 477.12, "upper95ci": 519.6}}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "7399e4ac-f64d-4be6-b649-2fc20756839f", "slug": "openbmb", "name": "OpenBMB", "logo": "/img/logos/openbmb_small.svg", "color": "#3B62EC", "country": "cn", "url": "https://www.openbmb.cn/en/home"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "64312f37-3701-4243-a4c9-7c07a58cd6b9", "slug": "grok-4-20-non-reasoning", "name": "Grok 4.20 0309 v2 (Non-reasoning)", "shortName": "Grok 4.20 0309 v2 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-07", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "grok-4-20", "name": "Grok 4.20 0309 v2"}, "deprecated": true, "deprecatedTo": "grok-4-3-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 14.2010039023924, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -44.6333333333333, "omniscienceBreakdown": {"accuracy": 0.2668333333333333, "hallucinationRate": 0.9727210729711298}, "gdpval": null, "itBenchSre": null, "tau2": 0.599415204678363, "tauBanking": null, "terminalbenchHard": 0.166666666666667, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.233333333333333, "ifbench": 0.493197278911565, "hle": 0.279425393883225, "gpqa": 0.775757575757576, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.649132947976879, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 2.5, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.84, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5625, "price1mBlended7To2To1": 0.64, "price1mBlended0To1To1": 1.875, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.2623762376237624, "timescaleData": {"medianOutputSpeed": 99.8759260236295, "medianTimeToFirstChunk": 0.574409843999945}, "outputSpeedVariance": {"p05": 70.252906345359, "q25": 90.4990730338152, "median": 99.8759260236295, "q75": 113.827748078677, "p95": 135.584295549741}, "timeToFirstChunkVariance": {"p05": 0.505193624950072, "q25": 0.536750160249966, "median": 0.574409843999945, "q75": 0.618255218499968, "p95": 0.783996654200046}, "performanceByPromptType": {"long": {"medianOutputSpeed": 99.8759260236295, "medianTimeToFirstChunk": 0.574409843999945, "medianTimeToFirstAnswerToken": 0.574409843999945, "medianEndToEndResponseTime": 5.580621249556332}}, "endToEndResponseTime": {"input": 0.574409843999945, "reasoning": 0, "answer": 5.006211405556387, "total": 5.580621249556332}, "timeToFirstAnswerToken": {"input": 0.574409843999945, "reasoning": 0, "total": 0.574409843999945}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 1, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "651ef7ae-9a8f-477e-9c8e-460aa156ba02", "slug": "qwen3-5-4b", "name": "Qwen3.5 4B (Reasoning)", "shortName": "Qwen3.5 4B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-5-4b", "name": "Qwen3.5 4B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 4.66, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-4B", "microevalsEnabled": false, "intelligenceIndex": 13.1248174602542, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -58.35, "omniscienceBreakdown": {"accuracy": 0.15116666666666667, "hallucinationRate": 0.8655016689573924}, "gdpval": null, "itBenchSre": null, "tau2": 0.921052631578947, "tauBanking": 0.0680412371134021, "terminalbenchHard": 0.181818181818182, "terminalBench21": 0.258426966292135, "terminalBench40": null, "scicode": null, "lcr": 0.63, "ifbench": 0.519727891156463, "hle": 0.0991658943466172, "gpqa": 0.770707070707071, "critpt": 0, "apexAgents": null, "mmmuPro": 0.653757225433526, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.03, "price1mOutputTokens": 0.15, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.06, "price1mBlended7To2To1": 0.042, "price1mBlended0To1To1": 0.09, "price1mBlended100To1To1": 0.03117647058823529, "price1mBlended0To100To1": 0.031188118811881188, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 17.5888891600316, "medianTimeToFirstChunk": 0.745718431}, "outputSpeedVariance": {"p05": 9.20665225816752, "q25": 12.3299549709938, "median": 17.5888891600316, "q75": 26.5877153935958, "p95": 53.635567163965}, "timeToFirstChunkVariance": {"p05": 0.642732604899982, "q25": 0.664505312000017, "median": 0.745718431, "q75": 0.825969412999996, "p95": 1.27193336519997}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 24.7145471176098, "medianTimeToFirstChunk": 0.485086496000008, "medianTimeToFirstAnswerToken": 81.409086053125, "medianEndToEndResponseTime": 101.64008594240623}, "long": {"medianOutputSpeed": 17.5888891600316, "medianTimeToFirstChunk": 0.745718431, "medianTimeToFirstAnswerToken": 114.45386576214203, "medianEndToEndResponseTime": 142.88090259492753}, "hundredK": {"medianOutputSpeed": 28.8462938396395, "medianTimeToFirstChunk": 5.59083436, "medianTimeToFirstAnswerToken": 74.92383121284612, "medianEndToEndResponseTime": 92.25708042605766}, "mediumParallel": {"medianOutputSpeed": 16.434975286442, "medianTimeToFirstChunk": 0.58396916900017, "medianTimeToFirstAnswerToken": 122.27566417567876, "medianEndToEndResponseTime": 152.6985879273484}}, "endToEndResponseTime": {"input": 0.745718431, "reasoning": 113.70814733114203, "answer": 28.427036832785507, "total": 142.88090259492753}, "timeToFirstAnswerToken": {"input": 0.745718431, "reasoning": 113.70814733114203, "total": 114.45386576214203}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "660965b2-66d2-49ee-a6b9-79a6ac47d3c0", "slug": "magistral-medium", "name": "Magistral Medium 1", "shortName": "Magistral Medium 1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "magistral-medium", "name": "Magistral Medium 1"}, "deprecated": true, "deprecatedTo": "magistral-medium-2509", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 40000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.05394062240647, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -26.9333333333333, "omniscienceBreakdown": {"accuracy": 0.20333333333333334, "hallucinationRate": 0.5933054393305439}, "gdpval": null, "itBenchSre": null, "tau2": 0.230994152046784, "tauBanking": null, "terminalbenchHard": 0.0909090909090909, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.251020408163265, "hle": 0.0982391102873031, "gpqa": 0.678787878787879, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.526984126984127, "aime25": 0.403333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "66445f84-b2e3-4202-afdc-92ba0f0e5f36", "slug": "kimi-k2-0905", "name": "Kimi K2 0905", "shortName": "Kimi K2 0905", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-05", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "kimi-k2-0905", "name": "Kimi K2 0905"}, "deprecated": true, "deprecatedTo": "kimi-k2-5-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1000, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Modified MIT License", "licenseUrl": "https://huggingface.co/moonshotai/Kimi-K2-Instruct/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905", "microevalsEnabled": false, "intelligenceIndex": 15.2941620102232, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -26.5833333333333, "omniscienceBreakdown": {"accuracy": 0.25416666666666665, "hallucinationRate": 0.6972067039106146}, "gdpval": null, "itBenchSre": null, "tau2": 0.733918128654971, "tauBanking": null, "terminalbenchHard": 0.234848484848485, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.53, "ifbench": 0.417006802721088, "hle": 0.0639481000926784, "gpqa": 0.766666666666667, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.60952380952381, "aime25": 0.573333333333333, "analystAgent": null, "price1mInputTokens": 0.6, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.075, "price1mBlended7To2To1": 0.79, "price1mBlended0To1To1": 1.55, "price1mBlended100To1To1": 0.6186274509803922, "price1mBlended0To100To1": 0.6188118811881188, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 40.0306066254192, "medianTimeToFirstChunk": 1.16553291900004}, "outputSpeedVariance": {"p05": 30.3016938293972, "q25": 37.3237028606011, "median": 40.0306066254192, "q75": 41.153959948406, "p95": 42.0909171409699}, "timeToFirstChunkVariance": {"p05": 1.03524374855, "q25": 1.09862997225, "median": 1.16553291900004, "q75": 2.00395250875, "p95": 8.06319628015001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 40.0306066254192, "medianTimeToFirstChunk": 1.16553291900004, "medianTimeToFirstAnswerToken": 1.16553291900004, "medianEndToEndResponseTime": 13.655975661441591}}, "endToEndResponseTime": {"input": 1.16553291900004, "reasoning": 0, "answer": 12.490442742441552, "total": 13.655975661441591}, "timeToFirstAnswerToken": {"input": 1.16553291900004, "reasoning": 0, "total": 1.16553291900004}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6657d7de-a2a9-40bc-a32f-86e80ad63698", "slug": "qwen3-8-27b-medium", "name": "Qwen3.8 27B (medium)", "shortName": "Qwen3.8 27B (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-14", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "qwen3-8-27b", "name": "Qwen3.8 27B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 27, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.8-27B", "microevalsEnabled": false, "intelligenceIndex": 27.8121478231586, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 28.80123237953811, "strategyAndOps": 34.75830491000717, "legal": 27.762869589486172, "engineering": 24.868593412812086, "economics": 31.489387028884757}, "omniscience": -36.15, "omniscienceBreakdown": {"accuracy": 0.1835, "hallucinationRate": 0.6674831598285365}, "gdpPdfAllPass": 0.128, "gdpval": 1430.39, "gdpvalNormalized": 0.465195, "itBenchSre": null, "tau2": null, "tauBanking": 0.474226804123711, "terminalbenchHard": null, "terminalBench21": 0.651685393258427, "terminalBench40": 0.0505050505050505, "scicode": 0.390046296296296, "lcr": 0.796666666666667, "ifbench": null, "hle": 0.140871177015755, "gpqa": 0.845454545454545, "critpt": 0, "apexAgents": null, "mmmuPro": 0.741618497109827, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.40252101015938635, "price1mInputTokens": 0.5, "price1mOutputTokens": 3, "cacheHitPrice": 0.05, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.125, "price1mBlended7To2To1": 0.43499999999999994, "price1mBlended0To1To1": 1.75, "price1mBlended100To1To1": 0.08333333333333333, "price1mBlended0To100To1": 0.5247524752475248, "intelligenceIndexTimePerTask": 969.8458353273076, "intelligenceIndexCost": {"total": 977.4452754040002, "input": 639.1700244040002, "nonCacheInput": 12.7424805, "cacheRead": 187.55800234400002, "cacheWrite": 438.86954156000013, "output": 338.275251, "reasoning": 242.150289, "answer": 96.12496200000001}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.9034163174028444, "input": 0.7475864192704818, "nonCacheInput": 0.00923424769998676, "cacheRead": 0.22964745662767694, "cacheWrite": 0.508704714942818, "output": 0.1558298981323625, "reasoning": 0.09663418285308062, "answer": 0.0591957152792819}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.33723251182417585}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0820306921184091}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.010454819150722987}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.4481738390348486}, {"slug": "scicode", "weightedCostPerTask": 0.0011675270833333333}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0038997665199258574}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.007090422000000001}, {"slug": "critpt", "weightedCostPerTask": 0.00917626857142857}, {"slug": "omniscience", "weightedCostPerTask": 0.0013106520999999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.002879819}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4654384091, "output": 112758417, "answer": 32041654, "reasoning": 80716763}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 32211.394284360205, "answer": 19731.905093093967, "output": 51943.29937745417}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1375.7, "lower95ci": 1367.04, "upper95ci": 1384.77}, "rubricPassRate": 0.4652631578947368, "analyticalQuality": {"elo": 1556.04, "lower95ci": 1540.73, "upper95ci": 1572.5}, "presentation": {"elo": 1252.31, "lower95ci": 1237.43, "upper95ci": 1267.16}}, "briefcaseTotalCost": 204.58772384000002, "timescaleData": {"medianOutputSpeed": 50.2241195397478, "medianTimeToFirstChunk": 3.79491333300002}, "outputSpeedVariance": {"p05": 35.125803741054, "q25": 43.4083490763676, "median": 50.2241195397478, "q75": 56.3488080994449, "p95": 62.7439058199474}, "timeToFirstChunkVariance": {"p05": 3.56593615064995, "q25": 3.73384285874998, "median": 3.79491333300002, "q75": 3.91591675475, "p95": 4.34466791495007}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 51.6467642947638, "medianTimeToFirstChunk": 1.21312189599999, "medianTimeToFirstAnswerToken": 39.93771630786656, "medianEndToEndResponseTime": 49.6188649108332}, "long": {"medianOutputSpeed": 50.2241195397478, "medianTimeToFirstChunk": 3.79491333300002, "medianTimeToFirstAnswerToken": 43.616417787989676, "medianEndToEndResponseTime": 53.57179390173709}, "hundredK": {"medianOutputSpeed": 76.8398633020678, "medianTimeToFirstChunk": 16.6720002855001, "medianTimeToFirstAnswerToken": 42.70015694863382, "medianEndToEndResponseTime": 49.20719611441724}, "mediumParallel": {"medianOutputSpeed": 47.1501374521747, "medianTimeToFirstChunk": 1.30702866799993, "medianTimeToFirstAnswerToken": 43.72472049400233, "medianEndToEndResponseTime": 54.329143450502926}}, "endToEndResponseTime": {"input": 3.79491333300002, "reasoning": 39.82150445498966, "answer": 9.955376113747414, "total": 53.57179390173709}, "timeToFirstAnswerToken": {"input": 3.79491333300002, "reasoning": 39.82150445498966, "total": 43.616417787989676}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "666eb13f-0d22-4438-8eb0-01876e1a8604", "slug": "motif-2-12-7b", "name": "Motif-2-12.7B-Reasoning", "shortName": "Motif-2-12.7B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-04", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "motif-2-12-7b-reasoning", "name": "Motif-2-12.7B-Reasoning"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 12.7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.18748556817538, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -61.6833333333333, "omniscienceBreakdown": {"accuracy": 0.15166666666666667, "hallucinationRate": 0.905893909626719}, "gdpval": null, "itBenchSre": null, "tau2": 0.464912280701754, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.146666666666667, "ifbench": 0.570068027210884, "hle": 0.08758109360519, "gpqa": 0.694949494949495, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.650793650793651, "aime25": 0.803333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "366bf3fc-4436-4baf-8d8f-acb7ec04d342", "slug": "motif-technologies", "name": "Motif Technologies", "logo": "/img/logos/motif_small.svg", "color": "#6a93eb", "country": "kr", "url": "https://model-hub.motiftech.io/en/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "66938aab-78fa-49d7-8461-b48b6833e837", "slug": "qwen3-6-35b-a3b-non-reasoning", "name": "Qwen3.6 35B A3B (Non-reasoning)", "shortName": "Qwen3.6 35B A3B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-16", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-6-35b-a3b", "name": "Qwen3.6 35B A3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 36, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "microevalsEnabled": false, "intelligenceIndex": 15.2320772647744, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -60.0166666666667, "omniscienceBreakdown": {"accuracy": 0.16716666666666666, "hallucinationRate": 0.9213528116870122}, "gdpval": 953.19, "gdpvalNormalized": 0.22659500000000002, "itBenchSre": null, "tau2": 0.850877192982456, "tauBanking": 0.0536082474226804, "terminalbenchHard": 0.257575757575758, "terminalBench21": 0.415730337078652, "terminalBench40": null, "scicode": null, "lcr": 0.643333333333333, "ifbench": 0.361904761904762, "hle": 0.139017608897127, "gpqa": 0.817171717171717, "critpt": 0, "apexAgents": null, "mmmuPro": 0.710404624277457, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.375, "price1mOutputTokens": 2.25, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.254, "price1mBlended0To3To1": 0.84375, "price1mBlended7To2To1": 0.5625, "price1mBlended0To1To1": 1.3125, "price1mBlended100To1To1": 0.39338235294117646, "price1mBlended0To100To1": 0.3935643564356436, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 130.714014693067, "medianTimeToFirstChunk": 2.08452556399999}, "outputSpeedVariance": {"p05": 100.813710740655, "q25": 104.240630931119, "median": 130.714014693067, "q75": 155.912404925102, "p95": 179.289976415211}, "timeToFirstChunkVariance": {"p05": 1.93544678444999, "q25": 2.00515159149998, "median": 2.08452556399999, "q75": 2.22981604250038, "p95": 2.55856992169991}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 131.456933393624, "medianTimeToFirstChunk": 1.29735753100005, "medianTimeToFirstAnswerToken": 1.29735753100005, "medianEndToEndResponseTime": 5.1008845652329295}, "long": {"medianOutputSpeed": 130.714014693067, "medianTimeToFirstChunk": 2.08452556399999, "medianTimeToFirstAnswerToken": 2.08452556399999, "medianEndToEndResponseTime": 5.909670107024416}, "hundredK": {"medianOutputSpeed": 208.38057157009, "medianTimeToFirstChunk": 8.20286478449997, "medianTimeToFirstAnswerToken": 8.20286478449997, "medianEndToEndResponseTime": 10.602320723374877}, "mediumParallel": {"medianOutputSpeed": 111.78019706335, "medianTimeToFirstChunk": 1.25909437400014, "medianTimeToFirstAnswerToken": 1.25909437400014, "medianEndToEndResponseTime": 5.732158594101946}}, "endToEndResponseTime": {"input": 2.08452556399999, "reasoning": 0, "answer": 3.8251445430244266, "total": 5.909670107024416}, "timeToFirstAnswerToken": {"input": 2.08452556399999, "reasoning": 0, "total": 2.08452556399999}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 7, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "66f4ce73-9a9b-4b49-9c6e-bedb9bfdc720", "slug": "ministral-3-3b", "name": "Ministral 3 3B", "shortName": "Ministral 3 3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "ministral-3-3b", "name": "Ministral 3 3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512", "microevalsEnabled": false, "intelligenceIndex": 4.83760020546443, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 5.250904095570125, "strategyAndOps": 3.2236226010849567, "legal": 7.26419943495534, "engineering": 6.843802131603336, "economics": 9.363871640407783}, "omniscience": -64, "omniscienceBreakdown": {"accuracy": 0.08983333333333333, "hallucinationRate": 0.8018677897820912}, "gdpPdfAllPass": 0, "gdpval": 233.97, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.248538011695906, "tauBanking": 0.0474226804123711, "terminalbenchHard": 0, "terminalBench21": 0, "terminalBench40": 0, "scicode": 0.152777777777778, "lcr": 0.17, "ifbench": 0.268027210884354, "hle": 0.0537534754402224, "gpqa": 0.357575757575758, "critpt": 0, "apexAgents": null, "mmmuPro": 0.380924855491329, "livecodebench": 0.246560846560847, "aime25": 0.22, "analystAgent": null, "automationBenchPartialScore": 0.006658657772309807, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.1, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.1, "price1mBlended7To2To1": 0.10000000000000002, "price1mBlended0To1To1": 0.1, "price1mBlended100To1To1": 0.09999999999999999, "price1mBlended0To100To1": 0.09999999999999999, "intelligenceIndexTimePerTask": 55.3779586611443, "intelligenceIndexCost": {"total": 61.2807986, "input": 58.5974746, "nonCacheInput": 1.5254449, "cacheRead": 0, "cacheWrite": 57.0720297, "output": 2.6833240000000003, "reasoning": 0, "answer": 2.6833240000000003}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.042290829470686256, "input": 0.04098200430422163, "nonCacheInput": 0.0008860130266932198, "cacheRead": 0, "cacheWrite": 0.040095991277528414, "output": 0.0013088251664646437, "reasoning": 0, "answer": 0.0013088251664646437}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.019762570054945056}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.01530028172727273}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0007129808447488585}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.005423985606060606}, {"slug": "scicode", "weightedCostPerTask": 4.586836805555556e-05}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 4.869205746061169e-05}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0002499771}, {"slug": "critpt", "weightedCostPerTask": 0.00026989985714285716}, {"slug": "omniscience", "weightedCostPerTask": 2.830455e-06}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0004737434}]}, "canonicalIntelligenceIndexTokenCount": {"input": 585974746, "output": 26833240, "answer": 26833240, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 13088.251664646437, "output": 13088.251664646437}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 16.01, "lower95ci": 5.39, "upper95ci": 25.12}, "rubricPassRate": 0.03664921465968586, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 11.989292500000001, "timescaleData": {"medianOutputSpeed": 222.586171474581, "medianTimeToFirstChunk": 0.640497081000092}, "outputSpeedVariance": {"p05": 159.389355891224, "q25": 178.739388394531, "median": 222.586171474581, "q75": 247.310914518671, "p95": 272.78088925603}, "timeToFirstChunkVariance": {"p05": 0.562944817249982, "q25": 0.59530816375009, "median": 0.640497081000092, "q75": 0.665206874250046, "p95": 1.12877214774996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 232.515122437457, "medianTimeToFirstChunk": 0.463419202000012, "medianTimeToFirstAnswerToken": 0.463419202000012, "medianEndToEndResponseTime": 2.6138169686420176}, "long": {"medianOutputSpeed": 222.586171474581, "medianTimeToFirstChunk": 0.640497081000092, "medianTimeToFirstAnswerToken": 0.640497081000092, "medianEndToEndResponseTime": 2.886818120117741}, "hundredK": {"medianOutputSpeed": 97.4221598124757, "medianTimeToFirstChunk": 5.40140720349999, "medianTimeToFirstAnswerToken": 5.40140720349999, "medianEndToEndResponseTime": 10.533709761382422}, "mediumParallel": {"medianOutputSpeed": 95.8771513243278, "medianTimeToFirstChunk": 0.477434552499972, "medianTimeToFirstAnswerToken": 0.477434552499972, "medianEndToEndResponseTime": 5.692441392958011}}, "endToEndResponseTime": {"input": 0.640497081000092, "reasoning": 0, "answer": 2.246321039117649, "total": 2.886818120117741}, "timeToFirstAnswerToken": {"input": 0.640497081000092, "reasoning": 0, "total": 0.640497081000092}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 2, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "686ab020-ee58-4a70-a9ac-24d675a73506", "slug": "lfm2-8b-a1b", "name": "LFM2 8B A1B", "shortName": "LFM2 8B A1B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-07", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "lfm2-8b-a1b", "name": "LFM2 8B A1B"}, "deprecated": true, "deprecatedTo": "lfm2-5-8b-a1b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 8.34, "inferenceParametersActiveBillions": 1.5, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "lfm 1.0", "licenseUrl": "https://huggingface.co/LiquidAI/LFM2-8B-A1B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LiquidAI/LFM2-8B-A1B", "microevalsEnabled": false, "intelligenceIndex": 4.92956933760184, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -76.5, "omniscienceBreakdown": {"accuracy": 0.08216666666666667, "hallucinationRate": 0.923007081895769}, "gdpval": null, "itBenchSre": null, "tau2": 0.105263157894737, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.262585034013605, "hle": 0.0491195551436515, "gpqa": 0.344444444444444, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.151322751322751, "aime25": 0.253333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5b1886c4-43ba-4007-b840-9d21a2b7d42c", "slug": "liquidai", "name": "Liquid AI", "logo": "/img/logos/liquidai_small.svg", "color": "#000000", "country": "us", "url": "https://www.liquid.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "68c89ebf-779c-4445-9241-de964cd17355", "slug": "gemini-2-5-flash-reasoning-04-2025", "name": "Gemini 2.5 Flash Preview (Reasoning)", "shortName": "Gemini 2.5 Flash (Apr)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-17", "knowledgeCutoffDate": "2025-01-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-flash-04-2025", "name": "Gemini 2.5 Flash Preview"}, "deprecated": true, "deprecatedTo": "gemini-2-5-flash-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.6539041327006, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.121, "gpqa": 0.697979797979798, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.504761904761905, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "69534bed-2ffd-4235-832b-e20a810333ab", "slug": "qwen3-7-max", "name": "Qwen3.7 Max", "shortName": "Qwen3.7 Max", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2409, "release": {"slug": "qwen3-7-max", "name": "Qwen3.7 Max"}, "deprecated": true, "deprecatedTo": "qwen3-8-max-0803", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 29.8725384255623, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 31.899871763549505, "strategyAndOps": 26.345228206196165, "legal": 35.9022870770862, "engineering": 33.7706279503629, "economics": 44.14141218721039}, "omniscience": 13.4833333333333, "omniscienceBreakdown": {"accuracy": 0.31133333333333335, "hallucinationRate": 0.2562923523717328}, "harveyLab": 0.834274135185989, "gdpPdfAllPass": 0.086, "gdpval": 1189.86, "gdpvalNormalized": 0.34492999999999996, "itBenchSre": 0.424670433145009, "tau2": 0.947368421052632, "tauBanking": 0.117525773195876, "terminalbenchHard": 0.507575757575758, "terminalBench21": 0.745318352059925, "terminalBench40": 0.0151515151515152, "scicode": 0.49537037037037, "lcr": 0.79, "ifbench": 0.805442176870748, "hle": 0.405004633920297, "gpqa": 0.923232323232323, "critpt": 0.134285714285714, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.1875, "automationBenchPartialScore": 0.22976890336173603, "enterpriseOpsGym": 0.4500149209191286, "price1mInputTokens": 2.5, "price1mOutputTokens": 7.5, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3.75, "price1mBlended7To2To1": 1.6, "price1mBlended0To1To1": 5, "price1mBlended100To1To1": 0.5882352941176471, "price1mBlended0To100To1": 2.5495049504950495, "intelligenceIndexTimePerTask": 148.35125309834726, "intelligenceIndexCost": {"total": 2277.1238117387743, "input": 1362.9175442387743, "nonCacheInput": 42.14684, "cacheRead": 349.7445839403064, "cacheWrite": 971.0261202984678, "output": 914.2062675, "reasoning": 771.781755, "answer": 142.4245125}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.1472961597972207, "input": 0.905868815379195, "nonCacheInput": 0.02427457742850523, "cacheRead": 0.24135105057729583, "cacheWrite": 0.640243187373394, "output": 0.24142734441802532, "reasoning": 0.15927817464197896, "answer": 0.08214916977604636}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.1951962724284756}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.06552569095043102}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.063030654209444}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.6819638915087728}, {"slug": "scicode", "weightedCostPerTask": 0.005839658854166666}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.024951903962001854}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0132132825}, {"slug": "critpt", "weightedCostPerTask": 0.08157697857142858}, {"slug": "omniscience", "weightedCostPerTask": 0.0020693718124999995}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.013928455}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1104758352, "output": 121894169, "answer": 18989935, "reasoning": 102904234}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 21237.08995226386, "answer": 10953.222636806182, "output": 32190.312589070043}, "briefcaseBreakdown": {"overall": {"elo": 917.94, "lower95ci": 911.76, "upper95ci": 924.42}, "rubricPassRate": 0.23737373737373738, "analyticalQuality": {"elo": 812.92, "lower95ci": 801.02, "upper95ci": 825.76}, "presentation": {"elo": 982.65, "lower95ci": 971.22, "upper95ci": 993.84}}, "briefcaseTotalCost": 118.41907193994186, "timescaleData": {"medianOutputSpeed": 195.383484734001, "medianTimeToFirstChunk": 2.46856486000009}, "outputSpeedVariance": {"p05": 52.1574606219053, "q25": 122.937551340984, "median": 195.383484734001, "q75": 211.555308742865, "p95": 236.259012605175}, "timeToFirstChunkVariance": {"p05": 2.19084649505002, "q25": 2.28495671524996, "median": 2.46856486000009, "q75": 3.08927550374997, "p95": 3.50956096545002}, "performanceByPromptType": {"long": {"medianOutputSpeed": 195.383484734001, "medianTimeToFirstChunk": 2.46856486000009, "medianTimeToFirstAnswerToken": 14.798163767910147, "medianEndToEndResponseTime": 17.357233694832118}}, "endToEndResponseTime": {"input": 2.46856486000009, "reasoning": 12.329598907910057, "answer": 2.559069926921971, "total": 17.357233694832118}, "timeToFirstAnswerToken": {"input": 2.46856486000009, "reasoning": 12.329598907910057, "total": 14.798163767910147}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6a5d56e1-bb68-4205-8d9b-26b97888bc84", "slug": "glm-4-6-reasoning", "name": "GLM-4.6 (Reasoning)", "shortName": "GLM-4.6", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "glm-4-6", "name": "GLM-4.6"}, "deprecated": true, "deprecatedTo": "glm-4-7", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 357, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://github.com/zai-org/GLM-4.6", "microevalsEnabled": false, "intelligenceIndex": 18.5297479165936, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -41.8833333333333, "omniscienceBreakdown": {"accuracy": 0.2688333333333333, "hallucinationRate": 0.9405060405744244}, "gdpval": 873.8, "gdpvalNormalized": 0.18689999999999998, "itBenchSre": null, "tau2": 0.704678362573099, "tauBanking": 0.134020618556701, "terminalbenchHard": 0.25, "terminalBench21": 0.49438202247191, "terminalBench40": null, "scicode": null, "lcr": 0.54, "ifbench": 0.434013605442177, "hle": 0.144578313253012, "gpqa": 0.77979797979798, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.695238095238095, "aime25": 0.86, "analystAgent": null, "price1mInputTokens": 0.55, "price1mOutputTokens": 2.2, "cacheHitPrice": 0.55, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.9625000000000001, "price1mBlended7To2To1": 0.7150000000000001, "price1mBlended0To1To1": 1.375, "price1mBlended100To1To1": 0.5661764705882354, "price1mBlended0To100To1": 0.5663366336633664, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 38.8517827184542, "medianTimeToFirstChunk": 3.59122536999997}, "outputSpeedVariance": {"p05": 26.7102955060944, "q25": 32.7166527341988, "median": 38.8517827184542, "q75": 52.0972922623134, "p95": 71.2898693715159}, "timeToFirstChunkVariance": {"p05": 0.659934157000009, "q25": 0.789516515500054, "median": 3.59122536999997, "q75": 4.14493637049999, "p95": 8.53568646125008}, "performanceByPromptType": {"long": {"medianOutputSpeed": 38.8517827184542, "medianTimeToFirstChunk": 3.59122536999997, "medianTimeToFirstAnswerToken": 55.0689146820536, "medianEndToEndResponseTime": 67.93833701006702}}, "endToEndResponseTime": {"input": 3.59122536999997, "reasoning": 51.477689312053634, "answer": 12.869422328013409, "total": 67.93833701006702}, "timeToFirstAnswerToken": {"input": 3.59122536999997, "reasoning": 51.477689312053634, "total": 55.0689146820536}, "performanceDataSource": {"type": "median"}, "hostModelCount": 3, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6a7c0e25-1dcb-4b15-8495-a8536a9da051", "slug": "gpt-4", "name": "GPT-4", "shortName": "GPT-4", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-03-14", "knowledgeCutoffDate": "2021-09-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4", "name": "GPT-4"}, "deprecated": true, "deprecatedTo": "gpt-4-5", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 8192, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.70159308543366, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -33.8333333333333, "omniscienceBreakdown": {"accuracy": 0.21, "hallucinationRate": 0.6940928270042194}, "gdpval": 188.72, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.331972789115646, "hle": null, "gpqa": 0.349494949494949, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 30, "price1mOutputTokens": 60, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 37.5, "price1mBlended7To2To1": 33, "price1mBlended0To1To1": 45, "price1mBlended100To1To1": 30.294117647058822, "price1mBlended0To100To1": 30.297029702970296, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6ace0ead-584f-4ce6-a9b7-6c3f9cc91c3c", "slug": "agnes-3-0-flash", "name": "Agnes 3.0 Flash", "shortName": "Agnes 3.0 Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "agnes-3-0-flash", "name": "Agnes 3.0 Flash"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 35.5, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -10.5666666666667, "omniscienceBreakdown": {"accuracy": 0.25483333333333336, "hallucinationRate": 0.48378438828002684}, "gdpPdfAllPass": 0.1, "gdpval": 1573.47, "gdpvalNormalized": 0.536735, "itBenchSre": null, "tau2": null, "tauBanking": 0.476288659793814, "terminalbenchHard": null, "terminalBench21": 0.820224719101124, "terminalBench40": 0.0707070707070707, "scicode": 0.516203703703704, "lcr": 0.81, "ifbench": null, "hle": 0.384615384615385, "gpqa": 0.924242424242424, "critpt": 0.151428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5070253234326328, "price1mInputTokens": 0.05, "price1mOutputTokens": 0.15, "cacheHitPrice": 0.005, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.07500000000000001, "price1mBlended7To2To1": 0.028500000000000004, "price1mBlended0To1To1": 0.1, "price1mBlended100To1To1": 0.0068627450980392165, "price1mBlended0To100To1": 0.050990099009900994, "timescaleData": {"medianOutputSpeed": 317.171489989209, "medianTimeToFirstChunk": 1.99376207599971}, "outputSpeedVariance": {"p05": 317.171489989209, "q25": 317.171489989209, "median": 317.171489989209, "q75": 317.171489989209, "p95": 317.171489989209}, "timeToFirstChunkVariance": {"p05": 1.99376207599971, "q25": 1.99376207599971, "median": 1.99376207599971, "q75": 1.99376207599971, "p95": 1.99376207599971}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 263.872999764028, "medianTimeToFirstChunk": 0.970113694999782, "medianTimeToFirstAnswerToken": 8.54951743008646, "medianEndToEndResponseTime": 10.444368363858128}, "long": {"medianOutputSpeed": 317.171489989209, "medianTimeToFirstChunk": 1.99376207599971, "medianTimeToFirstAnswerToken": 8.2994990767246, "medianEndToEndResponseTime": 9.875933326905825}, "hundredK": {"medianOutputSpeed": 235.216661073711, "medianTimeToFirstChunk": 5.43750842299778, "medianTimeToFirstAnswerToken": 13.940307463127212, "medianEndToEndResponseTime": 16.06600722315957}}, "endToEndResponseTime": {"input": 1.99376207599971, "reasoning": 6.305737000724892, "answer": 1.576434250181223, "total": 9.875933326905825}, "timeToFirstAnswerToken": {"input": 1.99376207599971, "reasoning": 6.305737000724892, "total": 8.2994990767246}, "performanceDataSource": {"type": "firstParty", "providerName": "Sapiens AI"}, "hostModelCount": 1, "creator": {"id": "5db3af1a-e372-4c62-98bd-f6027eeaf990", "slug": "agnes-ai", "name": "Sapiens AI", "logo": "/img/logos/sapiens.svg", "color": "#1521a9", "country": "sg", "url": "https://agnes-ai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6afbfb62-27e4-435e-9c85-d9fe1b92519e", "slug": "gemini-2-5-flash", "name": "Gemini 2.5 Flash (Non-reasoning)", "shortName": "Gemini 2.5 Flash (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-20", "knowledgeCutoffDate": "2025-01-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-flash", "name": "Gemini 2.5 Flash"}, "deprecated": true, "deprecatedTo": "gemini-2-5-flash-preview-09-2025", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.85128154382851, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -42.5666666666667, "omniscienceBreakdown": {"accuracy": 0.2613333333333333, "hallucinationRate": 0.9300541516245487}, "mlcrOverall": 0.0833333333333333, "gdpval": null, "itBenchSre": null, "tau2": 0.149122807017544, "tauBanking": null, "terminalbenchHard": 0.121212121212121, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.499, "ifbench": 0.389795918367347, "hle": 0.0472659870250232, "gpqa": 0.682828282828283, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": 0.654913294797688, "livecodebench": 0.495238095238095, "aime25": 0.603333333333333, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": 0.03, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.1935, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.331, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.056862745098039215, "price1mBlended0To100To1": 0.3217821782178218, "timescaleData": {"medianOutputSpeed": 216.841168977908, "medianTimeToFirstChunk": 0.443579424500002}, "outputSpeedVariance": {"p05": 173.032709848864, "q25": 185.96612268341, "median": 216.841168977908, "q75": 228.943109997285, "p95": 258.470043871912}, "timeToFirstChunkVariance": {"p05": 0.308707524499963, "q25": 0.407130106000011, "median": 0.443579424500002, "q75": 0.506978968750004, "p95": 0.648171496950084}, "performanceByPromptType": {"long": {"medianOutputSpeed": 216.841168977908, "medianTimeToFirstChunk": 0.443579424500002, "medianTimeToFirstAnswerToken": 0.443579424500002, "medianEndToEndResponseTime": 2.749414623400541}}, "endToEndResponseTime": {"input": 0.443579424500002, "reasoning": 0, "answer": 2.3058351989005392, "total": 2.749414623400541}, "timeToFirstAnswerToken": {"input": 0.443579424500002, "reasoning": 0, "total": 0.443579424500002}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 2, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6b08a75a-19ee-40b4-be33-133b8ef42f92", "slug": "llama-2-chat-13b", "name": "Llama 2 Chat 13B", "shortName": "Llama 2 Chat 13B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-07-18", "knowledgeCutoffDate": "2023-07-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-2-chat-13b", "name": "Llama 2 Chat 13B"}, "deprecated": true, "deprecatedTo": "llama-3-instruct-70b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 13, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 4096, "licenseName": "Llama 2 Community License Agreement", "licenseUrl": "https://ai.meta.com/llama/license/", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Llama-2-13b-chat-hf", "microevalsEnabled": false, "intelligenceIndex": 5.30069788678423, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0477, "gpqa": 0.321212121212121, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0984126984126984, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6b79f899-e3c0-45f6-923c-243faccdb2fc", "slug": "gpt-5-5-medium", "name": "GPT-5.5 (medium)", "shortName": "GPT-5.5 (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-23", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-5-5", "name": "GPT-5.5"}, "deprecated": true, "deprecatedTo": "gpt-5-6-sol-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 922000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 34.1541604432432, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 38.307357862433506, "strategyAndOps": 41.14437539216715, "legal": 41.853422400118056, "engineering": 35.377294769888756, "economics": 45.08503602873029}, "omniscience": 18.1, "omniscienceBreakdown": {"accuracy": 0.568, "hallucinationRate": 0.8958333333333334}, "gdpPdfAllPass": 0.206, "gdpval": 1288.18, "gdpvalNormalized": 0.39409000000000005, "itBenchSre": null, "tau2": 0.91812865497076, "tauBanking": 0.298969072164948, "terminalbenchHard": 0.575757575757576, "terminalBench21": 0.805243445692884, "terminalBench40": 0.0505050505050505, "scicode": 0.545138888888889, "lcr": 0.83, "ifbench": 0.70952380952381, "hle": 0.42354031510658, "gpqa": 0.926262626262626, "critpt": 0.185714285714286, "apexAgents": null, "mmmuPro": 0.811560693641619, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.40068834155236427, "enterpriseOpsGym": 0.44106236944195765, "price1mInputTokens": 5, "price1mOutputTokens": 30, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 3.83, "price1mBlended0To3To1": 11.25, "price1mBlended7To2To1": 4.35, "price1mBlended0To1To1": 17.5, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 5.247524752475248, "intelligenceIndexTimePerTask": 101.34144113181222, "intelligenceIndexCost": {"total": 2095.122320997447, "input": 1201.472360997447, "nonCacheInput": 138.490025, "cacheRead": 257.9026871113948, "cacheWrite": 805.079648886052, "output": 893.64996, "reasoning": 610.55799, "answer": 283.09197}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.9016588021523384, "input": 0.6450465434253837, "nonCacheInput": 0.10434854509442901, "cacheRead": 0.13400997665460013, "cacheWrite": 0.40668802167635465, "output": 0.2566122587269547, "reasoning": 0.10784482477579885, "answer": 0.14876743395115577}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.28847176205879993}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.08080570297565506}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.06639595903321593}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.2990882203619341}, {"slug": "scicode", "weightedCostPerTask": 0.006220809027777778}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.012626074837812789}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.08844243}, {"slug": "critpt", "weightedCostPerTask": 0.02935964285714286}, {"slug": "omniscience", "weightedCostPerTask": 0.005595401}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.024652800000000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 704519309, "output": 29788332, "answer": 9436399, "reasoning": 20351933}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 3594.827492526628, "answer": 4958.914465038528, "output": 8553.741957565155}, "briefcaseBreakdown": {"overall": {"elo": 1000, "lower95ci": 1000, "upper95ci": 1000}, "rubricPassRate": 0.26565656565656565, "analyticalQuality": {"elo": 1000, "lower95ci": 1000, "upper95ci": 1000}, "presentation": {"elo": 1000, "lower95ci": 1000, "upper95ci": 1000}}, "briefcaseTotalCost": 175.00620231567194, "timescaleData": {"medianOutputSpeed": 88.088929992763, "medianTimeToFirstChunk": 4.87704793750004}, "outputSpeedVariance": {"p05": 39.371613532924, "q25": 66.5657306589502, "median": 88.088929992763, "q75": 94.98667400584, "p95": 103.75064999069}, "timeToFirstChunkVariance": {"p05": 1.57153551285002, "q25": 2.68566280800002, "median": 4.87704793750004, "q75": 8.11513429450002, "p95": 19.1203667762501}, "performanceByPromptType": {"long": {"medianOutputSpeed": 88.088929992763, "medianTimeToFirstChunk": 4.87704793750004, "medianTimeToFirstAnswerToken": 4.87704793750004, "medianEndToEndResponseTime": 10.553130051802913}}, "endToEndResponseTime": {"input": 4.87704793750004, "reasoning": 0, "answer": 5.676082114302873, "total": 10.553130051802913}, "timeToFirstAnswerToken": {"input": 4.87704793750004, "reasoning": 0, "total": 4.87704793750004}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6ba9e8eb-8124-436d-842f-dbe36df80c27", "slug": "hermes-4-llama-3-1-70b-reasoning", "name": "Hermes 4 - Llama-3.1 70B (Reasoning)", "shortName": "Hermes 4 70B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-27", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "hermes-4-llama-3-1-70b", "name": "Hermes 4 - Llama-3.1 70B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 70.6, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "META LLAMA 3 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://llama.meta.com/llama3/license/", "modelWeightsSourceUrl": "https://huggingface.co/NousResearch/Hermes-4-70B", "microevalsEnabled": false, "intelligenceIndex": 7.90579275030455, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -49.3666666666667, "omniscienceBreakdown": {"accuracy": 0.2355, "hallucinationRate": 0.9537824286025725}, "gdpval": null, "itBenchSre": null, "tau2": 0.225146198830409, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.0966666666666667, "ifbench": 0.312925170068027, "hle": 0.08758109360519, "gpqa": 0.698989898989899, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.652910052910053, "aime25": 0.686666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 47.22222222222222, "modelAvailability": 4, "transparencyMethodology": 3, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0a2f41cc-2cbc-4949-be54-9fef1319d4a9", "slug": "nous-research", "name": "Nous Research", "logo": "/img/logos/nousresearch_small.jpg", "color": "#006fa8", "country": "us", "url": "https://nousresearch.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6c7b322e-2f35-48ff-9171-fb621a726fc0", "slug": "step-3-7-flash", "name": "Step 3.7 Flash", "shortName": "Step 3.7 Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-29", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "step-3-7-flash", "name": "Step 3.7 Flash"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 198, "inferenceParametersActiveBillions": 11, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/stepfun-ai/Step-3.7-Flash", "microevalsEnabled": true, "intelligenceIndex": 19.4812572685302, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -37.2833333333333, "omniscienceBreakdown": {"accuracy": 0.25783333333333336, "hallucinationRate": 0.8497642039074781}, "harveyLab": 0.727312201476335, "gdpval": 954.2, "gdpvalNormalized": 0.22710000000000002, "itBenchSre": 0.302730696798493, "tau2": 0.985380116959064, "tauBanking": 0.119587628865979, "terminalbenchHard": 0.356060606060606, "terminalBench21": 0.393258426966292, "terminalBench40": null, "scicode": 0.438657407407407, "lcr": 0.736666666666667, "ifbench": 0.672789115646258, "hle": 0.214087117701576, "gpqa": 0.809090909090909, "critpt": 0.0228571428571429, "apexAgents": 0.148230088495575, "mmmuPro": 0.753179190751445, "livecodebench": null, "aime25": null, "analystAgent": null, "enterpriseOpsGym": 0.29065950462548495, "price1mInputTokens": 0.2, "price1mOutputTokens": 1.15, "cacheHitPrice": 0.04, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.4375, "price1mBlended7To2To1": 0.183, "price1mBlended0To1To1": 0.6749999999999999, "price1mBlended100To1To1": 0.05245098039215686, "price1mBlended0To100To1": 0.2094059405940594, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 147.737461248418, "medianTimeToFirstChunk": 2.54307611200011}, "outputSpeedVariance": {"p05": 85.9308309220603, "q25": 113.51488829683, "median": 147.737461248418, "q75": 191.973777704901, "p95": 212.088392794082}, "timeToFirstChunkVariance": {"p05": 2.22451495009998, "q25": 2.46698200700001, "median": 2.54307611200011, "q75": 2.72595369300001, "p95": 4.7083800378}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 140.345062747085, "medianTimeToFirstChunk": 1.424757013, "medianTimeToFirstAnswerToken": 15.675347385417933, "medianEndToEndResponseTime": 19.237994978522416}, "long": {"medianOutputSpeed": 147.737461248418, "medianTimeToFirstChunk": 2.54307611200011, "medianTimeToFirstAnswerToken": 16.080603988135973, "medianEndToEndResponseTime": 19.464985957169937}, "hundredK": {"medianOutputSpeed": 140.158258849847, "medianTimeToFirstChunk": 9.08545469850006, "medianTimeToFirstAnswerToken": 23.355038356375125, "medianEndToEndResponseTime": 26.922434270843894}, "mediumParallel": {"medianOutputSpeed": 101.406878168706, "medianTimeToFirstChunk": 1.48319993350006, "medianTimeToFirstAnswerToken": 21.205727991929106, "medianEndToEndResponseTime": 26.136360006536368}}, "endToEndResponseTime": {"input": 2.54307611200011, "reasoning": 13.537527876135862, "answer": 3.3843819690339654, "total": 19.464985957169937}, "timeToFirstAnswerToken": {"input": 2.54307611200011, "reasoning": 13.537527876135862, "total": 16.080603988135973}, "performanceDataSource": {"type": "firstParty", "providerName": "StepFun"}, "hostModelCount": 2, "creator": {"id": "ce2e2e8b-7a22-4020-98ec-8ef71000dd42", "slug": "stepfun", "name": "StepFun", "logo": "/img/logos/stepfun_small.svg", "color": "#017AFF", "country": "cn", "url": "https://www.stepfun.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6d6fa1c9-b833-40b2-8a58-fa810e24a84e", "slug": "ling-3-0-flash-fin", "name": "Ling-3.0-flash-Fin", "shortName": "Ling-3.0-flash-Fin", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "ling-3-0-flash-fin", "name": "Ling-3.0-flash-Fin"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 124, "inferenceParametersActiveBillions": 5.1, "sizeClass": "medium", "contextWindowTokens": 262144, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ling-3.0-flash-Fin", "microevalsEnabled": false, "intelligenceIndex": 23.0214828940594, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 23.84090501406378, "strategyAndOps": 19.458539661805233, "legal": 25.154873827173784, "engineering": 25.63574394280419, "economics": 34.38806919987643}, "omniscience": -14.5833333333333, "omniscienceBreakdown": {"accuracy": 0.17866666666666667, "hallucinationRate": 0.3950892857142857}, "gdpPdfAllPass": 0.054, "gdpval": 1170.55, "gdpvalNormalized": 0.335275, "itBenchSre": null, "tau2": null, "tauBanking": 0.385567010309278, "terminalbenchHard": null, "terminalBench21": 0.625468164794007, "terminalBench40": 0, "scicode": 0.423611111111111, "lcr": 0.736666666666667, "ifbench": null, "hle": 0.22613531047266, "gpqa": null, "critpt": 0.0257142857142857, "apexAgents": 0.274336283185841, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.1625, "automationBenchPartialScore": 0.07394444993005693, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "intelligenceIndexTimePerTask": 379.3854296134894, "canonicalIntelligenceIndexTokenCount": {"input": 4712319247, "output": 248534210, "answer": 55975173, "reasoning": 192559037}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 43178.6808771672, "answer": 23519.397643418808, "output": 66698.07852058602}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 967.05, "lower95ci": 956.7, "upper95ci": 977.09}, "rubricPassRate": 0.23535353535353534, "analyticalQuality": {"elo": 866.25, "lower95ci": 848.3, "upper95ci": 884.25}, "presentation": {"elo": 1094.9, "lower95ci": 1076.57, "upper95ci": 1113.93}}, "timescaleData": {"medianOutputSpeed": 161.499848114557, "medianTimeToFirstChunk": 3.19009004100002}, "outputSpeedVariance": {"p05": 154.257200663598, "q25": 158.103172101231, "median": 161.499848114557, "q75": 164.751522765821, "p95": 171.12111834754}, "timeToFirstChunkVariance": {"p05": 2.2409046848501, "q25": 3.07072103375011, "median": 3.19009004100002, "q75": 14.5149639007499, "p95": 47.5089275663}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 163.180180920841, "medianTimeToFirstChunk": 1.56768860199996, "medianTimeToFirstAnswerToken": 13.824078984176356, "medianEndToEndResponseTime": 16.888176579720458}, "long": {"medianOutputSpeed": 161.499848114557, "medianTimeToFirstChunk": 3.19009004100002, "medianTimeToFirstAnswerToken": 15.574002616455424, "medianEndToEndResponseTime": 18.669980760319273}, "hundredK": {"medianOutputSpeed": 175.005236546835, "medianTimeToFirstChunk": 8.47475632949999, "medianTimeToFirstAnswerToken": 19.90298578973536, "medianEndToEndResponseTime": 22.760043154794207}, "mediumParallel": {"medianOutputSpeed": 160.610036551159, "medianTimeToFirstChunk": 1.101109336, "medianTimeToFirstAnswerToken": 13.55363125148404, "medianEndToEndResponseTime": 16.66676173035505}}, "endToEndResponseTime": {"input": 3.19009004100002, "reasoning": 12.383912575455403, "answer": 3.0959781438638507, "total": 18.669980760319273}, "timeToFirstAnswerToken": {"input": 3.19009004100002, "reasoning": 12.383912575455403, "total": 15.574002616455424}, "performanceDataSource": {"type": "firstParty", "providerName": "InclusionAI"}, "hostModelCount": 1, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6d9a176d-feb8-4dac-8872-afe32b31897f", "slug": "deepseek-v3-2", "name": "DeepSeek V3.2 (Non-reasoning)", "shortName": "DeepSeek V3.2 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-01", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v3-2", "name": "DeepSeek V3.2"}, "deprecated": true, "deprecatedTo": "deepseek-v4-pro-0424-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "microevalsEnabled": false, "intelligenceIndex": 16.043537719683, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -46.8833333333333, "omniscienceBreakdown": {"accuracy": 0.24, "hallucinationRate": 0.9326754385964913}, "gdpval": null, "itBenchSre": null, "tau2": 0.789473684210526, "tauBanking": null, "terminalbenchHard": 0.325757575757576, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.456666666666667, "ifbench": 0.490476190476191, "hle": 0.112140871177016, "gpqa": 0.750505050505051, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.592592592592593, "aime25": 0.59, "analystAgent": null, "price1mInputTokens": 0.28, "price1mOutputTokens": 0.42, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.315, "price1mBlended7To2To1": 0.29400000000000004, "price1mBlended0To1To1": 0.35, "price1mBlended100To1To1": 0.2813725490196079, "price1mBlended0To100To1": 0.2813861386138614, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 11, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6da314d3-a984-4734-8f31-47dd32fb4699", "slug": "qwen3-vl-32b-instruct", "name": "Qwen3 VL 32B Instruct", "shortName": "Qwen3 VL 32B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-21", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-vl-32b-instruct", "name": "Qwen3 VL 32B Instruct"}, "deprecated": true, "deprecatedTo": "qwen3-5-27b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 33.4, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-VL-32B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 8.38699329476692, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -63.3666666666667, "omniscienceBreakdown": {"accuracy": 0.14833333333333334, "hallucinationRate": 0.9181996086105675}, "gdpval": null, "itBenchSre": null, "tau2": 0.292397660818713, "tauBanking": null, "terminalbenchHard": 0.0833333333333333, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.391836734693878, "hle": 0.0681186283595922, "gpqa": 0.670707070707071, "critpt": 0, "apexAgents": null, "mmmuPro": 0.642774566473988, "livecodebench": 0.514285714285714, "aime25": 0.683333333333333, "analystAgent": null, "price1mInputTokens": 0.16, "price1mOutputTokens": 0.64, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.716, "price1mBlended0To3To1": 0.28, "price1mBlended7To2To1": 0.20800000000000002, "price1mBlended0To1To1": 0.4, "price1mBlended100To1To1": 0.16470588235294117, "price1mBlended0To100To1": 0.16475247524752476, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 57.8735224193834, "medianTimeToFirstChunk": 2.8466270749999}, "outputSpeedVariance": {"p05": 34.8246481551952, "q25": 47.3868643976358, "median": 57.8735224193834, "q75": 73.1402070664039, "p95": 87.2940893987801}, "timeToFirstChunkVariance": {"p05": 2.5030832977, "q25": 2.56317870974997, "median": 2.8466270749999, "q75": 3.22608368474987, "p95": 3.55950577245008}, "performanceByPromptType": {"long": {"medianOutputSpeed": 57.8735224193834, "medianTimeToFirstChunk": 2.8466270749999, "medianTimeToFirstAnswerToken": 2.8466270749999, "medianEndToEndResponseTime": 11.486156502234772}}, "endToEndResponseTime": {"input": 2.8466270749999, "reasoning": 0, "answer": 8.639529427234873, "total": 11.486156502234772}, "timeToFirstAnswerToken": {"input": 2.8466270749999, "reasoning": 0, "total": 2.8466270749999}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6dd8ba55-5680-44a9-b309-82928165d5f0", "slug": "gpt-5-2-non-reasoning", "name": "GPT-5.2 (Non-reasoning)", "shortName": "GPT-5.2 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-11", "knowledgeCutoffDate": "2025-08-31", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-5-2", "name": "GPT-5.2"}, "deprecated": true, "deprecatedTo": "gpt-5-4-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 16.97598252351, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -12.25, "omniscienceBreakdown": {"accuracy": 0.3085, "hallucinationRate": 0.6232827187274042}, "gdpval": null, "itBenchSre": null, "tau2": 0.464912280701754, "tauBanking": 0.111340206185567, "terminalbenchHard": 0.318181818181818, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.456666666666667, "ifbench": 0.474149659863946, "hle": 0.0801668211306766, "gpqa": 0.712121212121212, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": 0.658381502890173, "livecodebench": 0.668783068783069, "aime25": 0.51, "analystAgent": null, "price1mInputTokens": 1.75, "price1mOutputTokens": 14, "cacheHitPrice": 0.175, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 2.15, "price1mBlended0To3To1": 4.8125, "price1mBlended7To2To1": 1.8725, "price1mBlended0To1To1": 7.875, "price1mBlended100To1To1": 0.32598039215686275, "price1mBlended0To100To1": 1.8712871287128714, "timescaleData": {"medianOutputSpeed": 73.9810244360247, "medianTimeToFirstChunk": 1.20085678100005}, "outputSpeedVariance": {"p05": 48.1586152772325, "q25": 59.0012385281919, "median": 73.9810244360247, "q75": 85.3997582695741, "p95": 95.9673896614331}, "timeToFirstChunkVariance": {"p05": 0.829018931500016, "q25": 1.02635739799999, "median": 1.20085678100005, "q75": 1.77080821074997, "p95": 2.55338126170015}, "performanceByPromptType": {"long": {"medianOutputSpeed": 73.9810244360247, "medianTimeToFirstChunk": 1.20085678100005, "medianTimeToFirstAnswerToken": 1.20085678100005, "medianEndToEndResponseTime": 7.959346593916556}}, "endToEndResponseTime": {"input": 1.20085678100005, "reasoning": 0, "answer": 6.758489812916506, "total": 7.959346593916556}, "timeToFirstAnswerToken": {"input": 1.20085678100005, "reasoning": 0, "total": 1.20085678100005}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6e1b44ff-c227-496b-aef4-19b70cd18c76", "slug": "gemma-4-26b-a4b", "name": "Gemma 4 26B A4B (Reasoning)", "shortName": "Gemma 4 26B A4B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "gemma-4-26b-a4b", "name": "Gemma 4 26B A4B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 25.2, "inferenceParametersActiveBillions": 3.8, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-4-26B-A4B-it", "microevalsEnabled": true, "intelligenceIndex": 16.671930040086, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -50.8333333333333, "omniscienceBreakdown": {"accuracy": 0.191, "hallucinationRate": 0.8644416975690152}, "gdpval": 693, "gdpvalNormalized": 0.0965, "itBenchSre": 0.236346516007533, "tau2": 0.435672514619883, "tauBanking": 0.119587628865979, "terminalbenchHard": 0.1364, "terminalBench21": 0.389513108614232, "terminalBench40": null, "scicode": 0.400462962962963, "lcr": 0.656666666666667, "ifbench": 0.724489795918367, "hle": 0.193234476367006, "gpqa": 0.791919191919192, "critpt": 0, "apexAgents": null, "mmmuPro": 0.692485549132948, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.115, "price1mOutputTokens": 0.37, "cacheHitPrice": 0.085, "cacheHitDiscountPercent": 0.6376923076923077, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.17875000000000002, "price1mBlended7To2To1": 0.11950000000000001, "price1mBlended0To1To1": 0.2425, "price1mBlended100To1To1": 0.08808823529411765, "price1mBlended0To100To1": 0.11752475247524752, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 8, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6e2a2572-ed8d-4616-8d7d-68d125fc8ee7", "slug": "deepseek-v4-pro-0424-non-reasoning", "name": "DeepSeek V4 Pro 0424 (Non-reasoning)", "shortName": "DeepSeek V4 Pro (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-24", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v4-pro-0424", "name": "DeepSeek V4 Pro 0424"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1600, "inferenceParametersActiveBillions": 49, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro", "microevalsEnabled": false, "intelligenceIndex": 20.8344651194768, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -29.8666666666667, "omniscienceBreakdown": {"accuracy": 0.30866666666666664, "hallucinationRate": 0.8784956605593057}, "gdpval": null, "itBenchSre": null, "tau2": 0.912280701754386, "tauBanking": null, "terminalbenchHard": 0.363636363636364, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.53, "ifbench": 0.457823129251701, "hle": 0.082483781278962, "gpqa": 0.717171717171717, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.435, "price1mOutputTokens": 0.87, "cacheHitPrice": 0.0036, "cacheHitDiscountPercent": 0.9917241379310345, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.54375, "price1mBlended7To2To1": 0.17652, "price1mBlended0To1To1": 0.6525, "price1mBlended100To1To1": 0.016323529411764705, "price1mBlended0To100To1": 0.4393069306930693, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 89.3686567528483, "medianTimeToFirstChunk": 1.74002086800002}, "outputSpeedVariance": {"p05": 47.1106902381223, "q25": 60.2347166695621, "median": 89.3686567528483, "q75": 116.70579339497, "p95": 159.094185653077}, "timeToFirstChunkVariance": {"p05": 1.0281696666, "q25": 1.50771544549986, "median": 1.74002086800002, "q75": 2.03738757275001, "p95": 2.73466410175003}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 82.5968850430098, "medianTimeToFirstChunk": 1.10669711999999, "medianTimeToFirstAnswerToken": 1.10669711999999, "medianEndToEndResponseTime": 7.160194170641067}, "long": {"medianOutputSpeed": 89.3686567528483, "medianTimeToFirstChunk": 1.74002086800002, "medianTimeToFirstAnswerToken": 1.74002086800002, "medianEndToEndResponseTime": 7.334823544544269}, "hundredK": {"medianOutputSpeed": 87.2004120808695, "medianTimeToFirstChunk": 6.20051720799997, "medianTimeToFirstAnswerToken": 6.20051720799997, "medianEndToEndResponseTime": 11.934435065364003}, "mediumParallel": {"medianOutputSpeed": 64.2084143659597, "medianTimeToFirstChunk": 1.00465239350001, "medianTimeToFirstAnswerToken": 1.00465239350001, "medianEndToEndResponseTime": 8.79179376643939}}, "endToEndResponseTime": {"input": 1.74002086800002, "reasoning": 0, "answer": 5.59480267654425, "total": 7.334823544544269}, "timeToFirstAnswerToken": {"input": 1.74002086800002, "reasoning": 0, "total": 1.74002086800002}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 5, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6e6e02fd-9cbd-417f-9bfc-673df89c313d", "slug": "nvidia-nemotron-nano-12b-v2-vl-reasoning", "name": "NVIDIA Nemotron Nano 12B v2 VL (Reasoning)", "shortName": "NVIDIA Nemotron Nano 12B v2 VL", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "nvidia-nemotron-nano-12b-v2-vl", "name": "NVIDIA Nemotron Nano 12B v2 VL"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 13.2, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Nvidia Open Model License", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16", "microevalsEnabled": false, "intelligenceIndex": 7.47796854824097, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -64.2333333333333, "omniscienceBreakdown": {"accuracy": 0.14616666666666667, "hallucinationRate": 0.9234823345695882}, "gdpval": null, "itBenchSre": null, "tau2": 0.213450292397661, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.41, "ifbench": 0.319047619047619, "hle": 0.0551436515291937, "gpqa": 0.571717171717172, "critpt": 0, "apexAgents": null, "mmmuPro": 0.528901734104046, "livecodebench": 0.694179894179894, "aime25": 0.75, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.30000000000000004, "price1mBlended7To2To1": 0.24000000000000005, "price1mBlended0To1To1": 0.4, "price1mBlended100To1To1": 0.20392156862745098, "price1mBlended0To100To1": 0.20396039603960398, "openness": {"opennessIndex": 72.22222222222223, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {"medianOutputSpeed": 60.8025198982094, "medianTimeToFirstChunk": 4.72277407000001}, "outputSpeedVariance": {"p05": 11.5383249513621, "q25": 32.5278572952797, "median": 60.8025198982094, "q75": 160.467974469673, "p95": 277.139741819598}, "timeToFirstChunkVariance": {"p05": 2.08436685649994, "q25": 3.17134845099998, "median": 4.72277407000001, "q75": 9.85770613749995, "p95": 59.7081420933}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 52.2710587946178, "medianTimeToFirstChunk": 7.40762206399999, "medianTimeToFirstAnswerToken": 45.66971290586245, "medianEndToEndResponseTime": 55.23523561632806}, "long": {"medianOutputSpeed": 60.8025198982094, "medianTimeToFirstChunk": 4.72277407000001, "medianTimeToFirstAnswerToken": 37.61614762340267, "medianEndToEndResponseTime": 45.83949101175333}, "hundredK": {"medianOutputSpeed": 69.3499510623954, "medianTimeToFirstChunk": 22.8982538265, "medianTimeToFirstAnswerToken": 51.737495518257845, "medianEndToEndResponseTime": 58.947305941197314}, "mediumParallel": {"medianOutputSpeed": 54.2404976100866, "medianTimeToFirstChunk": 6.52140771349991, "medianTimeToFirstAnswerToken": 43.394225776070165, "medianEndToEndResponseTime": 52.612430291712734}}, "endToEndResponseTime": {"input": 4.72277407000001, "reasoning": 32.89337355340266, "answer": 8.223343388350665, "total": 45.83949101175333}, "timeToFirstAnswerToken": {"input": 4.72277407000001, "reasoning": 32.89337355340266, "total": 37.61614762340267}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6f174934-5b7d-4333-86cb-f5ebf4a862e3", "slug": "gpt-5-6-sol-medium", "name": "GPT-5.6 Sol (medium)", "shortName": "GPT-5.6 Sol (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-5-6-sol", "name": "GPT-5.6 Sol"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 39.4845585889147, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 42.91095086436426, "strategyAndOps": 48.32007572965012, "legal": 45.18365853729745, "healthcareAndMedical": 39.06762058856894, "engineering": 40.22384321080527, "economics": 47.61448403228298}, "omniscience": 19.4, "omniscienceBreakdown": {"accuracy": 0.5775, "hallucinationRate": 0.9076923076923077}, "mlcrOverall": 0.15, "gdpPdfAllPass": 0.262, "gdpval": 1426.5, "gdpvalNormalized": 0.46325, "itBenchSre": null, "tau2": 0.809941520467836, "tauBanking": 0.364948453608247, "terminalbenchHard": 0.628787878787879, "terminalBench21": 0.861423220973783, "terminalBench40": 0.146464646464646, "scicode": 0.574074074074074, "lcr": 0.803333333333333, "ifbench": 0.695918367346939, "hle": 0.422150139017609, "gpqa": 0.926262626262626, "critpt": 0.228571428571429, "apexAgents": null, "mmmuPro": 0.813872832369942, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5132751158863986, "price1mInputTokens": 4, "price1mOutputTokens": 20, "cacheHitPrice": 0.4, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 8, "price1mBlended7To2To1": 3.08, "price1mBlended0To1To1": 12, "price1mBlended100To1To1": 0.6274509803921569, "price1mBlended0To100To1": 4.158415841584159, "intelligenceIndexTimePerTask": 121.77470794375714, "intelligenceIndexCost": {"total": 997.390755614641, "input": 572.0435956146409, "nonCacheInput": 107.3431, "cacheRead": 223.25974951177037, "cacheWrite": 241.4407461028705, "output": 425.34716000000003, "reasoning": 212.448, "answer": 212.89916000000002}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.5049926304382959, "input": 0.34751197892645896, "nonCacheInput": 0.08155611088404166, "cacheRead": 0.14820552113434882, "cacheWrite": 0.11775034690806853, "output": 0.15748065151183707, "reasoning": 0.053243991935226324, "answer": 0.10423665957661074}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.14523398231959825}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.059537218688163564}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.03005757767892733}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.16444740584699943}, {"slug": "scicode", "weightedCostPerTask": 0.0028483874999999997}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.004296019833178869}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.065298076}, {"slug": "critpt", "weightedCostPerTask": 0.01258578857142857}, {"slug": "omniscience", "weightedCostPerTask": 0.0015371699999999998}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.019151004}]}, "canonicalIntelligenceIndexTokenCount": {"input": 633273298, "output": 21267358, "answer": 10644958, "reasoning": 10622400}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 2662.1995967613157, "answer": 5211.832978830537, "output": 7874.032575591853}, "briefcaseBreakdown": {"overall": {"elo": 1236.71, "lower95ci": 1229.23, "upper95ci": 1243.97}, "rubricPassRate": 0.3181818181818182, "analyticalQuality": {"elo": 1219.03, "lower95ci": 1205.28, "upper95ci": 1233.29}, "presentation": {"elo": 1391.72, "lower95ci": 1378.15, "upper95ci": 1404.49}}, "briefcaseTotalCost": 88.10861594055628, "timescaleData": {"medianOutputSpeed": 63.4697750959714, "medianTimeToFirstChunk": 3.80721266799998}, "outputSpeedVariance": {"p05": 42.822137683301, "q25": 55.7412545782872, "median": 63.4697750959714, "q75": 84.4410938226336, "p95": 96.1745877949489}, "timeToFirstChunkVariance": {"p05": 2.63518634019999, "q25": 2.94812498374997, "median": 3.80721266799998, "q75": 6.12582456000001, "p95": 31.349965932}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 63.6418587277053, "medianTimeToFirstChunk": 6.51816854000003, "medianTimeToFirstAnswerToken": 6.51816854000003, "medianEndToEndResponseTime": 14.374632980161554}, "long": {"medianOutputSpeed": 63.4697750959714, "medianTimeToFirstChunk": 3.80721266799998, "medianTimeToFirstAnswerToken": 3.80721266799998, "medianEndToEndResponseTime": 11.684978096409957}, "hundredK": {"medianOutputSpeed": 82.9527264163914, "medianTimeToFirstChunk": 6.10267294949995, "medianTimeToFirstAnswerToken": 6.10267294949995, "medianEndToEndResponseTime": 12.130202382229967}, "mediumParallel": {"medianOutputSpeed": 61.3116552123875, "medianTimeToFirstChunk": 19.9905433365, "medianTimeToFirstAnswerToken": 19.9905433365, "medianEndToEndResponseTime": 28.145599634816655}}, "endToEndResponseTime": {"input": 3.80721266799998, "reasoning": 0, "answer": 7.877765428409977, "total": 11.684978096409957}, "timeToFirstAnswerToken": {"input": 3.80721266799998, "reasoning": 0, "total": 3.80721266799998}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 3, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6f1a7562-6e96-46ac-af4f-6ba5a7a3da96", "slug": "gpt-5-5-non-reasoning", "name": "GPT-5.5 (Non-reasoning)", "shortName": "GPT-5.5 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-23", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-5-5", "name": "GPT-5.5"}, "deprecated": true, "deprecatedTo": "gpt-5-6-sol-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 922000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 23.1674381348311, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -4.75, "omniscienceBreakdown": {"accuracy": 0.4563333333333333, "hallucinationRate": 0.9267320662170447}, "mlcrOverall": 0.15, "gdpval": 1054.41, "gdpvalNormalized": 0.27720500000000003, "itBenchSre": null, "tau2": 0.692982456140351, "tauBanking": 0.148453608247423, "terminalbenchHard": 0.492424242424242, "terminalBench21": 0.610486891385768, "terminalBench40": null, "scicode": null, "lcr": 0.64, "ifbench": 0.461224489795918, "hle": 0.137164040778499, "gpqa": 0.767676767676768, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": 0.713872832369942, "livecodebench": null, "aime25": null, "analystAgent": 0.075, "price1mInputTokens": 5, "price1mOutputTokens": 30, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 3.83, "price1mBlended0To3To1": 11.25, "price1mBlended7To2To1": 4.35, "price1mBlended0To1To1": 17.5, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 5.247524752475248, "timescaleData": {"medianOutputSpeed": 92.4243896573878, "medianTimeToFirstChunk": 0.969938895000041}, "outputSpeedVariance": {"p05": 61.0313045930848, "q25": 68.3072688588034, "median": 92.4243896573878, "q75": 104.779790684845, "p95": 124.501087801066}, "timeToFirstChunkVariance": {"p05": 0.832470140499967, "q25": 0.935667811750008, "median": 0.969938895000041, "q75": 1.19073905374984, "p95": 2.18079742495}, "performanceByPromptType": {"long": {"medianOutputSpeed": 92.4243896573878, "medianTimeToFirstChunk": 0.969938895000041, "medianTimeToFirstAnswerToken": 0.969938895000041, "medianEndToEndResponseTime": 6.379766342641003}}, "endToEndResponseTime": {"input": 0.969938895000041, "reasoning": 0, "answer": 5.409827447640962, "total": 6.379766342641003}, "timeToFirstAnswerToken": {"input": 0.969938895000041, "reasoning": 0, "total": 0.969938895000041}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6f3534b1-1168-472e-b3e3-23ab521504f5", "slug": "qwen3-5-omni-flash", "name": "Qwen3.5 Omni Flash", "shortName": "Qwen3.5 Omni Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-5-omni-flash", "name": "Qwen3.5 Omni Flash"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.4740069826994, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -65.0666666666667, "omniscienceBreakdown": {"accuracy": 0.1465, "hallucinationRate": 0.9339972661589533}, "gdpval": null, "itBenchSre": null, "tau2": 0.845029239766082, "tauBanking": null, "terminalbenchHard": 0.0833333333333333, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.52, "ifbench": 0.379591836734694, "hle": 0.0759962928637627, "gpqa": 0.742424242424242, "critpt": 0, "apexAgents": null, "mmmuPro": 0.647398843930636, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.275, "price1mBlended7To2To1": 0.17, "price1mBlended0To1To1": 0.45, "price1mBlended100To1To1": 0.10686274509803922, "price1mBlended0To100To1": 0.10693069306930694, "timescaleData": {"medianOutputSpeed": 243.25339268732, "medianTimeToFirstChunk": 1.86316625149994}, "outputSpeedVariance": {"p05": 176.691547693927, "q25": 203.131830897123, "median": 243.25339268732, "q75": 261.901710688419, "p95": 307.512618115478}, "timeToFirstChunkVariance": {"p05": 1.74113701315, "q25": 1.79686900850004, "median": 1.86316625149994, "q75": 2.02744141249999, "p95": 3.46065834129966}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 248.787377307548, "medianTimeToFirstChunk": 0.913199529999992, "medianTimeToFirstAnswerToken": 0.913199529999992, "medianEndToEndResponseTime": 2.9229477954110057}, "long": {"medianOutputSpeed": 243.25339268732, "medianTimeToFirstChunk": 1.86316625149994, "medianTimeToFirstAnswerToken": 1.86316625149994, "medianEndToEndResponseTime": 3.9186360415665655}, "hundredK": {"medianOutputSpeed": 249.376763288025, "medianTimeToFirstChunk": 11.152461164, "medianTimeToFirstAnswerToken": 11.152461164, "medianEndToEndResponseTime": 13.157459518327466}, "mediumParallel": {"medianOutputSpeed": 210.242054995644, "medianTimeToFirstChunk": 1.10836293399989, "medianTimeToFirstAnswerToken": 1.10836293399989, "medianEndToEndResponseTime": 3.4865740869034303}}, "endToEndResponseTime": {"input": 1.86316625149994, "reasoning": 0, "answer": 2.0554697900666254, "total": 3.9186360415665655}, "timeToFirstAnswerToken": {"input": 1.86316625149994, "reasoning": 0, "total": 1.86316625149994}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": true, "outputModalityVideo": false}, {"id": "6fc35842-0165-44cf-8570-c484a92b3d8c", "slug": "glm-4-7", "name": "GLM-4.7 (Reasoning)", "shortName": "GLM-4.7", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-22", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "glm-4-7", "name": "GLM-4.7"}, "deprecated": true, "deprecatedTo": "glm-5", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 357, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-4.7", "microevalsEnabled": false, "intelligenceIndex": 22.2402659332875, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -36.4333333333333, "omniscienceBreakdown": {"accuracy": 0.2931666666666667, "hallucinationRate": 0.9302051402970998}, "gdpval": 1095.87, "gdpvalNormalized": 0.29793499999999995, "itBenchSre": null, "tau2": 0.95906432748538, "tauBanking": 0.121649484536082, "terminalbenchHard": 0.318181818181818, "terminalBench21": 0.453183520599251, "terminalBench40": null, "scicode": null, "lcr": 0.71, "ifbench": 0.67891156462585, "hle": 0.27386468952734, "gpqa": 0.858585858585858, "critpt": 0.0171020408163265, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.894179894179894, "aime25": 0.95, "analystAgent": null, "price1mInputTokens": 0.6, "price1mOutputTokens": 2.2, "cacheHitPrice": 0.6, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1, "price1mBlended7To2To1": 0.76, "price1mBlended0To1To1": 1.4000000000000001, "price1mBlended100To1To1": 0.615686274509804, "price1mBlended0To100To1": 0.6158415841584158, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 103.617347331454, "medianTimeToFirstChunk": 1.20506351}, "outputSpeedVariance": {"p05": 14.7897213469053, "q25": 34.46702115661, "median": 103.617347331454, "q75": 195.049415692792, "p95": 242.733153540333}, "timeToFirstChunkVariance": {"p05": 0.603069498000037, "q25": 0.714034862250003, "median": 1.20506351, "q75": 3.46874312425002, "p95": 6.51861266084995}, "performanceByPromptType": {"long": {"medianOutputSpeed": 103.617347331454, "medianTimeToFirstChunk": 1.20506351, "medianTimeToFirstAnswerToken": 20.506850821755293, "medianEndToEndResponseTime": 25.332297649694116}}, "endToEndResponseTime": {"input": 1.20506351, "reasoning": 19.301787311755294, "answer": 4.825446827938824, "total": 25.332297649694116}, "timeToFirstAnswerToken": {"input": 1.20506351, "reasoning": 19.301787311755294, "total": 20.506850821755293}, "performanceDataSource": {"type": "median"}, "hostModelCount": 7, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "6fd796d3-f346-4f66-97df-5da81714fc73", "slug": "nova-2-0-lite-reasoning-low", "name": "Nova 2.0 Lite (low)", "shortName": "Nova 2.0 Lite (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-29", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "nova-2-0-lite", "name": "Nova 2.0 Lite"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 11.8041280807831, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.1, "omniscienceBreakdown": {"accuracy": 0.1765, "hallucinationRate": 0.8712811171827566}, "gdpval": null, "itBenchSre": null, "tau2": 0.719298245614035, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.543333333333333, "ifbench": 0.612244897959184, "hle": 0.0403151065801668, "gpqa": 0.697979797979798, "critpt": 0, "apexAgents": null, "mmmuPro": 0.579768786127168, "livecodebench": 0.468783068783069, "aime25": 0.466666666666667, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.42, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.52, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.32156862745098036, "price1mBlended0To100To1": 0.3217821782178218, "timescaleData": {"medianOutputSpeed": 159.360978456621, "medianTimeToFirstChunk": 7.21231261400002}, "outputSpeedVariance": {"p05": 113.598803148992, "q25": 131.333933815006, "median": 159.360978456621, "q75": 205.709437376153, "p95": 243.384344896527}, "timeToFirstChunkVariance": {"p05": 5.19901436925009, "q25": 5.89532001950002, "median": 7.21231261400002, "q75": 12.38286113875, "p95": 22.8365860438}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 196.017641271103, "medianTimeToFirstChunk": 4.40951644200001, "medianTimeToFirstAnswerToken": 14.612679723787958, "medianEndToEndResponseTime": 17.163470544234947}, "long": {"medianOutputSpeed": 159.360978456621, "medianTimeToFirstChunk": 7.21231261400002, "medianTimeToFirstAnswerToken": 19.76243636053821, "medianEndToEndResponseTime": 22.899967297172754}, "hundredK": {"medianOutputSpeed": 196.387203970664, "medianTimeToFirstChunk": 24.7100763914999, "medianTimeToFirstAnswerToken": 34.894039295206994, "medianEndToEndResponseTime": 37.440030021133765}, "mediumParallel": {"medianOutputSpeed": 193.175907313743, "medianTimeToFirstChunk": 5.15530623499989, "medianTimeToFirstAnswerToken": 15.508564194605267, "medianEndToEndResponseTime": 18.09687868450661}}, "endToEndResponseTime": {"input": 7.21231261400002, "reasoning": 12.550123746538189, "answer": 3.137530936634547, "total": 22.899967297172754}, "timeToFirstAnswerToken": {"input": 7.21231261400002, "reasoning": 12.550123746538189, "total": 19.76243636053821}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "70152cb0-fb36-4732-a925-89ef40994be1", "slug": "magistral-small-2509", "name": "Magistral Small 1.2", "shortName": "Magistral Small 1.2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-17", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "magistral-small-2509", "name": "Magistral Small 1.2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 24, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://choosealicense.com/licenses/apache-2.0/", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Magistral-Small-2509", "microevalsEnabled": false, "intelligenceIndex": 8.59366235978288, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -65.1, "omniscienceBreakdown": {"accuracy": 0.1345, "hallucinationRate": 0.9075678798382438}, "gdpval": 212.7, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.277777777777778, "tauBanking": 0.045360824742268, "terminalbenchHard": 0.0454545454545455, "terminalBench21": 0.0449438202247191, "terminalBench40": null, "scicode": null, "lcr": 0.193333333333333, "ifbench": 0.443537414965986, "hle": 0.0644114921223355, "gpqa": 0.662626262626263, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.554913294797688, "livecodebench": 0.722751322751323, "aime25": 0.803333333333333, "analystAgent": null, "automationBenchPartialScore": 0.0019111706206154657, "price1mInputTokens": 0.5, "price1mOutputTokens": 1.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.75, "price1mBlended7To2To1": 0.6, "price1mBlended0To1To1": 1, "price1mBlended100To1To1": 0.5098039215686274, "price1mBlended0To100To1": 0.5099009900990099, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "70882ec6-914c-41f0-9754-5e8f75005f77", "slug": "gemma-4-26b-a4b-non-reasoning", "name": "Gemma 4 26B A4B (Non-reasoning)", "shortName": "Gemma 4 26B A4B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-4-26b-a4b", "name": "Gemma 4 26B A4B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 25.2, "inferenceParametersActiveBillions": 3.8, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-4-26B-A4B-it", "microevalsEnabled": false, "intelligenceIndex": 13.1303772801787, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -62.3166666666667, "omniscienceBreakdown": {"accuracy": 0.15483333333333332, "hallucinationRate": 0.9205284953658056}, "gdpval": null, "itBenchSre": null, "tau2": 0.403508771929825, "tauBanking": null, "terminalbenchHard": 0.25, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.423333333333333, "ifbench": 0.454421768707483, "hle": 0.114921223354958, "gpqa": 0.714141414141414, "critpt": 0, "apexAgents": null, "mmmuPro": 0.667052023121387, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.13, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.6376923076923077, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.1975, "price1mBlended7To2To1": 0.15350000000000003, "price1mBlended0To1To1": 0.265, "price1mBlended100To1To1": 0.1277450980392157, "price1mBlended0To100To1": 0.13267326732673268, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 64.7005529204953, "medianTimeToFirstChunk": 1.52422025499982}, "outputSpeedVariance": {"p05": 8.62444211144638, "q25": 27.4126150205976, "median": 64.7005529204953, "q75": 115.93908720514, "p95": 200.288412239597}, "timeToFirstChunkVariance": {"p05": 0.699684703000003, "q25": 1.03270433299997, "median": 1.52422025499982, "q75": 2.31434168500004, "p95": 5.77789526399988}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 77.5263210060772, "medianTimeToFirstChunk": 0.730163316000002, "medianTimeToFirstAnswerToken": 0.730163316000002, "medianEndToEndResponseTime": 7.179585828398154}, "long": {"medianOutputSpeed": 64.7005529204953, "medianTimeToFirstChunk": 1.52422025499982, "medianTimeToFirstAnswerToken": 1.52422025499982, "medianEndToEndResponseTime": 9.25212948344807}, "hundredK": {"medianOutputSpeed": 39.8543466551363, "medianTimeToFirstChunk": 11.505828754, "medianTimeToFirstAnswerToken": 11.505828754, "medianEndToEndResponseTime": 24.051511771377015}, "mediumParallel": {"medianOutputSpeed": 51.3627658826288, "medianTimeToFirstChunk": 0.734368733999986, "medianTimeToFirstAnswerToken": 0.734368733999986, "medianEndToEndResponseTime": 10.469046985996206}}, "endToEndResponseTime": {"input": 1.52422025499982, "reasoning": 0, "answer": 7.72790922844825, "total": 9.25212948344807}, "timeToFirstAnswerToken": {"input": 1.52422025499982, "reasoning": 0, "total": 1.52422025499982}, "performanceDataSource": {"type": "median"}, "hostModelCount": 8, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "712be54a-77ae-41b2-9a58-21181479d6ee", "slug": "claude-opus-5-high", "name": "Claude Opus 5 (Adaptive Reasoning, High Effort)", "shortName": "Claude Opus 5 (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "claude-opus-5", "name": "Claude Opus 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 48.2371932595908, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 51.63183661613135, "strategyAndOps": 53.520852699846046, "legal": 54.65157952259484, "healthcareAndMedical": 52.22444467962718, "engineering": 51.76735735816125, "economics": 58.359341983317904}, "omniscience": 33.7166666666667, "omniscienceBreakdown": {"accuracy": 0.5888333333333333, "hallucinationRate": 0.6120794487231456}, "mlcrOverall": 0.594444444444444, "gdpPdfAllPass": 0.196, "gdpval": 1628.94, "gdpvalNormalized": 0.56447, "itBenchSre": null, "tau2": null, "tauBanking": 0.447422680412371, "terminalbenchHard": null, "terminalBench21": 0.876404494382023, "terminalBench40": 0.45959595959596, "scicode": 0.554398148148148, "lcr": 0.79, "ifbench": null, "hle": 0.528266913809083, "gpqa": 0.937373737373737, "critpt": 0.282857142857143, "apexAgents": null, "mmmuPro": 0.824277456647399, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5356401051539629, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.86, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "intelligenceIndexTimePerTask": 533.117340121058, "intelligenceIndexCost": {"total": 4331.683086670721, "input": 2318.4105366707213, "nonCacheInput": 176.86891500000002, "cacheRead": 1503.106576376459, "cacheWrite": 638.4350452942621, "output": 2013.2725500000001, "reasoning": 1291.9434, "answer": 721.32915}, "intelligenceIndexCostPerTask": {"cost": {"total": 3.6132670078004714, "input": 2.457285921808886, "nonCacheInput": 0.12886904238179273, "cacheRead": 1.8172430157813064, "cacheWrite": 0.5111738636457864, "output": 1.155981085991586, "reasoning": 0.6351958119992573, "answer": 0.5207852739923285}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 1.5613803512263267}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.30271454854977625}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.05354085313494873}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.314006653925276}, {"slug": "scicode", "weightedCostPerTask": 0.004808434027777778}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.035209134847080624}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.10346749}, {"slug": "critpt", "weightedCostPerTask": 0.1994518357142857}, {"slug": "omniscience", "weightedCostPerTask": 0.0014100488749999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0372776575}]}, "canonicalIntelligenceIndexTokenCount": {"input": 3143736543, "output": 80530902, "answer": 28853166, "reasoning": 51677736}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 25407.832479970297, "answer": 20831.41095969314, "output": 46239.243439663434}, "briefcaseBreakdown": {"overall": {"elo": 1556.66, "lower95ci": 1549.99, "upper95ci": 1563.84}, "rubricPassRate": 0.5383838383838384, "analyticalQuality": {"elo": 1814.96, "lower95ci": 1803.29, "upper95ci": 1828.12}, "presentation": {"elo": 1435.62, "lower95ci": 1424.21, "upper95ci": 1446.86}}, "briefcaseTotalCost": 947.2374130773048, "timescaleData": {"medianOutputSpeed": 53.6853222680299, "medianTimeToFirstChunk": 12.17768284}, "outputSpeedVariance": {"p05": 39.7953386404427, "q25": 44.6429315055819, "median": 53.6853222680299, "q75": 63.9194276669479, "p95": 72.939069848369}, "timeToFirstChunkVariance": {"p05": 1.24353486890003, "q25": 4.51973448274998, "median": 12.17768284, "q75": 18.34822578025, "p95": 32.38801474495}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 52.1445462103823, "medianTimeToFirstChunk": 12.4195416805, "medianTimeToFirstAnswerToken": 12.4195416805, "medianEndToEndResponseTime": 22.008272167916665}, "long": {"medianOutputSpeed": 53.6853222680299, "medianTimeToFirstChunk": 12.17768284, "medianTimeToFirstAnswerToken": 12.17768284, "medianEndToEndResponseTime": 21.491215457047446}, "hundredK": {"medianOutputSpeed": 63.5479253110992, "medianTimeToFirstChunk": 16.8183762825, "medianTimeToFirstAnswerToken": 16.8183762825, "medianEndToEndResponseTime": 24.68645376185511}, "mediumParallel": {"medianOutputSpeed": 49.0307549608279, "medianTimeToFirstChunk": 17.6817831600001, "medianTimeToFirstAnswerToken": 17.6817831600001, "medianEndToEndResponseTime": 27.879464195086438}}, "endToEndResponseTime": {"input": 12.17768284, "reasoning": 0, "answer": 9.313532617047445, "total": 21.491215457047446}, "timeToFirstAnswerToken": {"input": 12.17768284, "reasoning": 0, "total": 12.17768284}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 3, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "713fae11-c75c-4f10-ae2c-8e4074cd58af", "slug": "ministral-3-14b", "name": "Ministral 3 14B", "shortName": "Ministral 3 14B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "ministral-3-14b", "name": "Ministral 3 14B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 14, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512", "microevalsEnabled": false, "intelligenceIndex": 6.04436817215002, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 5.415922761775029, "strategyAndOps": 4.070650158285546, "legal": 5.868054115226994, "engineering": 7.730088044485636, "economics": 8.59103877046648}, "omniscience": -66.3666666666667, "omniscienceBreakdown": {"accuracy": 0.13583333333333333, "hallucinationRate": 0.925168756027001}, "gdpPdfAllPass": 0.012, "gdpval": 432.06, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.271929824561404, "tauBanking": 0.065979381443299, "terminalbenchHard": 0.0454545454545455, "terminalBench21": 0.0973782771535581, "terminalBench40": 0, "scicode": 0.238425925925926, "lcr": 0.263333333333333, "ifbench": 0.320408163265306, "hle": 0.046339202965709, "gpqa": 0.571717171717172, "critpt": 0, "apexAgents": null, "mmmuPro": 0.498265895953757, "livecodebench": 0.351322751322751, "aime25": 0.3, "analystAgent": null, "automationBenchPartialScore": 0.0055121326737361245, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.2, "price1mBlended7To2To1": 0.20000000000000004, "price1mBlended0To1To1": 0.2, "price1mBlended100To1To1": 0.19999999999999998, "price1mBlended0To100To1": 0.19999999999999998, "intelligenceIndexTimePerTask": 64.66825148323841, "intelligenceIndexCost": {"total": 249.873237, "input": 246.9668802, "nonCacheInput": 3.5318188, "cacheRead": 0, "cacheWrite": 243.4350614, "output": 2.9063568, "reasoning": 0, "answer": 2.9063568}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.13923016604368538, "input": 0.13802677872283134, "nonCacheInput": 0.002249939120309075, "cacheRead": 0, "cacheWrite": 0.1357768396025223, "output": 0.0012033873208540022, "reasoning": 0, "answer": 0.0012033873208540022}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.06407164582417582}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.023919455909090913}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.009707485266362254}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.039079925151515156}, {"slug": "scicode", "weightedCostPerTask": 7.170194444444445e-05}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 6.678580166821131e-05}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0011144106000000001}, {"slug": "critpt", "weightedCostPerTask": 0.0002479485714285714}, {"slug": "omniscience", "weightedCostPerTask": 5.101775e-06}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0009457052000000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1234834401, "output": 14531784, "answer": 14531784, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 6016.936604270011, "output": 6016.936604270011}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 149.57, "lower95ci": 139.51, "upper95ci": 158.79}, "rubricPassRate": 0.049029622063329927, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 54.17, "lower95ci": 35.99, "upper95ci": 72.47}}, "briefcaseTotalCost": 38.870131799999996, "timescaleData": {"medianOutputSpeed": 87.0444397150657, "medianTimeToFirstChunk": 0.907481412999914}, "outputSpeedVariance": {"p05": 45.6744842979992, "q25": 57.6559850128126, "median": 87.0444397150657, "q75": 105.097501253098, "p95": 118.522118711667}, "timeToFirstChunkVariance": {"p05": 0.815231269300079, "q25": 0.859059697250025, "median": 0.907481412999914, "q75": 1.14591057775005, "p95": 1.5829300099}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 76.757335750967, "medianTimeToFirstChunk": 0.531163397, "medianTimeToFirstAnswerToken": 0.531163397, "medianEndToEndResponseTime": 7.045198767146377}, "long": {"medianOutputSpeed": 87.0444397150657, "medianTimeToFirstChunk": 0.907481412999914, "medianTimeToFirstAnswerToken": 0.907481412999914, "medianEndToEndResponseTime": 6.651673708759613}, "hundredK": {"medianOutputSpeed": 59.6945838804744, "medianTimeToFirstChunk": 9.28871238950002, "medianTimeToFirstAnswerToken": 9.28871238950002, "medianEndToEndResponseTime": 17.66468165668082}, "mediumParallel": {"medianOutputSpeed": 72.4238780281341, "medianTimeToFirstChunk": 0.58973112700005, "medianTimeToFirstAnswerToken": 0.58973112700005, "medianEndToEndResponseTime": 7.49353155323196}}, "endToEndResponseTime": {"input": 0.907481412999914, "reasoning": 0, "answer": 5.744192295759699, "total": 6.651673708759613}, "timeToFirstAnswerToken": {"input": 0.907481412999914, "reasoning": 0, "total": 0.907481412999914}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 2, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "715e05fb-1313-441c-bf1d-8651c752a841", "slug": "k-exaone", "name": "K-EXAONE (Reasoning)", "shortName": "K-EXAONE", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-31", "knowledgeCutoffDate": "2024-12-01", "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "k-exaone", "name": "K-EXAONE"}, "deprecated": true, "deprecatedTo": "k-exaone-2-0-0803", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 236, "inferenceParametersActiveBillions": 23, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "K Exaone", "licenseUrl": "https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B", "microevalsEnabled": false, "intelligenceIndex": 14.3683727563074, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -57.9666666666667, "omniscienceBreakdown": {"accuracy": 0.1635, "hallucinationRate": 0.8884239888423989}, "gdpval": 539.71, "gdpvalNormalized": 0.01985500000000002, "itBenchSre": null, "tau2": 0.742690058479532, "tauBanking": null, "terminalbenchHard": 0.227272727272727, "terminalBench21": 0.303370786516854, "terminalBench40": null, "scicode": null, "lcr": 0.613333333333333, "ifbench": 0.646938775510204, "hle": 0.139481000926784, "gpqa": 0.782828282828283, "critpt": 0.0111836734693878, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.768253968253968, "aime25": 0.903333333333334, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "45157c16-fcbb-4110-b20f-7bca754b6554", "slug": "lg", "name": "LG AI Research", "logo": "/img/logos/lg_small.png", "color": "#df3b8a", "country": "kr", "url": "https://www.lgresearch.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "71e8d48c-1920-4f27-8ea9-1f10becc615a", "slug": "llama-3-2-instruct-3b", "name": "Llama 3.2 Instruct 3B", "shortName": "Llama 3.2 3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-25", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-2-instruct-3b", "name": "Llama 3.2 Instruct 3B"}, "deprecated": true, "deprecatedTo": "llama-3-3-instruct-70b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 3, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.2 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Llama-3.2-3B", "microevalsEnabled": false, "intelligenceIndex": 5.70063694214945, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.210526315789474, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.0433333333333333, "ifbench": 0.261904761904762, "hle": 0.0535, "gpqa": 0.254545454545455, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0825396825396825, "aime25": 0.0333333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "71f51ea9-94fe-4635-a80d-4cfffbb685f4", "slug": "gemini-2-5-flash-lite-preview-09-2025", "name": "Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)", "shortName": "Gemini 2.5 Flash-Lite (Sep) (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-25", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-flash-lite-preview-09-2025", "name": "Gemini 2.5 Flash-Lite Preview (Sep '25)"}, "deprecated": true, "deprecatedTo": "gemini-3-1-flash-lite-preview", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.33681660061059, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -42.5666666666667, "omniscienceBreakdown": {"accuracy": 0.1415, "hallucinationRate": 0.6606484177829548}, "gdpval": null, "itBenchSre": null, "tau2": 0.304093567251462, "tauBanking": null, "terminalbenchHard": 0.0757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.496666666666667, "ifbench": 0.418367346938776, "hle": 0.0509731232622799, "gpqa": 0.65050505050505, "critpt": 0, "apexAgents": null, "mmmuPro": 0.634104046242775, "livecodebench": 0.641269841269841, "aime25": 0.466666666666667, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.01, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.17500000000000002, "price1mBlended7To2To1": 0.067, "price1mBlended0To1To1": 0.25, "price1mBlended100To1To1": 0.014705882352941176, "price1mBlended0To100To1": 0.10297029702970298, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7261504e-503c-4a66-a9d3-a3272cdf9ad6", "slug": "inkling-small", "name": "Inkling Small", "shortName": "Inkling Small", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "inkling-small", "name": "Inkling Small"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 266, "inferenceParametersActiveBillions": 12, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/thinkingmachines/Inkling-Small", "microevalsEnabled": false, "intelligenceIndex": 26.0860584411942, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 28.29803945464558, "strategyAndOps": 22.051359169185325, "legal": 28.74497520240199, "engineering": 29.339355334224017, "economics": 38.24871875965401}, "omniscience": -8.93333333333333, "omniscienceBreakdown": {"accuracy": 0.33166666666666667, "hallucinationRate": 0.629925187032419}, "gdpPdfAllPass": 0.112, "gdpval": 1191.44, "gdpvalNormalized": 0.34572, "itBenchSre": null, "tau2": null, "tauBanking": 0.187628865979381, "terminalbenchHard": null, "terminalBench21": 0.550561797752809, "terminalBench40": 0.0101010101010101, "scicode": 0.496527777777778, "lcr": 0.756666666666667, "ifbench": null, "hle": 0.333178869323448, "gpqa": 0.894949494949495, "critpt": 0.0828571428571429, "apexAgents": null, "mmmuPro": 0.740462427745665, "livecodebench": null, "aime25": null, "analystAgent": 0.275, "automationBenchPartialScore": 0.048142275152503786, "enterpriseOpsGym": 0.4270367054610564, "price1mInputTokens": 0.3, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.06, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5249999999999999, "price1mBlended7To2To1": 0.22199999999999998, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.07352941176470588, "price1mBlended0To100To1": 0.3089108910891089, "intelligenceIndexTimePerTask": 155.66582425084718, "intelligenceIndexCost": {"total": 240.84597331335652, "input": 76.11289531335655, "nonCacheInput": 5.991492, "cacheRead": 53.16810802166086, "cacheWrite": 16.95329529169568, "output": 164.73307799999998, "reasoning": 153.06557279999998, "answer": 11.667505199999999}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.0894649973284348, "input": 0.053273380077746235, "nonCacheInput": 0.00405798457701741, "cacheRead": 0.038486787821886706, "cacheWrite": 0.010728607678842116, "output": 0.03619161725068855, "reasoning": 0.027463019003434955, "answer": 0.008728598247253591}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.017705579438213256}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.008890024629976439}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.002849366204865099}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.03508047687317921}, {"slug": "scicode", "weightedCostPerTask": 0.0023154234375}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.004262272562557923}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0036747746999999994}, {"slug": "critpt", "weightedCostPerTask": 0.012199389857142856}, {"slug": "omniscience", "weightedCostPerTask": 0.0008977568249999998}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0015899328000000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 962617758, "output": 137277565, "answer": 9722921, "reasoning": 127554644}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 22885.84916952913, "answer": 7273.831872711327, "output": 30159.68104224046}, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 5, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 912.02, "lower95ci": 905.15, "upper95ci": 919.59}, "rubricPassRate": 0.2, "analyticalQuality": {"elo": 788.74, "lower95ci": 774.32, "upper95ci": 803.42}, "presentation": {"elo": 1061.01, "lower95ci": 1048.05, "upper95ci": 1073.77}}, "briefcaseTotalCost": 10.741384859182709, "timescaleData": {"medianOutputSpeed": 184.775457809178, "medianTimeToFirstChunk": 2.11660956699995}, "outputSpeedVariance": {"p05": 79.024106977613, "q25": 154.600472735009, "median": 184.775457809178, "q75": 201.938045821898, "p95": 210.208106491672}, "timeToFirstChunkVariance": {"p05": 1.9544553252, "q25": 2.00942834700004, "median": 2.11660956699995, "q75": 2.46353789, "p95": 4.96636114980007}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 177.612469982532, "medianTimeToFirstChunk": 1.74127321950002, "medianTimeToFirstAnswerToken": 13.001743839590478, "medianEndToEndResponseTime": 15.816861494613093}, "long": {"medianOutputSpeed": 184.775457809178, "medianTimeToFirstChunk": 2.11660956699995, "medianTimeToFirstAnswerToken": 12.940557853819769, "medianEndToEndResponseTime": 15.646544925524724}, "hundredK": {"medianOutputSpeed": 170.219394995347, "medianTimeToFirstChunk": 5.39777673599997, "medianTimeToFirstAnswerToken": 17.147319143048655, "medianEndToEndResponseTime": 20.084704744810825}, "mediumParallel": {"medianOutputSpeed": 167.953822320838, "medianTimeToFirstChunk": 1.89182562550002, "medianTimeToFirstAnswerToken": 13.79986065776889, "medianEndToEndResponseTime": 16.776869415836106}}, "endToEndResponseTime": {"input": 2.11660956699995, "reasoning": 10.82394828681982, "answer": 2.705987071704955, "total": 15.646544925524724}, "timeToFirstAnswerToken": {"input": 2.11660956699995, "reasoning": 10.82394828681982, "total": 12.940557853819769}, "performanceDataSource": {"type": "firstParty", "providerName": "Thinking Machines"}, "hostModelCount": 3, "creator": {"id": "8f3f9fdd-e42f-4814-a35e-5da1925b539b", "slug": "thinking-machines", "name": "Thinking Machines", "logo": "/img/logos/thinking_machines.svg", "color": "#676767", "country": "us", "url": "https://thinkingmachines.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "72c358fd-7d45-4d68-89aa-699743710924", "slug": "gpt-4-1-nano", "name": "GPT-4.1 nano", "shortName": "GPT-4.1 nano", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-14", "knowledgeCutoffDate": "2024-05-31", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4-1-nano", "name": "GPT-4.1 nano"}, "deprecated": true, "deprecatedTo": "gpt-5-nano-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.81796186868883, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -57.5833333333333, "omniscienceBreakdown": {"accuracy": 0.13683333333333333, "hallucinationRate": 0.8256420158331724}, "gdpval": 12.78, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.172514619883041, "tauBanking": 0.0350515463917526, "terminalbenchHard": 0.0378787878787879, "terminalBench21": 0.0374531835205993, "terminalBench40": null, "scicode": null, "lcr": 0.203333333333333, "ifbench": 0.320408163265306, "hle": 0.0375347544022243, "gpqa": 0.512121212121212, "critpt": 0, "apexAgents": null, "mmmuPro": 0.401156069364162, "livecodebench": 0.325925925925926, "aime25": 0.24, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.025, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": 0.2519, "price1mBlended0To3To1": 0.17500000000000002, "price1mBlended7To2To1": 0.0775, "price1mBlended0To1To1": 0.25, "price1mBlended100To1To1": 0.029411764705882353, "price1mBlended0To100To1": 0.10297029702970298, "timescaleData": {"medianOutputSpeed": 141.071308697051, "medianTimeToFirstChunk": 0.837584317000164}, "outputSpeedVariance": {"p05": 64.7834288125125, "q25": 103.756466685688, "median": 141.071308697051, "q75": 150.651991438139, "p95": 200.661590961992}, "timeToFirstChunkVariance": {"p05": 0.537349091199894, "q25": 0.671962375999982, "median": 0.837584317000164, "q75": 0.951242836999938, "p95": 1.30085722539984}, "performanceByPromptType": {"long": {"medianOutputSpeed": 141.071308697051, "medianTimeToFirstChunk": 0.837584317000164, "medianTimeToFirstAnswerToken": 0.837584317000164, "medianEndToEndResponseTime": 4.3818911262163756}}, "endToEndResponseTime": {"input": 0.837584317000164, "reasoning": 0, "answer": 3.5443068092162116, "total": 4.3818911262163756}, "timeToFirstAnswerToken": {"input": 0.837584317000164, "reasoning": 0, "total": 0.837584317000164}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7393c56a-ec31-48e9-b804-c04f2d2cb641", "slug": "llama-3-1-nemotron-instruct-70b", "name": "Llama 3.1 Nemotron Instruct 70B", "shortName": "Llama 3.1 Nemotron 70B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-10-15", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-1-nemotron-instruct-70b", "name": "Llama 3.1 Nemotron Instruct 70B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.1 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF", "microevalsEnabled": false, "intelligenceIndex": 6.9438219838506, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -40.8333333333333, "omniscienceBreakdown": {"accuracy": 0.17766666666666667, "hallucinationRate": 0.7126064045399271}, "gdpval": null, "itBenchSre": null, "tau2": 0.230994152046784, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.0833333333333333, "ifbench": 0.307482993197279, "hle": 0.0419, "gpqa": 0.464646464646465, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.169312169312169, "aime25": 0.11, "analystAgent": null, "price1mInputTokens": 1.2, "price1mOutputTokens": 1.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.2, "price1mBlended7To2To1": 1.2, "price1mBlended0To1To1": 1.2, "price1mBlended100To1To1": 1.2, "price1mBlended0To100To1": 1.2, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 4, "transparencyMethodology": 3, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 75.8546894745425, "medianTimeToFirstChunk": 7.8709744245001}, "outputSpeedVariance": {"p05": 14.0755993501221, "q25": 34.1285264672937, "median": 75.8546894745425, "q75": 189.630233965656, "p95": 315.335371882214}, "timeToFirstChunkVariance": {"p05": 1.78650426075008, "q25": 2.49161959924999, "median": 7.8709744245001, "q75": 12.60087361775, "p95": 72.9413884570499}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 45.1189924839061, "medianTimeToFirstChunk": 8.192318371, "medianTimeToFirstAnswerToken": 8.192318371, "medianEndToEndResponseTime": 19.274126108137516}, "long": {"medianOutputSpeed": 75.8546894745425, "medianTimeToFirstChunk": 7.8709744245001, "medianTimeToFirstAnswerToken": 7.8709744245001, "medianEndToEndResponseTime": 14.462524709177021}, "hundredK": {"medianOutputSpeed": 97.7297098940759, "medianTimeToFirstChunk": 8.08622338499998, "medianTimeToFirstAnswerToken": 8.08622338499998, "medianEndToEndResponseTime": 13.202374865874361}, "mediumParallel": {"medianOutputSpeed": 62.8364054179804, "medianTimeToFirstChunk": 5.88954361699996, "medianTimeToFirstAnswerToken": 5.88954361699996, "medianEndToEndResponseTime": 13.846714251985501}}, "endToEndResponseTime": {"input": 7.8709744245001, "reasoning": 0, "answer": 6.591550284676921, "total": 14.462524709177021}, "timeToFirstAnswerToken": {"input": 7.8709744245001, "reasoning": 0, "total": 7.8709744245001}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "739684ba-0f63-4e2a-b4ee-30741c9e9320", "slug": "llama-3-1-instruct-8b", "name": "Llama 3.1 Instruct 8B", "shortName": "Llama 3.1 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-07-23", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-1-instruct-8b", "name": "Llama 3.1 Instruct 8B"}, "deprecated": true, "deprecatedTo": "llama-3-2-instruct-11b-vision", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.1 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Meta-Llama-3.1-8B", "microevalsEnabled": false, "intelligenceIndex": 6.93350756346201, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -30.8833333333333, "omniscienceBreakdown": {"accuracy": 0.085, "hallucinationRate": 0.43041894353369764}, "gdpval": -150.78, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.16374269005848, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": 0.0149812734082397, "terminalBench40": null, "scicode": null, "lcr": 0.18, "ifbench": 0.285714285714286, "hle": 0.0529, "gpqa": 0.258585858585859, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.116402116402116, "aime25": 0.0433333333333333, "analystAgent": null, "price1mInputTokens": 0.02, "price1mOutputTokens": 0.05, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.0275, "price1mBlended7To2To1": 0.023000000000000003, "price1mBlended0To1To1": 0.035, "price1mBlended100To1To1": 0.020294117647058824, "price1mBlended0To100To1": 0.020297029702970294, "timescaleData": {"medianOutputSpeed": 138.213323967943, "medianTimeToFirstChunk": 0.82332753799983}, "outputSpeedVariance": {"p05": 12.6956308194053, "q25": 34.2108069901036, "median": 138.213323967943, "q75": 186.588172853666, "p95": 699.675263447538}, "timeToFirstChunkVariance": {"p05": 0.660380075599914, "q25": 0.728716841500031, "median": 0.82332753799983, "q75": 1.02463982350009, "p95": 2.29378463339996}, "performanceByPromptType": {"long": {"medianOutputSpeed": 138.213323967943, "medianTimeToFirstChunk": 0.82332753799983, "medianTimeToFirstAnswerToken": 0.82332753799983, "medianEndToEndResponseTime": 4.440923770009772}}, "endToEndResponseTime": {"input": 0.82332753799983, "reasoning": 0, "answer": 3.6175962320099417, "total": 4.440923770009772}, "timeToFirstAnswerToken": {"input": 0.82332753799983, "reasoning": 0, "total": 0.82332753799983}, "performanceDataSource": {"type": "median"}, "hostModelCount": 7, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "739e531a-eb0a-478f-bb67-5845b79ce65d", "slug": "lfm2-2-6b", "name": "LFM2 2.6B", "shortName": "LFM2 2.6B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-23", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "lfm2-2-6b", "name": "LFM2 2.6B"}, "deprecated": true, "deprecatedTo": "lfm2-5-2-6b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 2.57, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32768, "licenseName": "lfm 1.0", "licenseUrl": "https://huggingface.co/LiquidAI/LFM2-2.6B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LiquidAI/LFM2-2.6B", "microevalsEnabled": false, "intelligenceIndex": 5.21069904506505, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.0666666666667, "omniscienceBreakdown": {"accuracy": 0.05416666666666667, "hallucinationRate": 0.628898678414097}, "gdpval": null, "itBenchSre": null, "tau2": 0.134502923976608, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.195238095238095, "hle": 0.0546802594995366, "gpqa": 0.306060606060606, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0814814814814815, "aime25": 0.0833333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5b1886c4-43ba-4007-b840-9d21a2b7d42c", "slug": "liquidai", "name": "Liquid AI", "logo": "/img/logos/liquidai_small.svg", "color": "#000000", "country": "us", "url": "https://www.liquid.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "744fa3c1-42a7-4995-b138-fb6be11f463c", "slug": "gemini-3-8-flash-medium", "name": "Gemini 3.8 Flash (medium)", "shortName": "Gemini 3.8 Flash (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gemini-3-8-flash", "name": "Gemini 3.8 Flash"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 39.9993187061926, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 45.006863760475774, "strategyAndOps": 48.88312427041714, "legal": 51.32177943716094, "engineering": 40.677852921777024, "economics": 50.57981742354033}, "omniscience": 28.5833333333333, "omniscienceBreakdown": {"accuracy": 0.5298333333333334, "hallucinationRate": 0.5189649060616802}, "gdpPdfAllPass": 0.228, "gdpval": 1455.38, "gdpvalNormalized": 0.47769000000000006, "itBenchSre": null, "tau2": null, "tauBanking": 0.457731958762887, "terminalbenchHard": null, "terminalBench21": 0.838951310861423, "terminalBench40": 0.196969696969697, "scicode": 0.550925925925926, "lcr": 0.84, "ifbench": null, "hle": 0.421223354958295, "gpqa": 0.935353535353535, "critpt": 0.122857142857143, "apexAgents": null, "mmmuPro": 0.842196531791908, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.6088997392114149, "price1mInputTokens": 0.75, "price1mOutputTokens": 3.75, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.75, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5, "price1mBlended7To2To1": 0.5775, "price1mBlended0To1To1": 2.25, "price1mBlended100To1To1": 0.11764705882352941, "price1mBlended0To100To1": 0.7797029702970297, "intelligenceIndexCost": {"total": 1100.060747791257, "input": 743.687297791257, "nonCacheInput": 16.4052645, "cacheRead": 290.6418956898603, "cacheWrite": 436.64013760139676, "output": 356.37345, "reasoning": 233.6941425, "answer": 122.6793075}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.9310379374376306, "input": 0.733792430681439, "nonCacheInput": 0.011138314006110156, "cacheRead": 0.3012328521578915, "cacheWrite": 0.42142126451743733, "output": 0.1972455067561916, "reasoning": 0.10108435575019221, "answer": 0.09616115100599934}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.29849338778065554}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.12442497030319828}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0177114636259795}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.461055082184726}, {"slug": "scicode", "weightedCostPerTask": 0.0029326989583333333}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0024840718025949953}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0087463005}, {"slug": "critpt", "weightedCostPerTask": 0.010172202857142858}, {"slug": "omniscience", "weightedCostPerTask": 0.0005331588}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.004484600625000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4479285812, "output": 95032920, "answer": 32714482, "reasoning": 62318438}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 26955.82820005126, "answer": 25642.973601599828, "output": 52598.80180165109}, "briefcaseBreakdown": {"overall": {"elo": 1176.54, "lower95ci": 1166.59, "upper95ci": 1186.65}, "rubricPassRate": 0.4111111111111111, "analyticalQuality": {"elo": 1116.51, "lower95ci": 1098.79, "upper95ci": 1135.3}, "presentation": {"elo": 1162.75, "lower95ci": 1144.67, "upper95ci": 1180.25}}, "briefcaseTotalCost": 181.08598858693102, "timescaleData": {}, "performanceByPromptType": {"hundredK": {"medianOutputSpeed": 286.888409292529, "medianTimeToFirstChunk": 9.80611171199999, "medianTimeToFirstAnswerToken": 9.80611171199999, "medianEndToEndResponseTime": 11.54894963714659}}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "755d7281-2ed8-48c7-808f-709ec4cbfb71", "slug": "gemma-4-e2b-non-reasoning", "name": "Gemma 4 E2B (Non-reasoning)", "shortName": "Gemma 4 E2B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-4-e2b", "name": "Gemma 4 E2B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 5.1, "inferenceParametersActiveBillions": 2.3, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-4-E2B-it", "microevalsEnabled": false, "intelligenceIndex": 6.47543520107148, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -60.1833333333333, "omniscienceBreakdown": {"accuracy": 0.0815, "hallucinationRate": 0.7439666122300853}, "gdpval": null, "itBenchSre": null, "tau2": 0.222222222222222, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.163333333333333, "ifbench": 0.336054421768707, "hle": 0.0472659870250232, "gpqa": 0.405050505050505, "critpt": 0, "apexAgents": null, "mmmuPro": 0.417919075144509, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": true, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "75e1c197-f239-4361-a9d6-66dccfead236", "slug": "deepseek-v3-0324", "name": "DeepSeek V3 0324", "shortName": "DeepSeek V3 0324", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-25", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v3-0324", "name": "DeepSeek V3 0324"}, "deprecated": true, "deprecatedTo": "deepseek-v3-1", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 671, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3-0324", "microevalsEnabled": false, "intelligenceIndex": 9.72000501684011, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 9.180239690134428, "strategyAndOps": 7.1914695957771535, "legal": 11.678762539235834, "engineering": 11.098887887887889, "economics": 13.772333333333336}, "omniscience": -40.6666666666667, "omniscienceBreakdown": {"accuracy": 0.24316666666666667, "hallucinationRate": 0.8586214490200397}, "gdpPdfAllPass": 0.016, "gdpval": 274.71, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.470760233918129, "tauBanking": 0.0474226804123711, "terminalbenchHard": 0.151515151515152, "terminalBench21": 0.138576779026217, "terminalBench40": 0, "scicode": 0.390046296296296, "lcr": 0.406666666666667, "ifbench": 0.410204081632653, "hle": 0.0474, "gpqa": 0.654545454545455, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.405291005291005, "aime25": 0.41, "analystAgent": null, "automationBenchPartialScore": 0.0027298597954690243, "price1mInputTokens": 0.845, "price1mOutputTokens": 1.175, "cacheHitPrice": 0.7925, "cacheHitDiscountPercent": 0.4374999999999999, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.9275, "price1mBlended7To2To1": 0.8412499999999999, "price1mBlended0To1To1": 1.01, "price1mBlended100To1To1": 0.7967647058823529, "price1mBlended0To100To1": 0.8482673267326732, "intelligenceIndexCost": {"total": 87.21067297732687, "input": 82.74110222732686, "nonCacheInput": 12.80973018, "cacheRead": 31.37042049916104, "cacheWrite": 38.560951548165825, "output": 4.46957075, "reasoning": 0, "answer": 4.46957075}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.10527388598776051, "input": 0.1029668435165565, "nonCacheInput": 0.007388739163264151, "cacheRead": 0.04392546231898557, "cacheWrite": 0.051652642034306764, "output": 0.0023070424712040138, "reasoning": 0, "answer": 0.0023070424712040138}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.07130520639091321}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.005848007359600259}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.00016934619137142876}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.02005606984762381}, {"slug": "scicode", "weightedCostPerTask": 0.0002500673715277778}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00013228705050973122}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.002892423305}, {"slug": "critpt", "weightedCostPerTask": 0.0005613395357142856}, {"slug": "omniscience", "weightedCostPerTask": 1.6993747999999998e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0040421451874999995}]}, "canonicalIntelligenceIndexTokenCount": {"input": 100377833, "output": 3803890, "answer": 3803890, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 1963.4404010246926, "output": 1963.4404010246926}, "briefcaseBreakdown": {"overall": {"elo": 91.96, "lower95ci": 81.39, "upper95ci": 101.71}, "rubricPassRate": 0.032989690721649485, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 25.99, "lower95ci": 4.12, "upper95ci": 48.27}}, "briefcaseTotalCost": 43.258491877154015, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "76361085-f5dc-49ec-b069-fe56ca885933", "slug": "command-r-plus-04-2024", "name": "Command-R+ (Apr '24)", "shortName": "Command-R+ (Apr)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-04-04", "knowledgeCutoffDate": "2023-02-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "command-r-plus-04-2024", "name": "Command-R+ (Apr '24)"}, "deprecated": true, "deprecatedTo": "command-a", "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 104, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "CC-BY-NC 4.0 License with Acceptable Use Addendum", "licenseUrl": "https://cohere.com/c4ai-cc-by-nc-license", "modelWeightsSourceUrl": "https://huggingface.co/CohereForAI/c4ai-command-r-plus", "microevalsEnabled": false, "intelligenceIndex": 5.29816467823515, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0463, "gpqa": 0.323232323232323, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.121693121693122, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "671d3708-c407-4b8f-b350-f728e4689d26", "slug": "cohere", "name": "Cohere", "logo": "/img/logos/cohere_small.svg", "color": "#D18EE2", "country": "ca", "url": "https://cohere.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "764dd095-6ebd-4760-8eb3-cbc40964db2e", "slug": "sarvam-30b", "name": "Sarvam 30B (high)", "shortName": "Sarvam 30B (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-06", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "sarvam-30b", "name": "Sarvam 30B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32.2, "inferenceParametersActiveBillions": 2.4, "sizeClass": "small", "contextWindowTokens": 65536, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/sarvamai/sarvam-30b", "microevalsEnabled": false, "intelligenceIndex": 6.55971145066503, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -71.5166666666667, "omniscienceBreakdown": {"accuracy": 0.12616666666666668, "hallucinationRate": 0.9628075529277131}, "gdpval": null, "itBenchSre": null, "tau2": 0.345029239766082, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.264625850340136, "hle": 0.0750695088044486, "gpqa": 0.633333333333333, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.026, "price1mOutputTokens": 0.11, "cacheHitPrice": 0.016, "cacheHitDiscountPercent": 0.3846153846153846, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.047, "price1mBlended7To2To1": 0.0274, "price1mBlended0To1To1": 0.068, "price1mBlended100To1To1": 0.017019607843137257, "price1mBlended0To100To1": 0.02683168316831683, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "20273002-dc38-4ebc-8377-8f432aec9e7e", "slug": "sarvam", "name": "Sarvam", "logo": "/img/logos/sarvam.svg", "color": "#807D77", "country": "in", "url": "https://www.sarvam.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7656c62b-5345-435b-bf12-b6ce2ca0d58d", "slug": "qwen2-72b-instruct", "name": "Qwen2 Instruct 72B", "shortName": "Qwen2 72B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-06-07", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen2-72b-instruct", "name": "Qwen2 Instruct 72B"}, "deprecated": true, "deprecatedTo": "qwen2-5-72b-instruct", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 72, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 131072, "licenseName": "Tongyi Qianwen LICENSE AGREEMENT", "licenseUrl": "https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen2-72B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 6.32869002003161, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0366, "gpqa": 0.370707070707071, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.158730158730159, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "76aa6af5-fdc6-4739-a300-983f14e74a67", "slug": "gpt-4-turbo", "name": "GPT-4 Turbo", "shortName": "GPT-4 Turbo", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-11-06", "knowledgeCutoffDate": "2023-04-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4-turbo", "name": "GPT-4 Turbo"}, "deprecated": true, "deprecatedTo": "gpt-4-turbo-0125-preview", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.04351520157305, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0313, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.291005291005291, "aime25": null, "analystAgent": null, "price1mInputTokens": 10, "price1mOutputTokens": 30, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 7.65, "price1mBlended0To3To1": 15, "price1mBlended7To2To1": 12, "price1mBlended0To1To1": 20, "price1mBlended100To1To1": 10.196078431372548, "price1mBlended0To100To1": 10.198019801980198, "timescaleData": {"medianOutputSpeed": 31.5623933916787, "medianTimeToFirstChunk": 3.08061507999992}, "outputSpeedVariance": {"p05": 21.1597325691126, "q25": 29.6101484256051, "median": 31.5623933916787, "q75": 32.8592467713623, "p95": 33.2854901466332}, "timeToFirstChunkVariance": {"p05": 2.3907230913, "q25": 2.91545432149999, "median": 3.08061507999992, "q75": 3.56754377100009, "p95": 4.20447032089995}, "performanceByPromptType": {"long": {"medianOutputSpeed": 31.5623933916787, "medianTimeToFirstChunk": 3.08061507999992, "medianTimeToFirstAnswerToken": 3.08061507999992, "medianEndToEndResponseTime": 18.92225274654719}}, "endToEndResponseTime": {"input": 3.08061507999992, "reasoning": 0, "answer": 15.841637666547271, "total": 18.92225274654719}, "timeToFirstAnswerToken": {"input": 3.08061507999992, "reasoning": 0, "total": 3.08061507999992}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "76bce7fb-3a3f-4b66-a78d-35ccf3edf5d2", "slug": "nova-2-0-lite", "name": "Nova 2.0 Lite (Non-reasoning)", "shortName": "Nova 2.0 Lite (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-29", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "nova-2-0-lite", "name": "Nova 2.0 Lite"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 8.73661367769335, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -59.8166666666667, "omniscienceBreakdown": {"accuracy": 0.14016666666666666, "hallucinationRate": 0.8586935452607094}, "gdpval": null, "itBenchSre": null, "tau2": 0.619883040935672, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.186666666666667, "ifbench": 0.405442176870748, "hle": 0.0287303058387396, "gpqa": 0.603030303030303, "critpt": 0, "apexAgents": null, "mmmuPro": 0.490173410404624, "livecodebench": 0.346031746031746, "aime25": 0.336666666666667, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.42, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.52, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.32156862745098036, "price1mBlended0To100To1": 0.3217821782178218, "timescaleData": {"medianOutputSpeed": 152.947206251945, "medianTimeToFirstChunk": 1.04497885149999}, "outputSpeedVariance": {"p05": 95.3311779169701, "q25": 129.498480419488, "median": 152.947206251945, "q75": 191.35039349574, "p95": 206.917443209017}, "timeToFirstChunkVariance": {"p05": 0.921640495100093, "q25": 0.977266608249998, "median": 1.04497885149999, "q75": 1.13870676949992, "p95": 2.32175441405004}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 226.545454470569, "medianTimeToFirstChunk": 0.76467735350002, "medianTimeToFirstAnswerToken": 0.76467735350002, "medianEndToEndResponseTime": 2.9717399545506007}, "long": {"medianOutputSpeed": 152.947206251945, "medianTimeToFirstChunk": 1.04497885149999, "medianTimeToFirstAnswerToken": 1.04497885149999, "medianEndToEndResponseTime": 4.314080734775754}, "hundredK": {"medianOutputSpeed": 187.885577199254, "medianTimeToFirstChunk": 4.39835878900003, "medianTimeToFirstAnswerToken": 4.39835878900003, "medianEndToEndResponseTime": 7.059552944790639}, "mediumParallel": {"medianOutputSpeed": 232.131692878459, "medianTimeToFirstChunk": 1.51084962699986, "medianTimeToFirstAnswerToken": 1.51084962699986, "medianEndToEndResponseTime": 3.6647993690619796}}, "endToEndResponseTime": {"input": 1.04497885149999, "reasoning": 0, "answer": 3.2691018832757632, "total": 4.314080734775754}, "timeToFirstAnswerToken": {"input": 1.04497885149999, "reasoning": 0, "total": 1.04497885149999}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "76dcf6ef-39ea-4be0-b693-b88da25b4caf", "slug": "nvidia-nemotron-3-nano-30b-a3b-reasoning", "name": "NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)", "shortName": "Nemotron 3 Nano", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-15", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "nvidia-nemotron-3-nano-30b-a3b", "name": "NVIDIA Nemotron 3 Nano 30B A3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 31.6, "inferenceParametersActiveBillions": 3.6, "sizeClass": "small", "contextWindowTokens": 1000000, "licenseName": "Nvidia Nemotron Open Model License", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "microevalsEnabled": true, "intelligenceIndex": 8.8961440122188, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 9.191393881342714, "strategyAndOps": 5.881229045357266, "legal": 10.114416888063973, "engineering": 12.740988018006089, "economics": 14.86730537534754}, "omniscience": -51.5666666666667, "omniscienceBreakdown": {"accuracy": 0.173, "hallucinationRate": 0.8327287384119306}, "gdpPdfAllPass": 0.01, "gdpval": 438.32, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.409356725146199, "tauBanking": 0.0597938144329897, "terminalbenchHard": 0.136363636363636, "terminalBench21": 0.0674157303370786, "terminalBench40": 0, "scicode": 0.305555555555556, "lcr": 0.38, "ifbench": 0.710884353741497, "hle": 0.113994439295644, "gpqa": 0.756565656565657, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.740740740740741, "aime25": 0.91, "analystAgent": null, "automationBenchPartialScore": 0.009714694010433006, "price1mInputTokens": 0.05, "price1mOutputTokens": 0.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.08750000000000001, "price1mBlended7To2To1": 0.06500000000000002, "price1mBlended0To1To1": 0.125, "price1mBlended100To1To1": 0.051470588235294115, "price1mBlended0To100To1": 0.05148514851485149, "intelligenceIndexTimePerTask": 224.11261143536453, "intelligenceIndexCost": {"total": 63.743421350000006, "input": 28.044129350000002, "nonCacheInput": 0.7879770500000001, "cacheRead": 0, "cacheWrite": 27.256152300000004, "output": 35.69929200000001, "reasoning": 33.986321800000006, "answer": 1.7129702000000002}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.01675160944475661, "input": 0.011356612240642258, "nonCacheInput": 0.0004598339245663975, "cacheRead": 0, "cacheWrite": 0.010896778316075858, "output": 0.005394997204114354, "reasoning": 0.004793858732677218, "answer": 0.000601138471437137}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.008095116181318682}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.002774078954545455}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.002336767264079148}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.0011619118181818181}, {"slug": "scicode", "weightedCostPerTask": 0.00011380795138888888}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0006205766334569046}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00031606395000000005}, {"slug": "critpt", "weightedCostPerTask": 0.0009033042142857145}, {"slug": "omniscience", "weightedCostPerTask": 0.0001507703775}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00027921209999999996}]}, "canonicalIntelligenceIndexTokenCount": {"input": 560882587, "output": 178496460, "answer": 8564851, "reasoning": 169931609}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 23969.293663386088, "answer": 3005.6923571856855, "output": 26974.986020571774}, "openness": {"opennessIndex": 83.33333333333333, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "briefcaseBreakdown": {"overall": {"elo": 100.39, "lower95ci": 89.04, "upper95ci": 109.75}, "rubricPassRate": 0.029471544715447155, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 30.37, "lower95ci": 10.16, "upper95ci": 49.96}}, "briefcaseTotalCost": 4.91103715, "timescaleData": {"medianOutputSpeed": 109.611199447177, "medianTimeToFirstChunk": 1.80413407450001}, "outputSpeedVariance": {"p05": 63.4833138387502, "q25": 86.5125505640823, "median": 109.611199447177, "q75": 208.496402328369, "p95": 315.350899936594}, "timeToFirstChunkVariance": {"p05": 0.937990169800025, "q25": 1.11474626250007, "median": 1.80413407450001, "q75": 3.38209374725011, "p95": 15.5384594100001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 110.319393799007, "medianTimeToFirstChunk": 1.41304319999999, "medianTimeToFirstAnswerToken": 19.542221861404148, "medianEndToEndResponseTime": 24.07451652675519}, "long": {"medianOutputSpeed": 109.611199447177, "medianTimeToFirstChunk": 1.80413407450001, "medianTimeToFirstAnswerToken": 20.050444762522584, "medianEndToEndResponseTime": 24.612022434528228}, "hundredK": {"medianOutputSpeed": 190.14677609586, "medianTimeToFirstChunk": 5.87351883950003, "medianTimeToFirstAnswerToken": 16.391709266203485, "medianEndToEndResponseTime": 19.02125687287935}, "mediumParallel": {"medianOutputSpeed": 105.604427175297, "medianTimeToFirstChunk": 1.47286197899996, "medianTimeToFirstAnswerToken": 20.411461936368415, "medianEndToEndResponseTime": 25.146111925710528}}, "endToEndResponseTime": {"input": 1.80413407450001, "reasoning": 18.246310688022575, "answer": 4.561577672005644, "total": 24.612022434528228}, "timeToFirstAnswerToken": {"input": 1.80413407450001, "reasoning": 18.246310688022575, "total": 20.050444762522584}, "performanceDataSource": {"type": "median"}, "hostModelCount": 3, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7707a46f-895f-4247-b7a8-ddab87c9a11d", "slug": "deepseek-v4-flash-vision", "name": "DeepSeek V4 Flash 0731 Vision (Reasoning, Max Effort)", "shortName": "DeepSeek V4 Flash Vision (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-21", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash 0731"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 284, "inferenceParametersActiveBillions": 13, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 35.0122378035969, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 38.026031032199825, "strategyAndOps": 43.59947860816674, "legal": 36.906225706552014, "engineering": 34.888558297726384, "economics": 40.453207618937284}, "omniscience": -17.6333333333333, "omniscienceBreakdown": {"accuracy": 0.38566666666666666, "hallucinationRate": 0.9148128052088985}, "gdpPdfAllPass": 0.12, "gdpval": 1577.21, "gdpvalNormalized": 0.538605, "itBenchSre": null, "tau2": null, "tauBanking": 0.410309278350515, "terminalbenchHard": null, "terminalBench21": 0.741573033707865, "terminalBench40": 0.121212121212121, "scicode": 0.496527777777778, "lcr": 0.813333333333333, "ifbench": null, "hle": 0.344763670064875, "gpqa": 0.913131313131313, "critpt": 0.108571428571429, "apexAgents": null, "mmmuPro": 0.747976878612717, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.4747087040091967, "enterpriseOpsGym": 0.4709042076991943, "price1mInputTokens": 0.44, "price1mOutputTokens": 1.32, "cacheHitPrice": 0.014, "cacheHitDiscountPercent": 0.9681818181818181, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.66, "price1mBlended7To2To1": 0.2298, "price1mBlended0To1To1": 0.88, "price1mBlended100To1To1": 0.030980392156862747, "price1mBlended0To100To1": 0.4487128712871287, "intelligenceIndexTimePerTask": 231.82548918834064, "intelligenceIndexCost": {"total": 445.4128724482095, "input": 220.6200259282095, "nonCacheInput": 7.64663284, "cacheRead": 95.32083948404944, "cacheWrite": 117.65255360416006, "output": 224.79284652, "reasoning": 183.81627264, "answer": 40.976573880000004}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.314372044499279, "input": 0.2230621920453345, "nonCacheInput": 0.004512471084016182, "cacheRead": 0.1084393756669931, "cacheWrite": 0.11011034529432517, "output": 0.09130985245394455, "reasoning": 0.06059319913934186, "answer": 0.030716653314602705}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.12073192530591144}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.03463116526665481}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.005196745183697225}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.1279333912457593}, {"slug": "scicode", "weightedCostPerTask": 0.0034389608611111117}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00378751473957368}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.004353567240000001}, {"slug": "critpt", "weightedCostPerTask": 0.011051894228571427}, {"slug": "omniscience", "weightedCostPerTask": 0.000869383548}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0023774968799999997}]}, "canonicalIntelligenceIndexTokenCount": {"input": 7093402270, "output": 170297611, "answer": 31042859, "reasoning": 139254752}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 45903.93874192563, "answer": 23270.191905002044, "output": 69174.13064692768}, "briefcaseBreakdown": {"overall": {"elo": 1432.36, "lower95ci": 1423.12, "upper95ci": 1442.01}, "rubricPassRate": 0.4614594039054471, "analyticalQuality": {"elo": 1614.33, "lower95ci": 1596.44, "upper95ci": 1633.05}, "presentation": {"elo": 1357.66, "lower95ci": 1345.25, "upper95ci": 1371.02}}, "briefcaseTotalCost": 73.24403468558627, "timescaleData": {"medianOutputSpeed": 226.362008933674, "medianTimeToFirstChunk": 1.13835732149999}, "outputSpeedVariance": {"p05": 179.913958165032, "q25": 207.360711459819, "median": 226.362008933674, "q75": 248.438289815485, "p95": 252.400315100144}, "timeToFirstChunkVariance": {"p05": 0.83304028164999, "q25": 0.893146228000006, "median": 1.13835732149999, "q75": 1.32786090475002, "p95": 1.89067351234999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 223.993728533581, "medianTimeToFirstChunk": 0.972460543000011, "medianTimeToFirstAnswerToken": 9.90128195730207, "medianEndToEndResponseTime": 12.133487310877584}, "long": {"medianOutputSpeed": 226.362008933674, "medianTimeToFirstChunk": 1.13835732149999, "medianTimeToFirstAnswerToken": 9.973762208660261, "medianEndToEndResponseTime": 12.182613430450328}, "hundredK": {"medianOutputSpeed": 202.240902026058, "medianTimeToFirstChunk": 3.68453244749997, "medianTimeToFirstAnswerToken": 13.57372884626953, "medianEndToEndResponseTime": 16.046027945961917}, "mediumParallel": {"medianOutputSpeed": 218.272528772393, "medianTimeToFirstChunk": 0.897178829499907, "medianTimeToFirstAnswerToken": 10.060035975327592, "medianEndToEndResponseTime": 12.350750261784512}}, "endToEndResponseTime": {"input": 1.13835732149999, "reasoning": 8.835404887160271, "answer": 2.2088512217900678, "total": 12.182613430450328}, "timeToFirstAnswerToken": {"input": 1.13835732149999, "reasoning": 8.835404887160271, "total": 9.973762208660261}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 2, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7764d514-694f-444c-8d60-bdc6e24e223f", "slug": "deepseek-llm-67b-chat", "name": "DeepSeek LLM 67B Chat (V1)", "shortName": "DeepSeek LLM 67B (V1)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-11-29", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-llm-67b-chat", "name": "DeepSeek LLM 67B Chat (V1)"}, "deprecated": true, "deprecatedTo": "deepseek-v3-0324", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 4096, "licenseName": "DEEPSEEK LICENSE AGREEMENT", "licenseUrl": "https://github.com/deepseek-ai/deepseek-LLM/blob/main/LICENSE-MODEL", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/deepseek-llm-67b-chat", "microevalsEnabled": false, "intelligenceIndex": 5.3045047203477, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "77f5ff8b-1536-474a-a337-e1bfd138d343", "slug": "minicpm5-1b", "name": "MiniCPM5-1B (Reasoning)", "shortName": "MiniCPM5-1B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-25", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "minicpm5-1b", "name": "MiniCPM5-1B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md", "modelWeightsSourceUrl": "https://huggingface.co/openbmb/MiniCPM5-1B", "microevalsEnabled": false, "intelligenceIndex": 8.79664321370212, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -14.6166666666667, "omniscienceBreakdown": {"accuracy": 0.02033333333333333, "hallucinationRate": 0.16995576726777817}, "gdpval": null, "itBenchSre": null, "tau2": 0.809941520467836, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.06, "ifbench": 0.493197278911565, "hle": 0.0648748841519926, "gpqa": 0.277777777777778, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 83.33333333333333, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 3, "transparencyPreTrainingData": 3}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "7399e4ac-f64d-4be6-b649-2fc20756839f", "slug": "openbmb", "name": "OpenBMB", "logo": "/img/logos/openbmb_small.svg", "color": "#3B62EC", "country": "cn", "url": "https://www.openbmb.cn/en/home"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7829427f-f0e3-4f6d-a228-5fbf70dacc02", "slug": "claude-3-opus", "name": "Claude 3 Opus", "shortName": "Claude 3 Opus", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-03-04", "knowledgeCutoffDate": "2023-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-3-opus", "name": "Claude 3 Opus"}, "deprecated": true, "deprecatedTo": "claude-35-sonnet-june-24", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.72397483423503, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0275, "gpqa": 0.488888888888889, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.279365079365079, "aime25": null, "analystAgent": null, "price1mInputTokens": 15, "price1mOutputTokens": 75, "cacheHitPrice": 1.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 18.75, "pricePer1k1mpImages": 20, "price1mBlended0To3To1": 30, "price1mBlended7To2To1": 11.55, "price1mBlended0To1To1": 45, "price1mBlended100To1To1": 2.3529411764705883, "price1mBlended0To100To1": 15.594059405940595, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "78332c88-fe60-42c8-af9d-3617e44cf1f5", "slug": "gemini-3-6-flash", "name": "Gemini 3.6 Flash (high)", "shortName": "Gemini 3.6 Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-21", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gemini-3-6-flash", "name": "Gemini 3.6 Flash"}, "deprecated": true, "deprecatedTo": "gemini-3-7-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 34.3395678920714, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 39.85892187919093, "strategyAndOps": 42.14597933714249, "legal": 46.517478066754336, "healthcareAndMedical": 35.73033715165267, "engineering": 36.13814601823879, "economics": 46.456943234476356}, "omniscience": 22.1333333333333, "omniscienceBreakdown": {"accuracy": 0.49966666666666665, "hallucinationRate": 0.5562958027981346}, "mlcrOverall": 0.144444444444444, "harveyLab": 0.851498046026921, "gdpPdfAllPass": 0.174, "gdpval": 1331.37, "gdpvalNormalized": 0.41568499999999997, "itBenchSre": null, "tau2": null, "tauBanking": 0.298969072164948, "terminalbenchHard": null, "terminalBench21": 0.775280898876405, "terminalBench40": 0.0707070707070707, "scicode": 0.533564814814815, "lcr": 0.8, "ifbench": null, "hle": 0.408248378127896, "gpqa": 0.928282828282828, "critpt": 0.105714285714286, "apexAgents": null, "mmmuPro": 0.832369942196532, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5301669491509355, "price1mInputTokens": 0.75, "price1mOutputTokens": 3.75, "cacheHitPrice": 0.15, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5, "price1mBlended7To2To1": 0.63, "price1mBlended0To1To1": 2.25, "price1mBlended100To1To1": 0.19117647058823528, "price1mBlended0To100To1": 0.7797029702970297, "intelligenceIndexTimePerTask": 218.33807299682545, "intelligenceIndexCost": {"total": 1036.8142167476205, "input": 698.0974467476206, "nonCacheInput": 16.3862265, "cacheRead": 384.6791921880949, "cacheWrite": 297.03202805952566, "output": 338.71677, "reasoning": 242.25994875, "answer": 96.45682125}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.9288448964661649, "input": 0.7728232836957376, "nonCacheInput": 0.011102801381198419, "cacheRead": 0.4473356316985243, "cacheWrite": 0.31438485061601495, "output": 0.15602161277042725, "reasoning": 0.07522880582815455, "answer": 0.08079280694227269}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.1494407444824638}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.06140850673289859}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.01562834775594673}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.6670042766708214}, {"slug": "scicode", "weightedCostPerTask": 0.0030375859375}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00454959077849861}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.009033479249999999}, {"slug": "critpt", "weightedCostPerTask": 0.013472185714285715}, {"slug": "omniscience", "weightedCostPerTask": 0.00077743914375}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00449274}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2982418954, "output": 90324472, "answer": 25721819, "reasoning": 64602653}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 20061.01488750788, "answer": 21544.748517939388, "output": 41605.76340544727}, "briefcaseBreakdown": {"overall": {"elo": 952.75, "lower95ci": 945.7, "upper95ci": 959.99}, "rubricPassRate": 0.2808080808080808, "analyticalQuality": {"elo": 794.28, "lower95ci": 780.74, "upper95ci": 808.85}, "presentation": {"elo": 1032.87, "lower95ci": 1020.58, "upper95ci": 1044.97}}, "briefcaseTotalCost": 90.66071831936138, "timescaleData": {"medianOutputSpeed": 199.475526476905, "medianTimeToFirstChunk": 18.3363438365}, "outputSpeedVariance": {"p05": 139.294481827244, "q25": 160.0423176243, "median": 199.475526476905, "q75": 225.576430535732, "p95": 281.949718556757}, "timeToFirstChunkVariance": {"p05": 10.9902606212, "q25": 14.8140290825, "median": 18.3363438365, "q75": 40.28537199775, "p95": 87.2847902010498}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 185.171948277382, "medianTimeToFirstChunk": 13.492792533, "medianTimeToFirstAnswerToken": 13.492792533, "medianEndToEndResponseTime": 16.19298554091184}, "long": {"medianOutputSpeed": 199.475526476905, "medianTimeToFirstChunk": 18.3363438365, "medianTimeToFirstAnswerToken": 18.3363438365, "medianEndToEndResponseTime": 20.842916992770824}, "hundredK": {"medianOutputSpeed": 268.326964815222, "medianTimeToFirstChunk": 43.282632808, "medianTimeToFirstAnswerToken": 43.282632808, "medianEndToEndResponseTime": 45.146031070430745}, "mediumParallel": {"medianOutputSpeed": 211.01795722856, "medianTimeToFirstChunk": 11.4107461545003, "medianTimeToFirstAnswerToken": 11.4107461545003, "medianEndToEndResponseTime": 13.780212746665415}}, "endToEndResponseTime": {"input": 18.3363438365, "reasoning": 0, "answer": 2.5065731562708233, "total": 20.842916992770824}, "timeToFirstAnswerToken": {"input": 18.3363438365, "reasoning": 0, "total": 18.3363438365}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 4, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "783a0ea2-1eef-422a-8c3d-f6d40d943f54", "slug": "gemini-3-flash", "name": "Gemini 3 Flash Preview (Non-reasoning)", "shortName": "Gemini 3 Flash (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-17", "knowledgeCutoffDate": "2025-01-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-3-flash-preview", "name": "Gemini 3 Flash Preview"}, "deprecated": true, "deprecatedTo": "gemini-3-5-flash-minimal", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 17.9336848163786, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -4.31666666666667, "omniscienceBreakdown": {"accuracy": 0.4578333333333333, "hallucinationRate": 0.9240700891484783}, "mlcrOverall": 0.116666666666667, "gdpval": null, "itBenchSre": null, "tau2": 0.432748538011696, "tauBanking": null, "terminalbenchHard": 0.318181818181818, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.553333333333333, "ifbench": 0.551020408163265, "hle": 0.14967562557924, "gpqa": 0.812121212121212, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": 0.785549132947977, "livecodebench": 0.796825396825397, "aime25": 0.556666666666667, "analystAgent": null, "price1mInputTokens": 0.5, "price1mOutputTokens": 3, "cacheHitPrice": 0.05, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.56, "price1mBlended0To3To1": 1.125, "price1mBlended7To2To1": 0.43499999999999994, "price1mBlended0To1To1": 1.75, "price1mBlended100To1To1": 0.08333333333333333, "price1mBlended0To100To1": 0.5247524752475248, "timescaleData": {"medianOutputSpeed": 211.102901268882, "medianTimeToFirstChunk": 0.874130403500033}, "outputSpeedVariance": {"p05": 143.432454288106, "q25": 178.058968450454, "median": 211.102901268882, "q75": 237.40299572798, "p95": 250.405607802199}, "timeToFirstChunkVariance": {"p05": 0.786052141550067, "q25": 0.829214364000052, "median": 0.874130403500033, "q75": 1.09617370724992, "p95": 3.61028387719999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 211.102901268882, "medianTimeToFirstChunk": 0.874130403500033, "medianTimeToFirstAnswerToken": 0.874130403500033, "medianEndToEndResponseTime": 3.2426435645917864}}, "endToEndResponseTime": {"input": 0.874130403500033, "reasoning": 0, "answer": 2.3685131610917534, "total": 3.2426435645917864}, "timeToFirstAnswerToken": {"input": 0.874130403500033, "reasoning": 0, "total": 0.874130403500033}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 2, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "78452c64-7303-4192-bca5-2d9ec5c623d4", "slug": "jamba-1-7-large", "name": "Jamba 1.7 Large", "shortName": "Jamba 1.7 Large", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-07", "knowledgeCutoffDate": "2024-08-22", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "jamba-1-7-large", "name": "Jamba 1.7 Large"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 398, "inferenceParametersActiveBillions": 94, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Jamba Open Model License Agreement", "licenseUrl": "https://www.ai21.com/licenses/jamba-open-model-license", "modelWeightsSourceUrl": "https://huggingface.co/ai21labs/AI21-Jamba-Large-1.7", "microevalsEnabled": false, "intelligenceIndex": 6.0710365237197, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.9166666666667, "omniscienceBreakdown": {"accuracy": 0.20583333333333334, "hallucinationRate": 0.950682056663169}, "gdpval": null, "itBenchSre": null, "tau2": 0.134502923976608, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.193333333333333, "ifbench": 0.351700680272109, "hle": 0.0366079703429101, "gpqa": 0.38989898989899, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.180952380952381, "aime25": 0.0233333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 22.22222222222222, "modelAvailability": 4, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "6216c686-bc60-4dbb-9f25-83e9dba803d1", "slug": "ai21-labs", "name": "AI21 Labs", "logo": "/img/logos/ai21_small.svg", "color": "#d63864", "country": "il", "url": "https://www.ai21.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "794f69b5-cede-482b-b1cc-d769478497cd", "slug": "grok-4-5", "name": "Grok 4.5 (high)", "shortName": "Grok 4.5 (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-08", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "grok-4-5", "name": "Grok 4.5"}, "deprecated": true, "deprecatedTo": "grok-4-6", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 500000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 39.0842403240657, "intelligenceIndexIsEstimated": false, "capabilities": {"engineering": 39.61782343684299, "economics": 50.36849200092122}, "omniscience": 25.3166666666667, "omniscienceBreakdown": {"accuracy": 0.5155, "hallucinationRate": 0.5414516683866529}, "mlcrOverall": 0.15, "harveyLab": 0.924156896801274, "gdpPdfAllPass": 0.188, "gdpval": 1429.6, "gdpvalNormalized": 0.46479999999999994, "itBenchSre": null, "tau2": null, "tauBanking": 0.420618556701031, "terminalbenchHard": null, "terminalBench21": 0.816479400749064, "terminalBench40": 0.106060606060606, "scicode": 0.549768518518518, "lcr": 0.793333333333333, "ifbench": null, "hle": 0.42678405931418, "gpqa": 0.931313131313131, "critpt": 0.154285714285714, "apexAgents": null, "mmmuPro": 0.804046242774566, "livecodebench": null, "aime25": null, "analystAgent": 0.35, "automationBenchPartialScore": 0.5793486035084273, "enterpriseOpsGym": 0.40823634735899733, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.85, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.21, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 0.37254901960784315, "price1mBlended0To100To1": 2.0396039603960396, "intelligenceIndexTimePerTask": 443.72862408076145, "intelligenceIndexCost": {"total": 1403.7826003445405, "input": 944.1219223445405, "nonCacheInput": 46.003802, "cacheRead": 286.5791007627281, "cacheWrite": 611.5390195818125, "output": 459.66067799999996, "reasoning": 332.905134, "answer": 126.75554400000001}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.0364552526545159, "input": 0.8751614875391653, "nonCacheInput": 0.03272379760591891, "cacheRead": 0.2791646476856184, "cacheWrite": 0.5632730422476282, "output": 0.16129376511535043, "reasoning": 0.05868695288673834, "answer": 0.10260681222861204}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.18491413892655276}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0546028916500245}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.027523025524475997}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.6953063924860052}, {"slug": "scicode", "weightedCostPerTask": 0.002598052777777778}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.011246479425393882}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.024432133999999998}, {"slug": "critpt", "weightedCostPerTask": 0.024728965714285716}, {"slug": "omniscience", "weightedCostPerTask": 0.0009681591500000001}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.010135013}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1284035080, "output": 76610113, "answer": 21125924, "reasoning": 55484189}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 9781.15881445639, "answer": 17101.13537143534, "output": 26882.29418589173}, "briefcaseBreakdown": {"overall": {"elo": 1283.38, "lower95ci": 1277.28, "upper95ci": 1290}, "rubricPassRate": 0.4070707070707071, "analyticalQuality": {"elo": 1325.95, "lower95ci": 1313.95, "upper95ci": 1338.47}, "presentation": {"elo": 1292.55, "lower95ci": 1282.42, "upper95ci": 1303.43}}, "briefcaseTotalCost": 112.18124428210868, "timescaleData": {"medianOutputSpeed": 60.4848094654199, "medianTimeToFirstChunk": 7.4058058315}, "outputSpeedVariance": {"p05": 41.9160763566528, "q25": 49.8085489754305, "median": 60.4848094654199, "q75": 67.5746226800741, "p95": 81.9565973741294}, "timeToFirstChunkVariance": {"p05": 4.46567592145004, "q25": 5.33314880424999, "median": 7.4058058315, "q75": 11.5288849022499, "p95": 25.03459622}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 60.6337210561292, "medianTimeToFirstChunk": 12.318333562, "medianTimeToFirstAnswerToken": 12.318333562, "medianEndToEndResponseTime": 20.564570000914003}, "long": {"medianOutputSpeed": 60.4848094654199, "medianTimeToFirstChunk": 7.4058058315, "medianTimeToFirstAnswerToken": 7.4058058315, "medianEndToEndResponseTime": 15.67234423046541}, "hundredK": {"medianOutputSpeed": 64.3091083533886, "medianTimeToFirstChunk": 14.1020930950001, "medianTimeToFirstAnswerToken": 14.1020930950001, "medianEndToEndResponseTime": 21.877041509032246}, "mediumParallel": {"medianOutputSpeed": 52.3344005266049, "medianTimeToFirstChunk": 11.0990286745, "medianTimeToFirstAnswerToken": 11.0990286745, "medianEndToEndResponseTime": 20.652973975656515}}, "endToEndResponseTime": {"input": 7.4058058315, "reasoning": 0, "answer": 8.266538398965409, "total": 15.67234423046541}, "timeToFirstAnswerToken": {"input": 7.4058058315, "reasoning": 0, "total": 7.4058058315}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 2, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7a7b52f6-fdef-4dae-9203-58c710ccc81d", "slug": "mistral-saba", "name": "Mistral Saba", "shortName": "Mistral Saba", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-17", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-saba", "name": "Mistral Saba"}, "deprecated": true, "deprecatedTo": "mistral-small-3-2", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 24, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.48598593446849, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.043, "gpqa": 0.424242424242424, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7ae943a9-9310-4472-a834-c61f0ab68485", "slug": "qwen3-max", "name": "Qwen3 Max", "shortName": "Qwen3 Max", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-23", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-max", "name": "Qwen3 Max"}, "deprecated": true, "deprecatedTo": "qwen3-max-thinking", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 15.6098449457502, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -43.55, "omniscienceBreakdown": {"accuracy": 0.24416666666666667, "hallucinationRate": 0.8992282249173098}, "gdpval": null, "itBenchSre": null, "tau2": 0.742690058479532, "tauBanking": null, "terminalbenchHard": 0.204545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.5, "ifbench": 0.441496598639456, "hle": 0.119091751621872, "gpqa": 0.763636363636364, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.767195767195767, "aime25": 0.806666666666667, "analystAgent": null, "price1mInputTokens": 1.2, "price1mOutputTokens": 6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2.4, "price1mBlended7To2To1": 1.6800000000000002, "price1mBlended0To1To1": 3.6, "price1mBlended100To1To1": 1.2470588235294118, "price1mBlended0To100To1": 1.2475247524752475, "openness": {"opennessIndex": 16.666666666666668, "modelAvailability": 2, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 49.0834410935312, "medianTimeToFirstChunk": 2.28650414850001}, "outputSpeedVariance": {"p05": 42.4538247559303, "q25": 45.0849840744277, "median": 49.0834410935312, "q75": 58.2742749477845, "p95": 66.6094792960607}, "timeToFirstChunkVariance": {"p05": 2.13151626800004, "q25": 2.17260748274999, "median": 2.28650414850001, "q75": 2.47719091975002, "p95": 3.23861319709998}, "performanceByPromptType": {"long": {"medianOutputSpeed": 49.0834410935312, "medianTimeToFirstChunk": 2.28650414850001, "medianTimeToFirstAnswerToken": 2.28650414850001, "medianEndToEndResponseTime": 12.473238999612475}}, "endToEndResponseTime": {"input": 2.28650414850001, "reasoning": 0, "answer": 10.186734851112465, "total": 12.473238999612475}, "timeToFirstAnswerToken": {"input": 2.28650414850001, "reasoning": 0, "total": 2.28650414850001}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7b269763-ecc0-41ef-aa29-47ef632ac065", "slug": "gemini-2-0-flash-lite-001", "name": "Gemini 2.0 Flash-Lite (Feb '25)", "shortName": "Gemini 2.0 Flash-Lite (Feb)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-25", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-2-0-flash-lite-001", "name": "Gemini 2.0 Flash-Lite (Feb '25)"}, "deprecated": true, "deprecatedTo": "gemini-2-5-flash-lite-preview-09-2025", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.40799139518293, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0335, "gpqa": 0.535353535353535, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.185185185185185, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7c045ca0-b331-488d-af31-df0fd331dfd1", "slug": "mistral-small", "name": "Mistral Small (Sep '24)", "shortName": "Mistral Small (Sep)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-17", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-small", "name": "Mistral Small (Sep '24)"}, "deprecated": true, "deprecatedTo": "mistral-small-3", "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 22, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "Mistral Research License", "licenseUrl": "https://mistral.ai/licenses/MRL-0.1.md", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-Small-Instruct-2409", "microevalsEnabled": false, "intelligenceIndex": 5.84842869297048, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0425, "gpqa": 0.380808080808081, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.140740740740741, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.30000000000000004, "price1mBlended7To2To1": 0.24000000000000005, "price1mBlended0To1To1": 0.4, "price1mBlended100To1To1": 0.20392156862745098, "price1mBlended0To100To1": 0.20396039603960398, "timescaleData": {"medianOutputSpeed": 155.746830524534, "medianTimeToFirstChunk": 0.747463471999936}, "outputSpeedVariance": {"p05": 105.963827506801, "q25": 125.435954725631, "median": 155.746830524534, "q75": 179.111173407732, "p95": 193.367541672829}, "timeToFirstChunkVariance": {"p05": 0.701968345299974, "q25": 0.724869192499966, "median": 0.747463471999936, "q75": 1.07130723799992, "p95": 1.40315393380007}, "performanceByPromptType": {"long": {"medianOutputSpeed": 155.746830524534, "medianTimeToFirstChunk": 0.747463471999936, "medianTimeToFirstAnswerToken": 0.747463471999936, "medianEndToEndResponseTime": 3.9578016748132354}}, "endToEndResponseTime": {"input": 0.747463471999936, "reasoning": 0, "answer": 3.210338202813299, "total": 3.9578016748132354}, "timeToFirstAnswerToken": {"input": 0.747463471999936, "reasoning": 0, "total": 0.747463471999936}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7c4d1e30-6ecb-46cf-880c-41446d7b51f1", "slug": "gpt-5-6-sol-non-reasoning", "name": "GPT-5.6 Sol (Non-reasoning)", "shortName": "GPT-5.6 Sol (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-5-6-sol", "name": "GPT-5.6 Sol"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 28.3280042499237, "intelligenceIndexIsEstimated": true, "capabilities": {"financeAndAccounting": 29.62625227786326, "strategyAndOps": 32.54741184536981, "legal": 31.3226306166476, "economics": 32.461468740345985}, "omniscience": 1.1, "omniscienceBreakdown": {"accuracy": 0.487, "hallucinationRate": 0.9278752436647173}, "gdpPdfAllPass": 0.152, "gdpval": 1273.32, "gdpvalNormalized": 0.38665999999999995, "itBenchSre": null, "tau2": null, "tauBanking": 0.195876288659794, "terminalbenchHard": null, "terminalBench21": 0.741573033707865, "terminalBench40": null, "scicode": 0.476851851851852, "lcr": 0.623333333333333, "ifbench": null, "hle": 0.166821130676552, "gpqa": 0.78989898989899, "critpt": 0.0514285714285714, "apexAgents": null, "mmmuPro": 0.71907514450867, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.22656758038944594, "price1mInputTokens": 4, "price1mOutputTokens": 20, "cacheHitPrice": 0.4, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 8, "price1mBlended7To2To1": 3.08, "price1mBlended0To1To1": 12, "price1mBlended100To1To1": 0.6274509803921569, "price1mBlended0To100To1": 4.158415841584159, "briefcaseBreakdown": {"overall": {"elo": 1015.25, "lower95ci": 1008.02, "upper95ci": 1023.39}, "rubricPassRate": 0.2383838383838384, "analyticalQuality": {"elo": 967.47, "lower95ci": 953.43, "upper95ci": 982.18}, "presentation": {"elo": 1145.27, "lower95ci": 1131.13, "upper95ci": 1159.66}}, "briefcaseTotalCost": 41.87659401693851, "timescaleData": {"medianOutputSpeed": 67.8325293016515, "medianTimeToFirstChunk": 1.22859604799996}, "outputSpeedVariance": {"p05": 45.9366980404277, "q25": 53.9727839750641, "median": 67.8325293016515, "q75": 77.1803153820522, "p95": 91.5987625339792}, "timeToFirstChunkVariance": {"p05": 0.938406477049912, "q25": 1.04280063324997, "median": 1.22859604799996, "q75": 1.44084422050002, "p95": 1.68597016220004}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 63.4501400577033, "medianTimeToFirstChunk": 1.15821025400002, "medianTimeToFirstAnswerToken": 1.15821025400002, "medianEndToEndResponseTime": 9.038413505644323}, "long": {"medianOutputSpeed": 67.8325293016515, "medianTimeToFirstChunk": 1.22859604799996, "medianTimeToFirstAnswerToken": 1.22859604799996, "medianEndToEndResponseTime": 8.599690788939048}, "hundredK": {"medianOutputSpeed": 72.6350195820612, "medianTimeToFirstChunk": 2.20120314700003, "medianTimeToFirstAnswerToken": 2.20120314700003, "medianEndToEndResponseTime": 9.08493502835669}, "mediumParallel": {"medianOutputSpeed": 56.100472954781, "medianTimeToFirstChunk": 1.09970679550008, "medianTimeToFirstAnswerToken": 1.09970679550008, "medianEndToEndResponseTime": 10.012287628874123}}, "endToEndResponseTime": {"input": 1.22859604799996, "reasoning": 0, "answer": 7.371094740939088, "total": 8.599690788939048}, "timeToFirstAnswerToken": {"input": 1.22859604799996, "reasoning": 0, "total": 1.22859604799996}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7c73c3be-7f51-4d14-bec8-d5789488df25", "slug": "gemini-3-flash-reasoning", "name": "Gemini 3 Flash Preview (Reasoning)", "shortName": "Gemini 3 Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-17", "knowledgeCutoffDate": "2025-01-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-3-flash-preview", "name": "Gemini 3 Flash Preview"}, "deprecated": true, "deprecatedTo": "gemini-3-5-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 26.3272067856089, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 10.1333333333333, "omniscienceBreakdown": {"accuracy": 0.5343333333333333, "hallucinationRate": 0.9298496778811739}, "mlcrOverall": 0.111111111111111, "gdpval": null, "itBenchSre": null, "tau2": 0.804093567251462, "tauBanking": 0.208247422680412, "terminalbenchHard": 0.386363636363636, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.78, "ifbench": 0.779591836734694, "hle": 0.365616311399444, "gpqa": 0.897979797979798, "critpt": 0.0857142857142857, "apexAgents": 0.277286135693215, "mmmuPro": 0.799421965317919, "livecodebench": 0.907936507936508, "aime25": 0.97, "analystAgent": null, "price1mInputTokens": 0.5, "price1mOutputTokens": 3, "cacheHitPrice": 0.05, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.56, "price1mBlended0To3To1": 1.125, "price1mBlended7To2To1": 0.43499999999999994, "price1mBlended0To1To1": 1.75, "price1mBlended100To1To1": 0.08333333333333333, "price1mBlended0To100To1": 0.5247524752475248, "timescaleData": {"medianOutputSpeed": 228.903164665126, "medianTimeToFirstChunk": 6.35043438050002}, "outputSpeedVariance": {"p05": 154.636304236545, "q25": 189.954252081036, "median": 228.903164665126, "q75": 248.240580537451, "p95": 272.594765094328}, "timeToFirstChunkVariance": {"p05": 4.81593768419992, "q25": 5.29634139775001, "median": 6.35043438050002, "q75": 7.17017406325003, "p95": 9.68059864700002}, "performanceByPromptType": {"long": {"medianOutputSpeed": 228.903164665126, "medianTimeToFirstChunk": 6.35043438050002, "medianTimeToFirstAnswerToken": 6.35043438050002, "medianEndToEndResponseTime": 8.534764163495703}}, "endToEndResponseTime": {"input": 6.35043438050002, "reasoning": 0, "answer": 2.184329782995684, "total": 8.534764163495703}, "timeToFirstAnswerToken": {"input": 6.35043438050002, "reasoning": 0, "total": 6.35043438050002}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7d73161f-002f-4c9c-b4f8-6c4d91f2ba8e", "slug": "nanbeige4-1-3b", "name": "Nanbeige4.1-3B", "shortName": "Nanbeige4.1-3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "nanbeige4-1-3b", "name": "Nanbeige4.1-3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3.93, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Nanbeige/Nanbeige4.1-3B", "microevalsEnabled": false, "intelligenceIndex": 8.4012282586083, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -42.5, "omniscienceBreakdown": {"accuracy": 0.09866666666666667, "hallucinationRate": 0.580991124260355}, "gdpval": -166.42, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.216374269005848, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": 0.0112359550561798, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.354421768707483, "hle": 0.108897126969416, "gpqa": 0.84949494949495, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 41.666666666666664, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "c1c9377c-4745-4762-94b7-88c045ccda28", "slug": "nanbeige", "name": "Nanbeige", "logo": "/img/logos/nanbeige_small.png", "color": "#023c3e", "country": "cn", "url": "https://huggingface.co/Nanbeige"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7e30585f-fad7-40df-a8cb-03c1d96df38a", "slug": "qwen3-8-27b-low", "name": "Qwen3.8 27B (low)", "shortName": "Qwen3.8 27B (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-14", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "qwen3-8-27b", "name": "Qwen3.8 27B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 27, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.8-27B", "microevalsEnabled": false, "intelligenceIndex": 26.4944478189896, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 27.159413159165624, "strategyAndOps": 29.78851629912975, "legal": 27.97975798699848, "engineering": 24.184804653579352, "economics": 31.93331414118009}, "omniscience": -26.6666666666667, "omniscienceBreakdown": {"accuracy": 0.17133333333333334, "hallucinationRate": 0.5285599356395817}, "gdpPdfAllPass": 0.104, "gdpval": 1402.54, "gdpvalNormalized": 0.45127, "itBenchSre": null, "tau2": null, "tauBanking": 0.321649484536082, "terminalbenchHard": null, "terminalBench21": 0.674157303370786, "terminalBench40": 0.0252525252525253, "scicode": 0.400462962962963, "lcr": 0.773333333333333, "ifbench": null, "hle": 0.140407784986098, "gpqa": 0.845454545454545, "critpt": 0, "apexAgents": null, "mmmuPro": 0.73757225433526, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.3010329530343377, "price1mInputTokens": 0.5, "price1mOutputTokens": 3, "cacheHitPrice": 0.05, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.125, "price1mBlended7To2To1": 0.43499999999999994, "price1mBlended0To1To1": 1.75, "price1mBlended100To1To1": 0.08333333333333333, "price1mBlended0To100To1": 0.5247524752475248, "intelligenceIndexTimePerTask": 870.9490724997569, "intelligenceIndexCost": {"total": 875.9164648110001, "input": 628.5976558110001, "nonCacheInput": 13.040737, "cacheRead": 184.164648521, "cacheWrite": 431.39227029000006, "output": 247.318809, "reasoning": 140.377902, "answer": 106.940907}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.8340096586526328, "input": 0.6977302581520196, "nonCacheInput": 0.00942129186169311, "cacheRead": 0.21421287786340634, "cacheWrite": 0.4740960884269201, "output": 0.13627940050061324, "reasoning": 0.07757737806933192, "answer": 0.05870202243128136}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.2451047143285715}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.08010849427477273}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.012195753507914764}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.4783903186159091}, {"slug": "scicode", "weightedCostPerTask": 0.0008242126736111112}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002169087001853568}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00703096}, {"slug": "critpt", "weightedCostPerTask": 0.005091340000000001}, {"slug": "omniscience", "weightedCostPerTask": 0.00023747424999999997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.002857304}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4572158985, "output": 82439603, "answer": 35646969, "reasoning": 46792634}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 25859.126023110635, "answer": 19567.340810427126, "output": 45426.466833537765}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1277.44, "lower95ci": 1267.33, "upper95ci": 1287.6}, "rubricPassRate": 0.4207818930041152, "analyticalQuality": {"elo": 1382.11, "lower95ci": 1362.56, "upper95ci": 1403.16}, "presentation": {"elo": 1203.3, "lower95ci": 1184.4, "upper95ci": 1222.72}}, "briefcaseTotalCost": 148.69686002600005, "timescaleData": {"medianOutputSpeed": 50.8653188477534, "medianTimeToFirstChunk": 3.92851506099999}, "outputSpeedVariance": {"p05": 40.1269051567409, "q25": 45.7467415137681, "median": 50.8653188477534, "q75": 57.3425744757776, "p95": 60.9823498957247}, "timeToFirstChunkVariance": {"p05": 3.7238613955, "q25": 3.83840204149996, "median": 3.92851506099999, "q75": 4.23737070624995, "p95": 4.46481620554995}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 45.5758348503484, "medianTimeToFirstChunk": 1.243309291, "medianTimeToFirstAnswerToken": 45.12621361007933, "medianEndToEndResponseTime": 56.096939689849165}, "long": {"medianOutputSpeed": 50.8653188477534, "medianTimeToFirstChunk": 3.92851506099999, "medianTimeToFirstAnswerToken": 43.24803659956074, "medianEndToEndResponseTime": 53.07791698420093}, "hundredK": {"medianOutputSpeed": 77.4930420753502, "medianTimeToFirstChunk": 18.4857020235, "medianTimeToFirstAnswerToken": 44.29447073921649, "medianEndToEndResponseTime": 50.74666291814562}, "mediumParallel": {"medianOutputSpeed": 46.7884832218773, "medianTimeToFirstChunk": 1.22318606700002, "medianTimeToFirstAnswerToken": 43.96874784372465, "medianEndToEndResponseTime": 54.65513828790581}}, "endToEndResponseTime": {"input": 3.92851506099999, "reasoning": 39.31952153856075, "answer": 9.829880384640187, "total": 53.07791698420093}, "timeToFirstAnswerToken": {"input": 3.92851506099999, "reasoning": 39.31952153856075, "total": 43.24803659956074}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7eabd8ca-bf43-4d56-b3df-efd1c4eebfb0", "slug": "solar-open2-250b", "name": "Solar Open2 250B", "shortName": "Solar Open2 250B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-12", "knowledgeCutoffDate": "2026-02-01", "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "solar-open2-250b", "name": "Solar Open2 250B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 250, "inferenceParametersActiveBillions": 15, "sizeClass": "large", "contextWindowTokens": 1048576, "licenseName": "Upstage Solar License", "licenseUrl": "https://huggingface.co/upstage/Solar-Open2-250B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/upstage/Solar-Open2-250B", "microevalsEnabled": false, "intelligenceIndex": 24.7365297627523, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -1.76666666666667, "omniscienceBreakdown": {"accuracy": 0.18833333333333332, "hallucinationRate": 0.2537987679671458}, "gdpval": 1052.82, "gdpvalNormalized": 0.27641, "itBenchSre": null, "tau2": null, "tauBanking": 0.216494845360825, "terminalbenchHard": null, "terminalBench21": 0.441947565543071, "terminalBench40": null, "scicode": 0.480324074074074, "lcr": 0.716666666666667, "ifbench": null, "hle": 0.285449490268767, "gpqa": 0.856565656565657, "critpt": 0.0571428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "64ff7f06-c6fb-42ea-ba24-9cd103ab2d61", "slug": "upstage", "name": "Upstage", "logo": "/img/logos/upstage_small.svg", "color": "#7c59f5", "country": "kr", "url": "https://www.upstage.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7eaf926c-5f39-4e58-ae50-c38b5fc630fc", "slug": "ling-3-0-tiny", "name": "Ling 3.0 Tiny", "shortName": "Ling 3.0 Tiny", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-06", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "ling-3-0-tiny", "name": "Ling 3.0 Tiny"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 7.9, "inferenceParametersActiveBillions": 1.3, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ling-3.0-tiny-int4", "microevalsEnabled": false, "intelligenceIndex": 11.8679233769305, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 10.796641335565585, "strategyAndOps": 5.618223503957432, "legal": 15.242435142062776, "engineering": 16.650326969416128, "economics": 22.079379595304292}, "omniscience": -19.35, "omniscienceBreakdown": {"accuracy": 0.08516666666666667, "hallucinationRate": 0.3046092184368738}, "gdpPdfAllPass": 0.008, "gdpval": 715.64, "gdpvalNormalized": 0.10782, "itBenchSre": null, "tau2": null, "tauBanking": 0.208247422680412, "terminalbenchHard": null, "terminalBench21": 0.277153558052434, "terminalBench40": 0, "scicode": 0.241898148148148, "lcr": 0.603333333333333, "ifbench": null, "hle": 0.0931417979610751, "gpqa": 0.734343434343434, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.002807334937855976, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "intelligenceIndexTimePerTask": 356.05449574942605, "intelligenceIndexCost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "intelligenceIndexCostPerTask": {"cost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0}, {"slug": "gdpval-aa", "weightedCostPerTask": 0}, {"slug": "automationbench-aa", "weightedCostPerTask": 0}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0}, {"slug": "scicode", "weightedCostPerTask": 0}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0}, {"slug": "gdp-pdf", "weightedCostPerTask": 0}, {"slug": "critpt", "weightedCostPerTask": 0}, {"slug": "omniscience", "weightedCostPerTask": 0}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2607178931, "output": 231700870, "answer": 41770799, "reasoning": 189930071}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 39935.0719889828, "answer": 30352.390728791637, "output": 70287.46271777444}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 481.43, "lower95ci": 471.86, "upper95ci": 490.76}, "rubricPassRate": 0.08383838383838384, "analyticalQuality": {"elo": 156.24, "lower95ci": 136.99, "upper95ci": 174.85}, "presentation": {"elo": 624.82, "lower95ci": 607.31, "upper95ci": 640.74}}, "briefcaseTotalCost": 0, "timescaleData": {"medianOutputSpeed": 161.694651581487, "medianTimeToFirstChunk": 2.57862624900002}, "outputSpeedVariance": {"p05": 132.427975304277, "q25": 146.222912989616, "median": 161.694651581487, "q75": 185.772997560378, "p95": 210.15894887784}, "timeToFirstChunkVariance": {"p05": 2.06554715255, "q25": 2.40187744025002, "median": 2.57862624900002, "q75": 2.90293836274996, "p95": 4.85531268059998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 195.090968845847, "medianTimeToFirstChunk": 1.96479898500001, "medianTimeToFirstAnswerToken": 12.216426786286492, "medianEndToEndResponseTime": 14.779333736608114}, "long": {"medianOutputSpeed": 161.694651581487, "medianTimeToFirstChunk": 2.57862624900002, "medianTimeToFirstAnswerToken": 14.947619165207197, "medianEndToEndResponseTime": 18.039867394258987}, "hundredK": {"medianOutputSpeed": 135.601381043974, "medianTimeToFirstChunk": 7.81198108950005, "medianTimeToFirstAnswerToken": 22.561093411235348, "medianEndToEndResponseTime": 26.248371491669175}, "mediumParallel": {"medianOutputSpeed": 202.188559372454, "medianTimeToFirstChunk": 1.87618081750014, "medianTimeToFirstAnswerToken": 11.767937335314661, "medianEndToEndResponseTime": 14.240876464768291}}, "endToEndResponseTime": {"input": 2.57862624900002, "reasoning": 12.368992916207176, "answer": 3.092248229051794, "total": 18.039867394258987}, "timeToFirstAnswerToken": {"input": 2.57862624900002, "reasoning": 12.368992916207176, "total": 14.947619165207197}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7ec1065a-c90e-41e4-bd17-abb7042eed76", "slug": "qwen3-30b-a3b-2507", "name": "Qwen3 30B A3B 2507 Instruct", "shortName": "Qwen3 30B A3B 2507 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-29", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-30b-a3b-2507", "name": "Qwen3 30B A3B 2507"}, "deprecated": true, "deprecatedTo": "qwen3-5-35b-a3b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30.5, "inferenceParametersActiveBillions": 3.3, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507", "microevalsEnabled": false, "intelligenceIndex": 7.52105693426478, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -66.15, "omniscienceBreakdown": {"accuracy": 0.14966666666666667, "hallucinationRate": 0.9539396315170522}, "gdpval": null, "itBenchSre": null, "tau2": 0.10233918128655, "tauBanking": null, "terminalbenchHard": 0.0606060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.263333333333333, "ifbench": 0.330612244897959, "hle": 0.0690454124189064, "gpqa": 0.658585858585859, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.515343915343915, "aime25": 0.663333333333333, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.35000000000000003, "price1mBlended7To2To1": 0.26000000000000006, "price1mBlended0To1To1": 0.5, "price1mBlended100To1To1": 0.20588235294117646, "price1mBlended0To100To1": 0.20594059405940596, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 142.408725287021, "medianTimeToFirstChunk": 1.80675426749997}, "outputSpeedVariance": {"p05": 119.276146720667, "q25": 134.242693418836, "median": 142.408725287021, "q75": 155.558144420899, "p95": 168.707777508492}, "timeToFirstChunkVariance": {"p05": 1.76849394404994, "q25": 1.78398880874999, "median": 1.80675426749997, "q75": 1.85927827649999, "p95": 2.52221435029999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 142.408725287021, "medianTimeToFirstChunk": 1.80675426749997, "medianTimeToFirstAnswerToken": 1.80675426749997, "medianEndToEndResponseTime": 5.317775091485743}}, "endToEndResponseTime": {"input": 1.80675426749997, "reasoning": 0, "answer": 3.5110208239857723, "total": 5.317775091485743}, "timeToFirstAnswerToken": {"input": 1.80675426749997, "reasoning": 0, "total": 1.80675426749997}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 4, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "7f3c9423-3ee3-4369-a6d9-3f2a40aff00e", "slug": "gpt-5-low", "name": "GPT-5 (low)", "shortName": "GPT-5 (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-09-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gpt-5", "name": "GPT-5"}, "deprecated": true, "deprecatedTo": "gpt-5-1", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 20.7855980255103, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -10.7833333333333, "omniscienceBreakdown": {"accuracy": 0.38116666666666665, "hallucinationRate": 0.7901966065176407}, "gdpval": null, "itBenchSre": null, "tau2": 0.842105263157895, "tauBanking": null, "terminalbenchHard": 0.265151515151515, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.665986394557823, "hle": 0.195551436515292, "gpqa": 0.808080808080808, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": 0.73757225433526, "livecodebench": 0.762962962962963, "aime25": 0.83, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.788, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 1.3375, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.3366336633663367, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 88.1748207750098, "medianTimeToFirstChunk": 5.9901376295}, "outputSpeedVariance": {"p05": 44.5400730226185, "q25": 66.7502758558608, "median": 88.1748207750098, "q75": 122.490239119462, "p95": 159.881492800214}, "timeToFirstChunkVariance": {"p05": 2.51158747029999, "q25": 4.28963148000014, "median": 5.9901376295, "q75": 11.31037867475, "p95": 21.35316331545}, "performanceByPromptType": {"long": {"medianOutputSpeed": 88.1748207750098, "medianTimeToFirstChunk": 5.9901376295, "medianTimeToFirstAnswerToken": 5.9901376295, "medianEndToEndResponseTime": 11.660690692214114}}, "endToEndResponseTime": {"input": 5.9901376295, "reasoning": 0, "answer": 5.670553062714115, "total": 11.660690692214114}, "timeToFirstAnswerToken": {"input": 5.9901376295, "reasoning": 0, "total": 5.9901376295}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8014c311-fa23-4a4b-8485-8a864db8a113", "slug": "celeris-1", "name": "Celeris-1", "shortName": "Celeris-1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-24", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "celeris-1", "name": "Celeris-1"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 131072, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.3469533538601, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 5.970917219226429, "strategyAndOps": 4.285769330467948, "legal": 6.100851535680204, "engineering": 7.776779425393884, "economics": 9.451819660253394}, "omniscience": -71.5833333333333, "omniscienceBreakdown": {"accuracy": 0.10983333333333334, "hallucinationRate": 0.927541658865381}, "gdpPdfAllPass": 0.012, "gdpval": 482.83, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": null, "tauBanking": 0.0391752577319588, "terminalbenchHard": null, "terminalBench21": 0.112359550561798, "terminalBench40": 0, "scicode": 0.216435185185185, "lcr": 0.38, "ifbench": null, "hle": 0.0681186283595922, "gpqa": 0.631313131313131, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.004158035881179356, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.7, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.325, "price1mBlended7To2To1": 0.25, "price1mBlended0To1To1": 0.44999999999999996, "price1mBlended100To1To1": 0.20490196078431372, "price1mBlended0To100To1": 0.20495049504950494, "intelligenceIndexTimePerTask": 3.2569119366509685, "intelligenceIndexCost": {"total": 59.99287, "input": 54.280090200000004, "nonCacheInput": 3.3799554, "cacheRead": 0, "cacheWrite": 50.900134800000004, "output": 5.712779799999999, "reasoning": 0.028997499999999996, "answer": 5.683782299999999}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.05015755586591194, "input": 0.04595023316036006, "nonCacheInput": 0.00193353113288068, "cacheRead": 0, "cacheWrite": 0.04401670202747938, "output": 0.004207322705551879, "reasoning": 4.4379883624442526e-05, "answer": 0.004162942821927437}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.02183543142857143}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.00850900918181818}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.000914000281582953}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.01658375878787879}, {"slug": "scicode", "weightedCostPerTask": 0.00017395527777777777}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 6.158163113994439e-05}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0007522523}, {"slug": "critpt", "weightedCostPerTask": 0.00025084185714285715}, {"slug": "omniscience", "weightedCostPerTask": 4.20427e-06}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0010725208499999998}]}, "canonicalIntelligenceIndexTokenCount": {"input": 271400451, "output": 8161114, "answer": 8119689, "reasoning": 41425}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 63.39983374920362, "answer": 5947.061174182054, "output": 6010.461007931258}, "briefcaseBreakdown": {"overall": {"elo": 171.51, "lower95ci": 161.43, "upper95ci": 180.8}, "rubricPassRate": 0.05454545454545454, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 89.38, "lower95ci": 69.97, "upper95ci": 107.95}}, "briefcaseTotalCost": 13.246828400000002, "timescaleData": {"medianOutputSpeed": 1463.09568634564, "medianTimeToFirstChunk": 0.583745993999912}, "outputSpeedVariance": {"p05": 465.906302252776, "q25": 1179.99204843433, "median": 1463.09568634564, "q75": 1702.26208464132, "p95": 2784.29785679231}, "timeToFirstChunkVariance": {"p05": 0.52165776134988, "q25": 0.546705895750051, "median": 0.583745993999912, "q75": 0.622258765249857, "p95": 0.820493753049985}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 2016.80773017514, "medianTimeToFirstChunk": 0.496717466000007, "medianTimeToFirstAnswerToken": 0.496717466000007, "medianEndToEndResponseTime": 0.7446340088211613}, "long": {"medianOutputSpeed": 1463.09568634564, "medianTimeToFirstChunk": 0.583745993999912, "medianTimeToFirstAnswerToken": 0.583745993999912, "medianEndToEndResponseTime": 0.9254871423514905}, "hundredK": {"medianOutputSpeed": 632.979270202293, "medianTimeToFirstChunk": 2.10921821200009, "medianTimeToFirstAnswerToken": 2.10921821200009, "medianEndToEndResponseTime": 2.899133496019116}, "mediumParallel": {"medianOutputSpeed": 912.116653337697, "medianTimeToFirstChunk": 0.575864787999904, "medianTimeToFirstAnswerToken": 0.575864787999904, "medianEndToEndResponseTime": 1.1240402852571423}}, "endToEndResponseTime": {"input": 0.583745993999912, "reasoning": 0, "answer": 0.3417411483515786, "total": 0.9254871423514905}, "timeToFirstAnswerToken": {"input": 0.583745993999912, "reasoning": 0, "total": 0.583745993999912}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "13f5bdc0-3810-40bf-a333-a50d88ad9144", "slug": "celeris", "name": "Celeris", "logo": "/img/logos/celeris.svg", "color": "#ff8a75", "country": null, "url": "https://celeris.ai"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "806032ff-6252-4c22-ba99-a126e411b7a4", "slug": "qwen3-max-thinking", "name": "Qwen3 Max Thinking", "shortName": "Qwen3 Max Thinking", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-26", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-max-thinking", "name": "Qwen3 Max Thinking"}, "deprecated": true, "deprecatedTo": "qwen3-6-max", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 21.2551111296741, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -36.6166666666667, "omniscienceBreakdown": {"accuracy": 0.2981666666666667, "hallucinationRate": 0.9465685110425077}, "gdpval": null, "itBenchSre": null, "tau2": 0.836257309941521, "tauBanking": null, "terminalbenchHard": 0.242424242424242, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.743333333333333, "ifbench": 0.707482993197279, "hle": 0.279888785912882, "gpqa": 0.860606060606061, "critpt": 0.0171428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "80f7860a-7665-4658-9f05-15bccf5f832f", "slug": "llama-3-2-instruct-1b", "name": "Llama 3.2 Instruct 1B", "shortName": "Llama 3.2 1B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-25", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-2-instruct-1b", "name": "Llama 3.2 Instruct 1B"}, "deprecated": true, "deprecatedTo": "llama-3-3-instruct-70b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.2 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Llama-3.2-1B", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.7, "omniscienceBreakdown": {"accuracy": 0.07, "hallucinationRate": 0.6634408602150538}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.0666666666666667, "ifbench": 0.227891156462585, "hle": 0.0546, "gpqa": 0.195959595959596, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.019047619047619, "aime25": 0, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "81444bc8-72f9-4a2d-ad43-27e3f0d2f461", "slug": "tiny-aya-global", "name": "Tiny Aya Global", "shortName": "Tiny Aya Global", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-17", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "tiny-aya-global", "name": "Tiny Aya Global"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 3.35, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 8192, "licenseName": "Cc By Nc 4.0", "licenseUrl": "https://spdx.org/licenses/CC-BY-NC-4.0", "modelWeightsSourceUrl": "https://huggingface.co/CohereLabs/tiny-aya-global", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -84.3, "omniscienceBreakdown": {"accuracy": 0.06066666666666667, "hallucinationRate": 0.9620298083747338}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.201360544217687, "hle": 0.0523632993512512, "gpqa": 0.305050505050505, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 36.111111111111114, "modelAvailability": 3, "transparencyMethodology": 3, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 130.594977180477, "medianTimeToFirstChunk": 0.311120136500001, "medianTimeToFirstAnswerToken": 0.311120136500001, "medianEndToEndResponseTime": 4.139751304366588}, "mediumParallel": {"medianOutputSpeed": 126.488202859376, "medianTimeToFirstChunk": 0.302164572499919, "medianTimeToFirstAnswerToken": 0.302164572499919, "medianEndToEndResponseTime": 4.255102385648216}}, "performanceDataSource": {"type": "firstParty", "providerName": "Cohere"}, "hostModelCount": 1, "creator": {"id": "671d3708-c407-4b8f-b350-f728e4689d26", "slug": "cohere", "name": "Cohere", "logo": "/img/logos/cohere_small.svg", "color": "#D18EE2", "country": "ca", "url": "https://cohere.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "81972fba-1219-477e-bbfb-18c656a63ff7", "slug": "gpt-5-6-terra-high", "name": "GPT-5.6 Terra (high)", "shortName": "GPT-5.6 Terra (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5-6-terra", "name": "GPT-5.6 Terra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 34.4910058067555, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 37.52109198147655, "strategyAndOps": 40.4147833488231, "legal": 37.28287626379648, "healthcareAndMedical": 34.45132116417093, "engineering": 34.50812580551979, "economics": 41.9205905159098}, "omniscience": -3.46666666666667, "omniscienceBreakdown": {"accuracy": 0.4548333333333333, "hallucinationRate": 0.8978905533476002}, "mlcrOverall": 0.122222222222222, "gdpPdfAllPass": 0.208, "gdpval": 1415.36, "gdpvalNormalized": 0.45768, "itBenchSre": null, "tau2": 0.783625730994152, "tauBanking": 0.28659793814433, "terminalbenchHard": 0.575757575757576, "terminalBench21": 0.756554307116105, "terminalBench40": 0.0151515151515152, "scicode": 0.524305555555556, "lcr": 0.776666666666667, "ifbench": 0.64421768707483, "hle": 0.385078776645042, "gpqa": 0.895959595959596, "critpt": 0.228571428571429, "apexAgents": null, "mmmuPro": 0.790751445086705, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.42020382951827845, "price1mInputTokens": 2, "price1mOutputTokens": 12, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4.5, "price1mBlended7To2To1": 1.7399999999999998, "price1mBlended0To1To1": 7, "price1mBlended100To1To1": 0.3333333333333333, "price1mBlended0To100To1": 2.099009900990099, "intelligenceIndexTimePerTask": 131.5770170691756, "intelligenceIndexCost": {"total": 767.7843701229723, "input": 369.3161501229723, "nonCacheInput": 54.293506, "cacheRead": 155.73656964148066, "cacheWrite": 159.28607448149168, "output": 398.46822, "reasoning": 265.161804, "answer": 133.30641599999998}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.3378727947949101, "input": 0.2023488711662519, "nonCacheInput": 0.041349276299665325, "cacheRead": 0.0869347504829282, "cacheWrite": 0.07406484438365833, "output": 0.13552392362865825, "reasoning": 0.06529731992493919, "answer": 0.07022660370371908}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.12915186467191203}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.05324483321425613}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.020183923072752265}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.0628370040020466}, {"slug": "scicode", "weightedCostPerTask": 0.002319586111111111}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0061877140871177015}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.03543571}, {"slug": "critpt", "weightedCostPerTask": 0.017406634285714283}, {"slug": "omniscience", "weightedCostPerTask": 0.00146215135}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.009643374000000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 869544031, "output": 33205685, "answer": 11108868, "reasoning": 22096817}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 5441.443327078267, "answer": 5852.216975309924, "output": 11293.66030238819}, "briefcaseBreakdown": {"overall": {"elo": 1201.36, "lower95ci": 1192.55, "upper95ci": 1210.15}, "rubricPassRate": 0.29797979797979796, "analyticalQuality": {"elo": 1182.14, "lower95ci": 1165.23, "upper95ci": 1198.68}, "presentation": {"elo": 1380.18, "lower95ci": 1365.13, "upper95ci": 1394.51}}, "briefcaseTotalCost": 78.3521312342933, "timescaleData": {"medianOutputSpeed": 86.2279569675967, "medianTimeToFirstChunk": 3.13577595649997}, "outputSpeedVariance": {"p05": 59.2805823670968, "q25": 69.124175277356, "median": 86.2279569675967, "q75": 99.840916728968, "p95": 104.013197916586}, "timeToFirstChunkVariance": {"p05": 1.81049307005015, "q25": 2.25049569925, "median": 3.13577595649997, "q75": 4.87275371875012, "p95": 20.0619659658999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 83.0565784744628, "medianTimeToFirstChunk": 2.74026167650004, "medianTimeToFirstAnswerToken": 2.74026167650004, "medianEndToEndResponseTime": 8.760254423416935}, "long": {"medianOutputSpeed": 86.2279569675967, "medianTimeToFirstChunk": 3.13577595649997, "medianTimeToFirstAnswerToken": 3.13577595649997, "medianEndToEndResponseTime": 8.934359357796295}, "hundredK": {"medianOutputSpeed": 294.73602311511, "medianTimeToFirstChunk": 3.31725523449999, "medianTimeToFirstAnswerToken": 3.31725523449999, "medianEndToEndResponseTime": 5.013688519835877}, "mediumParallel": {"medianOutputSpeed": 80.4120574294938, "medianTimeToFirstChunk": 10.8961628805001, "medianTimeToFirstAnswerToken": 10.8961628805001, "medianEndToEndResponseTime": 17.11413585598833}}, "endToEndResponseTime": {"input": 3.13577595649997, "reasoning": 0, "answer": 5.798583401296325, "total": 8.934359357796295}, "timeToFirstAnswerToken": {"input": 3.13577595649997, "reasoning": 0, "total": 3.13577595649997}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "81b6ddfc-111e-4422-bd44-42ee6165b699", "slug": "glm-4-7-non-reasoning", "name": "GLM-4.7 (Non-reasoning)", "shortName": "GLM-4.7 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-22", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "glm-4-7", "name": "GLM-4.7"}, "deprecated": true, "deprecatedTo": "glm-5-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 357, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-4.7", "microevalsEnabled": false, "intelligenceIndex": 17.3564299133682, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -47.3166666666667, "omniscienceBreakdown": {"accuracy": 0.23633333333333334, "hallucinationRate": 0.9290702749890878}, "gdpval": null, "itBenchSre": null, "tau2": 0.941520467836257, "tauBanking": null, "terminalbenchHard": 0.303030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.406666666666667, "ifbench": 0.546258503401361, "hle": 0.0639481000926784, "gpqa": 0.663636363636364, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.561904761904762, "aime25": 0.48, "analystAgent": null, "price1mInputTokens": 0.6, "price1mOutputTokens": 2.2, "cacheHitPrice": 0.525, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1, "price1mBlended7To2To1": 0.7075, "price1mBlended0To1To1": 1.4000000000000001, "price1mBlended100To1To1": 0.5421568627450981, "price1mBlended0To100To1": 0.6158415841584158, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 98.5693652644279, "medianTimeToFirstChunk": 1.370167264}, "outputSpeedVariance": {"p05": 13.4395737798198, "q25": 34.450426738998, "median": 98.5693652644279, "q75": 173.536621962556, "p95": 253.036424833348}, "timeToFirstChunkVariance": {"p05": 0.540420236099999, "q25": 0.729162131750059, "median": 1.370167264, "q75": 3.41803247475004, "p95": 9.40106205104983}, "performanceByPromptType": {"long": {"medianOutputSpeed": 98.5693652644279, "medianTimeToFirstChunk": 1.370167264, "medianTimeToFirstAnswerToken": 1.370167264, "medianEndToEndResponseTime": 6.442737211657378}}, "endToEndResponseTime": {"input": 1.370167264, "reasoning": 0, "answer": 5.072569947657378, "total": 6.442737211657378}, "timeToFirstAnswerToken": {"input": 1.370167264, "reasoning": 0, "total": 1.370167264}, "performanceDataSource": {"type": "median"}, "hostModelCount": 6, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8215372b-66ff-457b-855e-e8abeafc9571", "slug": "a-x-k2", "name": "A.X-K2", "shortName": "A.X-K2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "a-x-k2", "name": "A.X-K2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 692, "inferenceParametersActiveBillions": 33, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/skt/A.X-K2", "microevalsEnabled": false, "intelligenceIndex": 22.7039007610661, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -8.23333333333333, "omniscienceBreakdown": {"accuracy": 0.18616666666666667, "hallucinationRate": 0.32992013106696705}, "gdpval": 1044.19, "gdpvalNormalized": 0.27209500000000003, "itBenchSre": null, "tau2": null, "tauBanking": 0.160824742268041, "terminalbenchHard": null, "terminalBench21": 0.389513108614232, "terminalBench40": null, "scicode": 0.409722222222222, "lcr": 0.7, "ifbench": null, "hle": 0.295644114921223, "gpqa": 0.856565656565657, "critpt": 0.0885714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b943b29d-0549-4b21-aa0f-3dd955ee12e2", "slug": "sk-telecom", "name": "SK Telecom", "logo": "/img/logos/sktelecom_small.svg", "color": "#E1002A", "country": "kr", "url": "https://www.sktelecom.com/index_en.html"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8273650d-40e5-45ee-aeda-df71de784164", "slug": "exaone-4-0-1-2b", "name": "Exaone 4.0 1.2B (Non-reasoning)", "shortName": "Exaone 4.0 1.2B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-15", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "exaone-4-0-1-2b", "name": "Exaone 4.0 1.2B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 1.28, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 64000, "licenseName": "EXAONE AI Model License Agreement 1.2 - NC", "licenseUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B", "microevalsEnabled": false, "intelligenceIndex": 5.22938457197929, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -82.15, "omniscienceBreakdown": {"accuracy": 0.05, "hallucinationRate": 0.9173684210526316}, "gdpval": null, "itBenchSre": null, "tau2": 0.204678362573099, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.253061224489796, "hle": 0.0569972196478221, "gpqa": 0.424242424242424, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.293121693121693, "aime25": 0.24, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 3, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "45157c16-fcbb-4110-b20f-7bca754b6554", "slug": "lg", "name": "LG AI Research", "logo": "/img/logos/lg_small.png", "color": "#df3b8a", "country": "kr", "url": "https://www.lgresearch.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "82879bb8-89fb-4adc-b519-315b8ef30b77", "slug": "llama-3-instruct-8b", "name": "Llama 3 Instruct 8B", "shortName": "Llama 3 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-04-18", "knowledgeCutoffDate": "2023-03-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-instruct-8b", "name": "Llama 3 Instruct 8B"}, "deprecated": true, "deprecatedTo": "llama-3-1-instruct-8b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 8192, "licenseName": "META LLAMA 3 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://llama.meta.com/llama3/license/", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -70.1166666666667, "omniscienceBreakdown": {"accuracy": 0.10366666666666667, "hallucinationRate": 0.8979174414280402}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.245578231292517, "hle": 0.0506, "gpqa": 0.295959595959596, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0962962962962963, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.045, "price1mOutputTokens": 0.145, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.07, "price1mBlended7To2To1": 0.05500000000000001, "price1mBlended0To1To1": 0.095, "price1mBlended100To1To1": 0.04598039215686274, "price1mBlended0To100To1": 0.04599009900990099, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 4, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "82b207dd-d285-4a52-b2fc-2cbd27543899", "slug": "hermes-4-llama-3-1-405b-reasoning", "name": "Hermes 4 - Llama-3.1 405B (Reasoning)", "shortName": "Hermes 4 405B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-27", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "hermes-4-llama-3-1-405b", "name": "Hermes 4 - Llama-3.1 405B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 406, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "META LLAMA 3 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://llama.meta.com/llama3/license/", "modelWeightsSourceUrl": "https://huggingface.co/NousResearch/Hermes-4-405B", "microevalsEnabled": false, "intelligenceIndex": 7.49497809925135, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -36.0166666666667, "omniscienceBreakdown": {"accuracy": 0.30083333333333334, "hallucinationRate": 0.9454112038140644}, "gdpval": null, "itBenchSre": null, "tau2": 0.222222222222222, "tauBanking": null, "terminalbenchHard": 0.113636363636364, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.223333333333333, "ifbench": 0.327210884353742, "hle": 0.108897126969416, "gpqa": 0.727272727272727, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.685714285714286, "aime25": 0.696666666666667, "analystAgent": null, "price1mInputTokens": 1, "price1mOutputTokens": 3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5, "price1mBlended7To2To1": 1.2, "price1mBlended0To1To1": 2, "price1mBlended100To1To1": 1.0196078431372548, "price1mBlended0To100To1": 1.0198019801980198, "openness": {"opennessIndex": 47.22222222222222, "modelAvailability": 4, "transparencyMethodology": 3, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 43.2212137855878, "medianTimeToFirstChunk": 2.45762511350006}, "outputSpeedVariance": {"p05": 37.8363761493636, "q25": 40.5111035147343, "median": 43.2212137855878, "q75": 44.4905476791435, "p95": 46.3738769067917}, "timeToFirstChunkVariance": {"p05": 2.28220853579999, "q25": 2.32697666400008, "median": 2.45762511350006, "q75": 3.02797010300003, "p95": 5.51288211660001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 44.7151784854139, "medianTimeToFirstChunk": 0.792808724999986, "medianTimeToFirstAnswerToken": 45.52035019399804, "medianEndToEndResponseTime": 56.702235561247555}, "long": {"medianOutputSpeed": 43.2212137855878, "medianTimeToFirstChunk": 2.45762511350006, "medianTimeToFirstAnswerToken": 48.731198315808044, "medianEndToEndResponseTime": 60.29959161638504}, "hundredK": {"medianOutputSpeed": 32.7581069650357, "medianTimeToFirstChunk": 24.5742492454999, "medianTimeToFirstAnswerToken": 85.62783827415458, "medianEndToEndResponseTime": 100.89123553131824}, "mediumParallel": {"medianOutputSpeed": 40.4941814848852, "medianTimeToFirstChunk": 1.95023598250009, "medianTimeToFirstAnswerToken": 51.34004771993494, "medianEndToEndResponseTime": 63.68750065429364}}, "endToEndResponseTime": {"input": 2.45762511350006, "reasoning": 46.273573202307986, "answer": 11.568393300576997, "total": 60.29959161638504}, "timeToFirstAnswerToken": {"input": 2.45762511350006, "reasoning": 46.273573202307986, "total": 48.731198315808044}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0a2f41cc-2cbc-4949-be54-9fef1319d4a9", "slug": "nous-research", "name": "Nous Research", "logo": "/img/logos/nousresearch_small.jpg", "color": "#006fa8", "country": "us", "url": "https://nousresearch.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "82b36b4d-84dd-4bc0-ad32-e3aee9442789", "slug": "mimo-v2-flash", "name": "MiMo-V2-Flash (Non-reasoning)", "shortName": "MiMo-V2-Flash (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-16", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mimo-v2-flash", "name": "MiMo-V2-Flash"}, "deprecated": true, "deprecatedTo": "mimo-v2-0206", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 309, "inferenceParametersActiveBillions": 15, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "MIT", "licenseUrl": "https://choosealicense.com/licenses/mit/", "modelWeightsSourceUrl": "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash", "microevalsEnabled": true, "intelligenceIndex": 16.0498614373966, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -48.45, "omniscienceBreakdown": {"accuracy": 0.15633333333333332, "hallucinationRate": 0.7595811932042671}, "gdpval": 788.18, "gdpvalNormalized": 0.14408999999999997, "itBenchSre": null, "tau2": 0.839181286549708, "tauBanking": null, "terminalbenchHard": 0.257575757575758, "terminalBench21": 0.617977528089888, "terminalBench40": null, "scicode": null, "lcr": 0.363333333333333, "ifbench": 0.399319727891157, "hle": 0.0857275254865616, "gpqa": 0.655555555555556, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.402116402116402, "aime25": 0.676666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 52.77777777777778, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5147c8b4-61d5-4070-9324-8adf8aa144c2", "slug": "xiaomi", "name": "Xiaomi", "logo": "/img/logos/xiaomi_small.svg", "color": "#ff6900", "country": "cn", "url": "https://huggingface.co/XiaomiMiMo"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "82ed9bd2-c97b-4c35-9312-94bb72001e36", "slug": "granite-4-1-8b", "name": "Granite 4.1 8B", "shortName": "Granite 4.1 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-29", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "granite-4-1-8b", "name": "Granite 4.1 8B"}, "deprecated": true, "deprecatedTo": "granite-4-2-8b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.1-8b", "microevalsEnabled": true, "intelligenceIndex": 6.57208916161427, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -64.1166666666667, "omniscienceBreakdown": {"accuracy": 0.123, "hallucinationRate": 0.871341695172938}, "gdpval": null, "itBenchSre": null, "tau2": 0.277777777777778, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": 0.0337078651685393, "terminalBench40": null, "scicode": null, "lcr": 0.133333333333333, "ifbench": 0.386394557823129, "hle": 0.0379981464318814, "gpqa": 0.433333333333333, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.05, "price1mOutputTokens": 0.1, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.0625, "price1mBlended7To2To1": 0.05500000000000001, "price1mBlended0To1To1": 0.07500000000000001, "price1mBlended100To1To1": 0.05049019607843137, "price1mBlended0To100To1": 0.05049504950495049, "openness": {"opennessIndex": 61.111111111111114, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {"medianOutputSpeed": 99.7940208765371, "medianTimeToFirstChunk": 0.800859679500149}, "outputSpeedVariance": {"p05": 25.123365933369, "q25": 49.8183825067927, "median": 99.7940208765371, "q75": 125.77840704215, "p95": 126.469325434645}, "timeToFirstChunkVariance": {"p05": 0.725206141400065, "q25": 0.765355660000043, "median": 0.800859679500149, "q75": 0.839868258750073, "p95": 1.10683238784998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 133.732575827773, "medianTimeToFirstChunk": 0.488425920999987, "medianTimeToFirstAnswerToken": 0.488425920999987, "medianEndToEndResponseTime": 4.2272307477605455}, "long": {"medianOutputSpeed": 99.7940208765371, "medianTimeToFirstChunk": 0.800859679500149, "medianTimeToFirstAnswerToken": 0.800859679500149, "medianEndToEndResponseTime": 5.811179893158927}, "hundredK": {"medianOutputSpeed": 62.7710617750621, "medianTimeToFirstChunk": 8.95566687450003, "medianTimeToFirstAnswerToken": 8.95566687450003, "medianEndToEndResponseTime": 16.92112079324578}, "mediumParallel": {"medianOutputSpeed": 126.785869718164, "medianTimeToFirstChunk": 0.612290270499898, "medianTimeToFirstAnswerToken": 0.612290270499898, "medianEndToEndResponseTime": 4.555947407619867}}, "endToEndResponseTime": {"input": 0.800859679500149, "reasoning": 0, "answer": 5.010320213658779, "total": 5.811179893158927}, "timeToFirstAnswerToken": {"input": 0.800859679500149, "reasoning": 0, "total": 0.800859679500149}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "83173329-c09a-41f1-a028-a282a5f908d7", "slug": "deepseek-v4-pro", "name": "DeepSeek V4 Pro 0813 (Reasoning, Max Effort)", "shortName": "DeepSeek V4 Pro 0813 (max)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-08-13", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "deepseek-v4-pro", "name": "DeepSeek V4 Pro 0813"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1600, "inferenceParametersActiveBillions": 49, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813", "microevalsEnabled": false, "intelligenceIndex": 36.2828791278402, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 41.77394563210203, "strategyAndOps": 46.94265991663919, "legal": 41.46014603790894, "healthcareAndMedical": 38.56490901580221, "engineering": 37.42014131491, "economics": 44.05760978529504}, "omniscience": 0.833333333333333, "omniscienceBreakdown": {"accuracy": 0.491, "hallucinationRate": 0.9482645710543549}, "mlcrOverall": 0.177777777777778, "gdpPdfAllPass": 0.114, "gdpval": 1493.31, "gdpvalNormalized": 0.49665499999999996, "itBenchSre": null, "tau2": null, "tauBanking": 0.395876288659794, "terminalbenchHard": null, "terminalBench21": 0.786516853932584, "terminalBench40": 0.141414141414141, "scicode": 0.510416666666667, "lcr": 0.803333333333333, "ifbench": null, "hle": 0.410101946246525, "gpqa": 0.928282828282828, "critpt": 0.18, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5671165546344002, "enterpriseOpsGym": 0.4959713518352731, "price1mInputTokens": 1.32, "price1mOutputTokens": 3.96, "cacheHitPrice": 0.044, "cacheHitDiscountPercent": 0.9666666666666667, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.98, "price1mBlended7To2To1": 0.6908, "price1mBlended0To1To1": 2.64, "price1mBlended100To1To1": 0.09490196078431372, "price1mBlended0To100To1": 1.3461386138613862, "intelligenceIndexTimePerTask": 485.6301416154231, "intelligenceIndexCost": {"total": 1122.2711228899416, "input": 477.2801868499415, "nonCacheInput": 22.054468919999998, "cacheRead": 231.08851933069167, "cacheWrite": 224.13719859924984, "output": 644.99093604, "reasoning": 547.05880944, "answer": 97.9321266}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.6740219040435134, "input": 0.4556103637305936, "nonCacheInput": 0.013123429432450151, "cacheRead": 0.26752018427641244, "cacheWrite": 0.1749667500217311, "output": 0.21841154031291962, "reasoning": 0.15112833401052114, "answer": 0.06728320630239852}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.14932322146719187}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.058046093558677556}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.017037512128089523}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.3755228533853407}, {"slug": "scicode", "weightedCostPerTask": 0.00502562225}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.01357293633364226}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.010998977879999998}, {"slug": "critpt", "weightedCostPerTask": 0.035675451428571425}, {"slug": "omniscience", "weightedCostPerTask": 0.0018756389519999997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00694359666}]}, "canonicalIntelligenceIndexTokenCount": {"input": 5438520642, "output": 162876499, "answer": 24730335, "reasoning": 138146164}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 38163.72070972756, "answer": 16990.708662221845, "output": 55154.4293719494}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1264.67, "lower95ci": 1258.2, "upper95ci": 1272.12}, "rubricPassRate": 0.4351851851851852, "analyticalQuality": {"elo": 1395.67, "lower95ci": 1383.17, "upper95ci": 1409.88}, "presentation": {"elo": 1123.33, "lower95ci": 1110.31, "upper95ci": 1136.17}}, "briefcaseTotalCost": 90.58942102342974, "timescaleData": {"medianOutputSpeed": 92.5179584618785, "medianTimeToFirstChunk": 1.84345583749996}, "outputSpeedVariance": {"p05": 47.489814548582, "q25": 65.246117317403, "median": 92.5179584618785, "q75": 118.080847832679, "p95": 142.674173773573}, "timeToFirstChunkVariance": {"p05": 0.925643424699968, "q25": 1.54586554374997, "median": 1.84345583749996, "q75": 2.14923073525001, "p95": 3.40578747929996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 81.1017281897276, "medianTimeToFirstChunk": 1.23273586849999, "medianTimeToFirstAnswerToken": 25.89312282500533, "medianEndToEndResponseTime": 32.05821956413167}, "long": {"medianOutputSpeed": 92.5179584618785, "medianTimeToFirstChunk": 1.84345583749996, "medianTimeToFirstAnswerToken": 23.46088053266429, "medianEndToEndResponseTime": 28.865236706455374}, "hundredK": {"medianOutputSpeed": 111.174475474175, "medianTimeToFirstChunk": 8.74864656099999, "medianTimeToFirstAnswerToken": 26.73838738477914, "medianEndToEndResponseTime": 31.23582259072393}, "mediumParallel": {"medianOutputSpeed": 63.4602236511467, "medianTimeToFirstChunk": 1.11709290700003, "medianTimeToFirstAnswerToken": 32.63289737365922, "medianEndToEndResponseTime": 40.51184849032401}}, "endToEndResponseTime": {"input": 1.84345583749996, "reasoning": 21.61742469516433, "answer": 5.404356173791083, "total": 28.865236706455374}, "timeToFirstAnswerToken": {"input": 1.84345583749996, "reasoning": 21.61742469516433, "total": 23.46088053266429}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 10, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "83cb898e-05d9-4e4b-9de3-2d305014d923", "slug": "claude-instant", "name": "Claude Instant", "shortName": "Claude Instant", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-03-14", "knowledgeCutoffDate": "2023-01-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-instant", "name": "Claude Instant"}, "deprecated": true, "deprecatedTo": "claude-2", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 100000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.03498213171439, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0353, "gpqa": 0.33030303030303, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.108994708994709, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "84922739-425f-46e1-87ac-bb4268dcacbb", "slug": "gemini-2-5-flash-lite-preview-09-2025-reasoning", "name": "Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)", "shortName": "Gemini 2.5 Flash-Lite (Sep)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-08", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-flash-lite-preview-09-2025", "name": "Gemini 2.5 Flash-Lite Preview (Sep '25)"}, "deprecated": true, "deprecatedTo": "gemini-3-1-flash-lite-preview", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 10.3543486383322, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.0166666666667, "omniscienceBreakdown": {"accuracy": 0.17983333333333335, "hallucinationRate": 0.8778703515545621}, "gdpval": null, "itBenchSre": null, "tau2": 0.307017543859649, "tauBanking": null, "terminalbenchHard": 0.128787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.646666666666667, "ifbench": 0.525850340136054, "hle": 0.0695088044485635, "gpqa": 0.709090909090909, "critpt": 0, "apexAgents": null, "mmmuPro": 0.64971098265896, "livecodebench": 0.687830687830688, "aime25": 0.686666666666667, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.01, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.17500000000000002, "price1mBlended7To2To1": 0.067, "price1mBlended0To1To1": 0.25, "price1mBlended100To1To1": 0.014705882352941176, "price1mBlended0To100To1": 0.10297029702970298, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "84b49308-6b93-47aa-a4f6-776ee1a1e8cd", "slug": "o4-mini", "name": "o4-mini (high)", "shortName": "o4-mini (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "o4-mini", "name": "o4-mini"}, "deprecated": true, "deprecatedTo": "gpt-5-mini", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 16.653105214846, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -35.7, "omniscienceBreakdown": {"accuracy": 0.248, "hallucinationRate": 0.8045212765957447}, "gdpval": null, "itBenchSre": null, "tau2": 0.555555555555556, "tauBanking": null, "terminalbenchHard": 0.151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.61, "ifbench": 0.687074829931973, "hle": 0.165430954587581, "gpqa": 0.783838383838384, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": 0.692485549132948, "livecodebench": 0.859259259259259, "aime25": 0.906666666666667, "analystAgent": null, "price1mInputTokens": 1.1, "price1mOutputTokens": 4.4, "cacheHitPrice": 0.275, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": 1.9371, "price1mBlended0To3To1": 1.9250000000000003, "price1mBlended7To2To1": 0.8525, "price1mBlended0To1To1": 2.75, "price1mBlended100To1To1": 0.32352941176470595, "price1mBlended0To100To1": 1.1326732673267328, "timescaleData": {"medianOutputSpeed": 139.488992492642, "medianTimeToFirstChunk": 27.4691298705}, "outputSpeedVariance": {"p05": 94.4982592686636, "q25": 113.259611284827, "median": 139.488992492642, "q75": 158.814915673431, "p95": 189.979292401288}, "timeToFirstChunkVariance": {"p05": 7.27073645110001, "q25": 19.6803334875, "median": 27.4691298705, "q75": 67.9137650075001, "p95": 160.7757034079}, "performanceByPromptType": {"long": {"medianOutputSpeed": 139.488992492642, "medianTimeToFirstChunk": 27.4691298705, "medianTimeToFirstAnswerToken": 27.4691298705, "medianEndToEndResponseTime": 31.053642103795937}}, "endToEndResponseTime": {"input": 27.4691298705, "reasoning": 0, "answer": 3.5845122332959343, "total": 31.053642103795937}, "timeToFirstAnswerToken": {"input": 27.4691298705, "reasoning": 0, "total": 27.4691298705}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 3, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "84e3f11e-d659-4941-8988-1dbfabbaf538", "slug": "gpt-5-2-medium", "name": "GPT-5.2 (medium)", "shortName": "GPT-5.2 (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-11", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-5-2", "name": "GPT-5.2"}, "deprecated": true, "deprecatedTo": "gpt-5-4", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 26.5009561703275, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 0.266666666666667, "omniscienceBreakdown": {"accuracy": 0.38283333333333336, "hallucinationRate": 0.615987037537132}, "gdpval": null, "itBenchSre": null, "tau2": 0.742690058479532, "tauBanking": null, "terminalbenchHard": 0.431818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.703333333333333, "ifbench": 0.652380952380953, "hle": 0.266913809082484, "gpqa": 0.863636363636364, "critpt": 0.0785714285714285, "apexAgents": null, "mmmuPro": 0.745664739884393, "livecodebench": 0.894179894179894, "aime25": 0.966666666666667, "analystAgent": null, "price1mInputTokens": 1.75, "price1mOutputTokens": 14, "cacheHitPrice": 0.9625, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 2.15, "price1mBlended0To3To1": 4.8125, "price1mBlended7To2To1": 2.42375, "price1mBlended0To1To1": 7.875, "price1mBlended100To1To1": 1.0980392156862746, "price1mBlended0To100To1": 1.8712871287128714, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "864da2a5-156c-45fd-873c-8923be91914f", "slug": "magistral-medium-2509", "name": "Magistral Medium 1.2", "shortName": "Magistral Medium 1.2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-18", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "magistral-medium-2509", "name": "Magistral Medium 1.2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.8254509953707, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -26.7333333333333, "omniscienceBreakdown": {"accuracy": 0.20783333333333334, "hallucinationRate": 0.5998316852514202}, "gdpval": 361.94, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.52046783625731, "tauBanking": 0.0556701030927835, "terminalbenchHard": 0.128787878787879, "terminalBench21": 0.123595505617978, "terminalBench40": null, "scicode": null, "lcr": 0.53, "ifbench": 0.429931972789116, "hle": 0.102873030583874, "gpqa": 0.739393939393939, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.596531791907514, "livecodebench": 0.75026455026455, "aime25": 0.82, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 2, "transparencyMethodology": 2, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8665ca00-c687-44c7-875c-22618cb31c4f", "slug": "qwen3-6-35b-a3b", "name": "Qwen3.6 35B A3B (Reasoning)", "shortName": "Qwen3.6 35B A3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 5395, "release": {"slug": "qwen3-6-35b-a3b", "name": "Qwen3.6 35B A3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 36, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "microevalsEnabled": false, "intelligenceIndex": 18.8138400189843, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 19.229441317927368, "strategyAndOps": 14.260939017040581, "legal": 21.62645980502629, "engineering": 22.14912975638819, "economics": 29.79063193157244}, "omniscience": -22.1833333333333, "omniscienceBreakdown": {"accuracy": 0.18816666666666668, "hallucinationRate": 0.5050297680147814}, "gdpPdfAllPass": 0.066, "gdpval": 990.51, "gdpvalNormalized": 0.245255, "itBenchSre": null, "tau2": 0.953216374269006, "tauBanking": 0.0927835051546392, "terminalbenchHard": 0.348484848484849, "terminalBench21": 0.449438202247191, "terminalBench40": 0, "scicode": 0.365740740740741, "lcr": 0.716666666666667, "ifbench": 0.643537414965986, "hle": 0.222428174235403, "gpqa": 0.841414141414142, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.75028901734104, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.05208565614505884, "price1mInputTokens": 0.375, "price1mOutputTokens": 2.25, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.254, "price1mBlended0To3To1": 0.84375, "price1mBlended7To2To1": 0.5625, "price1mBlended0To1To1": 1.3125, "price1mBlended100To1To1": 0.39338235294117646, "price1mBlended0To100To1": 0.3935643564356436, "intelligenceIndexTimePerTask": 261.9033525883093, "intelligenceIndexCost": {"total": 896.38941975, "input": 533.75105175, "nonCacheInput": 7.17558075, "cacheRead": 0, "cacheWrite": 526.575471, "output": 362.638368, "reasoning": 86.20767675, "answer": 276.43069125}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.4750534562511306, "input": 0.3972175434327144, "nonCacheInput": 0.004719833257341868, "cacheRead": 0, "cacheWrite": 0.39249771017537255, "output": 0.07783591281841616, "reasoning": 0.028136404966474637, "answer": 0.04969950785194152}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.10973247342032967}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.04294626954545455}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.019255842551369865}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.2760922772727273}, {"slug": "scicode", "weightedCostPerTask": 0.0009506582031250001}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.011800462917052825}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0043930751250000006}, {"slug": "critpt", "weightedCostPerTask": 0.007121451428571428}, {"slug": "omniscience", "weightedCostPerTask": 0.0007316329125}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0020293128749999997}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1423336138, "output": 161172608, "answer": 122858085, "reasoning": 38314523}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 12505.068873988728, "answer": 22088.67015641846, "output": 34593.73903040719}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 711.46, "lower95ci": 702.46, "upper95ci": 719.63}, "rubricPassRate": 0.15252525252525254, "analyticalQuality": {"elo": 563.44, "lower95ci": 546.17, "upper95ci": 578.75}, "presentation": {"elo": 762.19, "lower95ci": 746, "upper95ci": 776.22}}, "briefcaseTotalCost": 66.571033875, "timescaleData": {"medianOutputSpeed": 127.218887902964, "medianTimeToFirstChunk": 2.08781722400002}, "outputSpeedVariance": {"p05": 80.3994798632258, "q25": 93.272073288627, "median": 127.218887902964, "q75": 145.646151631449, "p95": 158.433263576102}, "timeToFirstChunkVariance": {"p05": 1.90949293809995, "q25": 1.98847434024999, "median": 2.08781722400002, "q75": 2.19543954450001, "p95": 2.48943146454996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 120.506502052975, "medianTimeToFirstChunk": 1.11656050599998, "medianTimeToFirstAnswerToken": 45.88592903043315, "medianEndToEndResponseTime": 50.03508273983381}, "long": {"medianOutputSpeed": 127.218887902964, "medianTimeToFirstChunk": 2.08781722400002, "medianTimeToFirstAnswerToken": 44.49504219608929, "medianEndToEndResponseTime": 48.42527620647754}, "hundredK": {"medianOutputSpeed": 167.001777919706, "medianTimeToFirstChunk": 8.61314368400002, "medianTimeToFirstAnswerToken": 40.91818897875073, "medianEndToEndResponseTime": 43.912169080210475}, "mediumParallel": {"medianOutputSpeed": 117.607693645885, "medianTimeToFirstChunk": 1.07718453550001, "medianTimeToFirstAnswerToken": 46.950033774804574, "medianEndToEndResponseTime": 51.20145631783558}}, "endToEndResponseTime": {"input": 2.08781722400002, "reasoning": 42.40722497208927, "answer": 3.9302340103882547, "total": 48.42527620647754}, "timeToFirstAnswerToken": {"input": 2.08781722400002, "reasoning": 42.40722497208927, "total": 44.49504219608929}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 8, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "87110ff0-1f79-41b4-9976-eda250597317", "slug": "gpt-5-6-luna-xhigh", "name": "GPT-5.6 Luna (xhigh)", "shortName": "GPT-5.6 Luna (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-6-luna", "name": "GPT-5.6 Luna"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 34.772048822309, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 37.52982474981427, "strategyAndOps": 40.96416125346716, "legal": 35.025534196517356, "healthcareAndMedical": 33.26141989646827, "engineering": 34.2177199110127, "economics": 40.87637272165587}, "omniscience": -10.7666666666667, "omniscienceBreakdown": {"accuracy": 0.4245, "hallucinationRate": 0.9247031566753547}, "mlcrOverall": 0.161111111111111, "gdpPdfAllPass": 0.238, "gdpval": 1428.47, "gdpvalNormalized": 0.464235, "itBenchSre": null, "tau2": null, "tauBanking": 0.28659793814433, "terminalbenchHard": null, "terminalBench21": 0.779026217228464, "terminalBench40": 0.0353535353535354, "scicode": 0.50462962962963, "lcr": 0.816666666666667, "ifbench": null, "hle": 0.369786839666358, "gpqa": 0.894949494949495, "critpt": 0.205714285714286, "apexAgents": null, "mmmuPro": 0.785549132947977, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.42597767374285944, "price1mInputTokens": 0.2, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.02, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.25, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.45, "price1mBlended7To2To1": 0.174, "price1mBlended0To1To1": 0.7, "price1mBlended100To1To1": 0.03333333333333334, "price1mBlended0To100To1": 0.2099009900990099, "intelligenceIndexTimePerTask": 197.7222306477936, "intelligenceIndexCost": {"total": 179.3338697377199, "input": 77.12482853771994, "nonCacheInput": 5.4821778000000005, "cacheRead": 45.532366370633056, "cacheWrite": 26.110284367086873, "output": 102.20904119999999, "reasoning": 84.57459359999999, "answer": 17.634447599999998}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.085342806135728, "input": 0.05699336768895161, "nonCacheInput": 0.004192357451982362, "cacheRead": 0.037834157348881084, "cacheWrite": 0.014966852888088147, "output": 0.02834943844677641, "reasoning": 0.01766787882808803, "answer": 0.010681559618688375}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.032015605411299955}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.007233741185115326}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.003602634566499703}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.030028798955259804}, {"slug": "scicode", "weightedCostPerTask": 0.00044690597222222226}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0016706746431881367}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0046454872}, {"slug": "critpt", "weightedCostPerTask": 0.003950594857142857}, {"slug": "omniscience", "weightedCostPerTask": 0.0007524035449999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0009959598}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2408470345, "output": 85174201, "answer": 14695373, "reasoning": 70478828}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 14723.232356740027, "answer": 8901.299682240313, "output": 23624.53203898034}, "briefcaseBreakdown": {"overall": {"elo": 1268.01, "lower95ci": 1259.36, "upper95ci": 1276.75}, "rubricPassRate": 0.3484848484848485, "analyticalQuality": {"elo": 1256.19, "lower95ci": 1242.16, "upper95ci": 1272.64}, "presentation": {"elo": 1406.97, "lower95ci": 1391.98, "upper95ci": 1423.01}}, "briefcaseTotalCost": 19.42280061618864, "timescaleData": {"medianOutputSpeed": 118.970892227368, "medianTimeToFirstChunk": 39.2074596980001}, "outputSpeedVariance": {"p05": 90.8757297865933, "q25": 108.634546319367, "median": 118.970892227368, "q75": 133.909505520278, "p95": 150.263407175343}, "timeToFirstChunkVariance": {"p05": 11.21350072255, "q25": 33.3694834670001, "median": 39.2074596980001, "q75": 58.7318528925, "p95": 118.3931900899}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 119.038344485893, "medianTimeToFirstChunk": 28.8992950860001, "medianTimeToFirstAnswerToken": 28.8992950860001, "medianEndToEndResponseTime": 33.09962231803124}, "long": {"medianOutputSpeed": 118.970892227368, "medianTimeToFirstChunk": 39.2074596980001, "medianTimeToFirstAnswerToken": 39.2074596980001, "medianEndToEndResponseTime": 43.41016836596939}, "hundredK": {"medianOutputSpeed": 116.212104924204, "medianTimeToFirstChunk": 27.330999444, "medianTimeToFirstAnswerToken": 27.330999444, "medianEndToEndResponseTime": 31.633477230854567}, "mediumParallel": {"medianOutputSpeed": 116.996686558902, "medianTimeToFirstChunk": 81.0386368459999, "medianTimeToFirstAnswerToken": 81.0386368459999, "medianEndToEndResponseTime": 85.31226214861286}}, "endToEndResponseTime": {"input": 39.2074596980001, "reasoning": 0, "answer": 4.202708667969293, "total": 43.41016836596939}, "timeToFirstAnswerToken": {"input": 39.2074596980001, "reasoning": 0, "total": 39.2074596980001}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "877fdfc9-2026-477a-af96-e4fd602c0131", "slug": "gemini-2-5-flash-preview-09-2025", "name": "Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)", "shortName": "Gemini 2.5 Flash (Sep) (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-25", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-flash-preview-09-2025", "name": "Gemini 2.5 Flash Preview (Sep '25)"}, "deprecated": true, "deprecatedTo": "gemini-3-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.3823294842565, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -39.9, "omniscienceBreakdown": {"accuracy": 0.2683333333333333, "hallucinationRate": 0.9120728929384966}, "gdpval": null, "itBenchSre": null, "tau2": 0.283625730994152, "tauBanking": null, "terminalbenchHard": 0.143939393939394, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.6, "ifbench": 0.435374149659864, "hle": 0.0871177015755329, "gpqa": 0.765656565656566, "critpt": 0, "apexAgents": null, "mmmuPro": 0.702312138728324, "livecodebench": 0.625396825396825, "aime25": 0.566666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8823351e-8232-4c9c-8a1d-cd2c1d2c1196", "slug": "QwQ-32B-Preview", "name": "QwQ 32B-Preview", "shortName": "QwQ 32B-Preview", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-11-27", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "QwQ-32B-Preview", "name": "QwQ 32B-Preview"}, "deprecated": true, "deprecatedTo": "qwq-32b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32.8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/QwQ-32B-Preview", "microevalsEnabled": false, "intelligenceIndex": 7.58699681312465, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0391, "gpqa": 0.556565656565656, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.336507936507937, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "882a5da3-94ca-4602-8693-c45970df17e2", "slug": "ling-flash-2-0", "name": "Ling-flash-2.0", "shortName": "Ling-flash-2.0", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-17", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "ling-flash-2-0", "name": "Ling-flash-2.0"}, "deprecated": true, "deprecatedTo": "ling-2-6-flash", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 103, "inferenceParametersActiveBillions": 6.1, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ling-flash-2.0", "microevalsEnabled": false, "intelligenceIndex": 7.8074626926252, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -62.7, "omniscienceBreakdown": {"accuracy": 0.14133333333333334, "hallucinationRate": 0.8947981366459627}, "gdpval": null, "itBenchSre": null, "tau2": 0.207602339181287, "tauBanking": null, "terminalbenchHard": 0.106060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.176666666666667, "ifbench": 0.343537414965986, "hle": 0.06209453197405, "gpqa": 0.656565656565657, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.58941798941799, "aime25": 0.653333333333333, "analystAgent": null, "price1mInputTokens": 0.14, "price1mOutputTokens": 0.57, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.2475, "price1mBlended7To2To1": 0.183, "price1mBlended0To1To1": 0.355, "price1mBlended100To1To1": 0.14421568627450984, "price1mBlended0To100To1": 0.14425742574257427, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 6.35659906465637, "medianTimeToFirstChunk": 2.70543903650002}, "outputSpeedVariance": {"p05": 3.32695225532613, "q25": 3.77937064669373, "median": 6.35659906465637, "q75": 10.3503191806867, "p95": 46.2893592650966}, "timeToFirstChunkVariance": {"p05": 2.54128895829998, "q25": 2.62351002324999, "median": 2.70543903650002, "q75": 2.78940569275002, "p95": 3.25196079304999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 6.35659906465637, "medianTimeToFirstChunk": 2.70543903650002, "medianTimeToFirstAnswerToken": 2.70543903650002, "medianEndToEndResponseTime": 81.36385290124633}}, "endToEndResponseTime": {"input": 2.70543903650002, "reasoning": 0, "answer": 78.65841386474631, "total": 81.36385290124633}, "timeToFirstAnswerToken": {"input": 2.70543903650002, "reasoning": 0, "total": 2.70543903650002}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8869f28a-a6ff-487f-8d32-93fe335fdda5", "slug": "gpt-5-4-nano-medium", "name": "GPT-5.4 nano (medium)", "shortName": "GPT-5.4 nano", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-17", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-5-4-nano", "name": "GPT-5.4 nano"}, "deprecated": true, "deprecatedTo": "gpt-5-6-luna-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 20.0139276661357, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -18.0333333333333, "omniscienceBreakdown": {"accuracy": 0.219, "hallucinationRate": 0.5113102859581733}, "gdpval": null, "itBenchSre": null, "tau2": 0.526315789473684, "tauBanking": null, "terminalbenchHard": 0.333333333333333, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.673333333333333, "ifbench": 0.64421768707483, "hle": 0.159406858202039, "gpqa": 0.760606060606061, "critpt": 0.0514285714285714, "apexAgents": null, "mmmuPro": 0.595375722543353, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 1.25, "cacheHitPrice": 0.02, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.5, "price1mBlended0To3To1": 0.4625, "price1mBlended7To2To1": 0.179, "price1mBlended0To1To1": 0.725, "price1mBlended100To1To1": 0.03382352941176471, "price1mBlended0To100To1": 0.2103960396039604, "timescaleData": {"medianOutputSpeed": 152.172905008394, "medianTimeToFirstChunk": 4.54767937000008}, "outputSpeedVariance": {"p05": 119.428148948051, "q25": 138.764840708445, "median": 152.172905008394, "q75": 164.304247373501, "p95": 185.183354624927}, "timeToFirstChunkVariance": {"p05": 1.2555958586, "q25": 2.33212261875008, "median": 4.54767937000008, "q75": 6.64107708499998, "p95": 8.36697729535003}, "performanceByPromptType": {"long": {"medianOutputSpeed": 152.172905008394, "medianTimeToFirstChunk": 4.54767937000008, "medianTimeToFirstAnswerToken": 4.54767937000008, "medianEndToEndResponseTime": 7.8334154211875076}}, "endToEndResponseTime": {"input": 4.54767937000008, "reasoning": 0, "answer": 3.2857360511874276, "total": 7.8334154211875076}, "timeToFirstAnswerToken": {"input": 4.54767937000008, "reasoning": 0, "total": 4.54767937000008}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "891bcdf2-8dd2-4dc3-829b-d963fde25876", "slug": "apertus-8b-instruct", "name": "Apertus 8B Instruct", "shortName": "Apertus 8B Instruct", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "apertus-8b-instruct", "name": "Apertus 8B Instruct"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 65536, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -77.2166666666667, "omniscienceBreakdown": {"accuracy": 0.0965, "hallucinationRate": 0.961446227633278}, "gdpval": null, "itBenchSre": null, "tau2": 0.114035087719298, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.223809523809524, "hle": 0.0495829471733086, "gpqa": 0.255555555555556, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.125, "price1mBlended7To2To1": 0.11000000000000001, "price1mBlended0To1To1": 0.15000000000000002, "price1mBlended100To1To1": 0.10098039215686273, "price1mBlended0To100To1": 0.10099009900990098, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "fd857f01-736c-46f7-92f0-09490f4bbc8b", "slug": "swiss-ai-initiative", "name": "Swiss AI Initiative", "logo": "/img/logos/swiss-ai-initiative_small.png", "color": "#bee9fa", "country": "ch", "url": "https://www.swiss-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "89a2c945-1fab-4ee4-9f45-83a9f46cb221", "slug": "deepseek-v4-flash-0420-high", "name": "DeepSeek V4 Flash 0420 (Reasoning, High Effort)", "shortName": "DeepSeek V4 Flash (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 1240, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "deepseek-v4-flash-0420", "name": "DeepSeek V4 Flash 0420"}, "deprecated": true, "deprecatedTo": "deepseek-v4-flash", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 284, "inferenceParametersActiveBillions": 13, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash", "microevalsEnabled": false, "intelligenceIndex": 24.8441069152521, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 28.872539405126783, "strategyAndOps": 29.444848237032666, "legal": 28.64000685266935, "healthcareAndMedical": 25.785464310689452, "engineering": 26.493756099322365, "economics": 33.7776998378128}, "omniscience": -23.0833333333333, "omniscienceBreakdown": {"accuracy": 0.3486666666666667, "hallucinationRate": 0.8897134083930399}, "mlcrOverall": 0.0666666666666667, "gdpPdfAllPass": 0.104, "gdpval": 1082.61, "gdpvalNormalized": 0.2913049999999999, "itBenchSre": null, "tau2": 0.956140350877193, "tauBanking": 0.261855670103093, "terminalbenchHard": 0.386363636363636, "terminalBench21": 0.569288389513109, "terminalBench40": 0.0303030303030303, "scicode": 0.40162037037037, "lcr": 0.72, "ifbench": 0.734693877551021, "hle": 0.30259499536608, "gpqa": 0.866666666666667, "critpt": 0.0342857142857143, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.28504323745973587, "price1mInputTokens": 0.13, "price1mOutputTokens": 0.28, "cacheHitPrice": 0.028, "cacheHitDiscountPercent": 0.7910283746104642, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.1675, "price1mBlended7To2To1": 0.0736, "price1mBlended0To1To1": 0.20500000000000002, "price1mBlended100To1To1": 0.03147058823529412, "price1mBlended0To100To1": 0.1314851485148515, "intelligenceIndexCost": {"total": 210.28647022637958, "input": 174.44576434637958, "nonCacheInput": 1.9516467100000001, "cacheRead": 57.09103906844483, "cacheWrite": 115.40307856793476, "output": 35.84070588, "reasoning": 29.878364880000003, "answer": 5.962341}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.1928330659445687, "input": 0.18095989371594595, "nonCacheInput": 0.0011142689635775483, "cacheRead": 0.06118943751029925, "cacheWrite": 0.1186561872420692, "output": 0.011873172228622738, "reasoning": 0.007386004172871047, "answer": 0.00448716805575169}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.05994894733692607}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.004539925081586357}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.004445767674777841}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.11935862757460647}, {"slug": "scicode", "weightedCostPerTask": 0.00024462556597222226}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0009471401371640407}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0007017299400000002}, {"slug": "critpt", "weightedCostPerTask": 0.0019495107142857143}, {"slug": "omniscience", "weightedCostPerTask": 5.6098644250000005e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0006406932750000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2941694337, "output": 128002521, "answer": 21294075, "reasoning": 106708446}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 26378.58633168231, "answer": 16025.600199113178, "output": 42404.18653079549}, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1052.09, "lower95ci": 1041.58, "upper95ci": 1062.17}, "rubricPassRate": 0.28484848484848485, "analyticalQuality": {"elo": 1029.6, "lower95ci": 1009.31, "upper95ci": 1049.2}, "presentation": {"elo": 1062.02, "lower95ci": 1044.65, "upper95ci": 1078.75}}, "briefcaseTotalCost": 36.36902805106848, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 7, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8a24865b-90d9-4e2b-a2fd-6851c2e9d627", "slug": "deepseek-v2-5-sep-2024", "name": "DeepSeek-V2.5", "shortName": "DeepSeek-V2.5", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-06", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v2-5-sep-2024", "name": "DeepSeek-V2.5"}, "deprecated": true, "deprecatedTo": "deepseek-v3-0324", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 236, "inferenceParametersActiveBillions": 21, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "DEEPSEEK LICENSE AGREEMENT", "licenseUrl": "https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V2.5", "microevalsEnabled": false, "intelligenceIndex": 6.55308603019382, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8a4a5ead-7789-4389-8400-30e9d20370b7", "slug": "claude-4-opus-thinking", "name": "Claude 4 Opus (Reasoning)", "shortName": "Claude 4 Opus", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-22", "knowledgeCutoffDate": "2025-03-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "claude-4-opus", "name": "Claude 4 Opus"}, "deprecated": true, "deprecatedTo": "claude-4-1-opus-thinking", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 20.6446355102762, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.733918128654971, "tauBanking": null, "terminalbenchHard": 0.310606060606061, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.693333333333333, "ifbench": 0.537414965986395, "hle": 0.123262279888786, "gpqa": 0.795959595959596, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.635978835978836, "aime25": 0.733333333333333, "analystAgent": null, "price1mInputTokens": 15, "price1mOutputTokens": 75, "cacheHitPrice": 1.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 18.75, "pricePer1k1mpImages": 20.01, "price1mBlended0To3To1": 30, "price1mBlended7To2To1": 11.55, "price1mBlended0To1To1": 45, "price1mBlended100To1To1": 2.3529411764705883, "price1mBlended0To100To1": 15.594059405940595, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 2, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8a999846-4c1d-4ce7-a8b7-1310a7166fd7", "slug": "gemini-3-8-flash", "name": "Gemini 3.8 Flash (high)", "shortName": "Gemini 3.8 Flash (high)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-09-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gemini-3-8-flash", "name": "Gemini 3.8 Flash"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 41.1863571765904, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 47.14571374140816, "strategyAndOps": 48.854925682934145, "legal": 51.954006190328656, "healthcareAndMedical": 42.10718768721036, "engineering": 43.072711216494355, "economics": 52.68563677788076}, "omniscience": 29.55, "omniscienceBreakdown": {"accuracy": 0.546, "hallucinationRate": 0.551762114537445}, "mlcrOverall": 0.216666666666667, "gdpPdfAllPass": 0.21, "gdpval": 1463.81, "gdpvalNormalized": 0.481905, "itBenchSre": null, "tau2": null, "tauBanking": 0.449484536082474, "terminalbenchHard": null, "terminalBench21": 0.876404494382023, "terminalBench40": 0.196969696969697, "scicode": 0.565972222222222, "lcr": 0.813333333333333, "ifbench": null, "hle": 0.478220574606117, "gpqa": 0.952525252525253, "critpt": 0.182857142857143, "apexAgents": null, "mmmuPro": 0.85606936416185, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5993009432118243, "price1mInputTokens": 0.75, "price1mOutputTokens": 3.75, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.75, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5, "price1mBlended7To2To1": 0.5775, "price1mBlended0To1To1": 2.25, "price1mBlended100To1To1": 0.11764705882352941, "price1mBlended0To100To1": 0.7797029702970297, "intelligenceIndexTimePerTask": 194.9115179868948, "intelligenceIndexCost": {"total": 1622.7263776021543, "input": 976.8698213521543, "nonCacheInput": 15.9922905, "cacheRead": 389.25144973864946, "cacheWrite": 571.6260811135048, "output": 645.85655625, "reasoning": 509.95095375, "answer": 135.90560250000001}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.2427947606950427, "input": 0.9765351346835661, "nonCacheInput": 0.010711051472870051, "cacheRead": 0.40646943883191045, "cacheWrite": 0.5593546443787857, "output": 0.2662596260114765, "reasoning": 0.16022678342212274, "answer": 0.10603284258935376}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.40528006932406446}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.16946334455685028}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.02120972243515781}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.584150246296734}, {"slug": "scicode", "weightedCostPerTask": 0.007681339583333333}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.009198539457831325}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0108961305}, {"slug": "critpt", "weightedCostPerTask": 0.028004601428571425}, {"slug": "omniscience", "weightedCostPerTask": 0.0019698571124999995}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.004940910000000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 5973510492, "output": 172228415, "answer": 36241494, "reasoning": 135986921}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 42727.142245899406, "answer": 28275.424690494336, "output": 71002.56693639373}, "briefcaseBreakdown": {"overall": {"elo": 1201.59, "lower95ci": 1193.68, "upper95ci": 1210.26}, "rubricPassRate": 0.4212121212121212, "analyticalQuality": {"elo": 1150.86, "lower95ci": 1135.65, "upper95ci": 1167.69}, "presentation": {"elo": 1198.44, "lower95ci": 1183.21, "upper95ci": 1213.35}}, "briefcaseTotalCost": 245.86990872326578, "timescaleData": {"medianOutputSpeed": 345.090936777822, "medianTimeToFirstChunk": 30.49441437}, "outputSpeedVariance": {"p05": 230.410914858533, "q25": 285.071651068635, "median": 345.090936777822, "q75": 379.181969066287, "p95": 404.150004423221}, "timeToFirstChunkVariance": {"p05": 8.96819255095002, "q25": 12.64553870575, "median": 30.49441437, "q75": 55.4546052735, "p95": 69.5801873888499}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 301.340351567019, "medianTimeToFirstChunk": 11.856395909, "medianTimeToFirstAnswerToken": 11.856395909, "medianEndToEndResponseTime": 13.515649299393681}, "long": {"medianOutputSpeed": 345.090936777822, "medianTimeToFirstChunk": 30.49441437, "medianTimeToFirstAnswerToken": 30.49441437, "medianEndToEndResponseTime": 31.943307825935392}, "hundredK": {"medianOutputSpeed": 302.267185775931, "medianTimeToFirstChunk": 28.173137137, "medianTimeToFirstAnswerToken": 28.173137137, "medianEndToEndResponseTime": 29.827302800786764}, "mediumParallel": {"medianOutputSpeed": 312.370704794631, "medianTimeToFirstChunk": 8.00654996549997, "medianTimeToFirstAnswerToken": 8.00654996549997, "medianEndToEndResponseTime": 9.607212230960254}}, "endToEndResponseTime": {"input": 30.49441437, "reasoning": 0, "answer": 1.448893455935391, "total": 31.943307825935392}, "timeToFirstAnswerToken": {"input": 30.49441437, "reasoning": 0, "total": 30.49441437}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 4, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8afc250d-b538-45a2-812a-4605f4ffd87e", "slug": "gpt-5-6-sol-high", "name": "GPT-5.6 Sol (high)", "shortName": "GPT-5.6 Sol (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5-6-sol", "name": "GPT-5.6 Sol"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 42.4991760420519, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 46.08809445144674, "strategyAndOps": 50.86105325168724, "legal": 47.56066982972045, "healthcareAndMedical": 41.988214692120714, "engineering": 43.13487774494581, "economics": 50.02908582406548}, "omniscience": 20.3666666666667, "omniscienceBreakdown": {"accuracy": 0.5835, "hallucinationRate": 0.9119647859143657}, "mlcrOverall": 0.172222222222222, "gdpPdfAllPass": 0.278, "gdpval": 1524.01, "gdpvalNormalized": 0.512005, "itBenchSre": null, "tau2": 0.833333333333333, "tauBanking": 0.36701030927835, "terminalbenchHard": 0.621212121212121, "terminalBench21": 0.872659176029963, "terminalBench40": 0.207070707070707, "scicode": 0.577546296296296, "lcr": 0.816666666666667, "ifbench": 0.691836734693878, "hle": 0.46014828544949, "gpqa": 0.928282828282828, "critpt": 0.257142857142857, "apexAgents": null, "mmmuPro": 0.81849710982659, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5531220357393729, "price1mInputTokens": 4, "price1mOutputTokens": 20, "cacheHitPrice": 0.4, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 8, "price1mBlended7To2To1": 3.08, "price1mBlended0To1To1": 12, "price1mBlended100To1To1": 0.6274509803921569, "price1mBlended0To100To1": 4.158415841584159, "intelligenceIndexTimePerTask": 216.14926362944817, "intelligenceIndexCost": {"total": 1487.3401803889374, "input": 812.7500003889376, "nonCacheInput": 107.701712, "cacheRead": 376.50576753139677, "cacheWrite": 328.5425208575408, "output": 674.5901799999999, "reasoning": 415.30557999999996, "answer": 259.2846}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.807982690134498, "input": 0.5429831976574473, "nonCacheInput": 0.08159637705551878, "cacheRead": 0.27762926202719224, "cacheWrite": 0.18375755857473625, "output": 0.2649994924770508, "reasoning": 0.11750644120610544, "answer": 0.1474930512709453}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.3095025638505036}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.11060261502491561}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.037035218696645264}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.22248980746095803}, {"slug": "scicode", "weightedCostPerTask": 0.003528609722222223}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.008283618164967563}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.070014776}, {"slug": "critpt", "weightedCostPerTask": 0.024528845714285714}, {"slug": "omniscience", "weightedCostPerTask": 0.0027016414999999996}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.019294994000000003}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1033898351, "output": 33729509, "answer": 12964230, "reasoning": 20765279}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 5875.322060305272, "answer": 7374.652563547264, "output": 13249.974623852537}, "briefcaseBreakdown": {"overall": {"elo": 1360.88, "lower95ci": 1352.64, "upper95ci": 1369.62}, "rubricPassRate": 0.38585858585858585, "analyticalQuality": {"elo": 1367.98, "lower95ci": 1352.42, "upper95ci": 1384.61}, "presentation": {"elo": 1525.53, "lower95ci": 1508.79, "upper95ci": 1542.27}}, "briefcaseTotalCost": 187.7648887359722, "timescaleData": {"medianOutputSpeed": 61.6344474419195, "medianTimeToFirstChunk": 10.0735661570001}, "outputSpeedVariance": {"p05": 41.8286131621117, "q25": 52.9991388537538, "median": 61.6344474419195, "q75": 76.1041280499632, "p95": 92.9327830020543}, "timeToFirstChunkVariance": {"p05": 5.49429669905, "q25": 7.21434468100017, "median": 10.0735661570001, "q75": 20.2273056435, "p95": 67.7183567865499}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 69.1865181398466, "medianTimeToFirstChunk": 9.47983380449999, "medianTimeToFirstAnswerToken": 9.47983380449999, "medianEndToEndResponseTime": 16.706675296788283}, "long": {"medianOutputSpeed": 61.6344474419195, "medianTimeToFirstChunk": 10.0735661570001, "medianTimeToFirstAnswerToken": 10.0735661570001, "medianEndToEndResponseTime": 18.18591275459342}, "hundredK": {"medianOutputSpeed": 85.535039941926, "medianTimeToFirstChunk": 7.97952239299999, "medianTimeToFirstAnswerToken": 7.97952239299999, "medianEndToEndResponseTime": 13.825079960278558}, "mediumParallel": {"medianOutputSpeed": 58.5394367464698, "medianTimeToFirstChunk": 43.4526809714998, "medianTimeToFirstAnswerToken": 43.4526809714998, "medianEndToEndResponseTime": 51.99393158457736}}, "endToEndResponseTime": {"input": 10.0735661570001, "reasoning": 0, "answer": 8.112346597593321, "total": 18.18591275459342}, "timeToFirstAnswerToken": {"input": 10.0735661570001, "reasoning": 0, "total": 10.0735661570001}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8b1a70d1-e05f-426b-9122-023d4629ab47", "slug": "gpt-3-5-turbo-0613", "name": "GPT-3.5 Turbo (0613)", "shortName": "GPT-3.5 Turbo (0613)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-06-13", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-3-5-turbo-0613", "name": "GPT-3.5 Turbo (0613)"}, "deprecated": true, "deprecatedTo": "gpt-35-turbo", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 4096, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": null, "intelligenceIndexIsEstimated": false, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8c1be908-67b6-4cf4-ba08-83ddbe44fde3", "slug": "gpt-4o-2024-08-06", "name": "GPT-4o (Aug '24)", "shortName": "GPT-4o (Aug)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-08-06", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4o-2024-08-06", "name": "GPT-4o (Aug '24)"}, "deprecated": true, "deprecatedTo": "gpt-4o", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.73970909995321, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -20.8666666666667, "omniscienceBreakdown": {"accuracy": 0.237, "hallucinationRate": 0.5840978593272171}, "gdpval": null, "itBenchSre": null, "tau2": 0.289473684210526, "tauBanking": null, "terminalbenchHard": 0.0833333333333333, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.41, "ifbench": 0.359863945578231, "hle": 0.0233, "gpqa": 0.521212121212121, "critpt": 0, "apexAgents": null, "mmmuPro": 0.563005780346821, "livecodebench": 0.317460317460317, "aime25": null, "analystAgent": null, "price1mInputTokens": 2.5, "price1mOutputTokens": 10, "cacheHitPrice": 1.25, "cacheHitDiscountPercent": 0.5, "cacheWritePrice": null, "pricePer1k1mpImages": 1.9125, "price1mBlended0To3To1": 4.375, "price1mBlended7To2To1": 2.375, "price1mBlended0To1To1": 6.25, "price1mBlended100To1To1": 1.3480392156862746, "price1mBlended0To100To1": 2.5742574257425743, "timescaleData": {"medianOutputSpeed": 86.5116826705312, "medianTimeToFirstChunk": 1.30528343050008}, "outputSpeedVariance": {"p05": 37.1890785340937, "q25": 64.9047204553689, "median": 86.5116826705312, "q75": 118.417749166029, "p95": 142.157430697453}, "timeToFirstChunkVariance": {"p05": 0.864954300500011, "q25": 1.14174180250001, "median": 1.30528343050008, "q75": 2.07980342050001, "p95": 3.28341163284998}, "performanceByPromptType": {"long": {"medianOutputSpeed": 86.5116826705312, "medianTimeToFirstChunk": 1.30528343050008, "medianTimeToFirstAnswerToken": 1.30528343050008, "medianEndToEndResponseTime": 7.084849664394603}}, "endToEndResponseTime": {"input": 1.30528343050008, "reasoning": 0, "answer": 5.779566233894522, "total": 7.084849664394603}, "timeToFirstAnswerToken": {"input": 1.30528343050008, "reasoning": 0, "total": 1.30528343050008}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 3, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8c29d66d-bf98-4ea3-8572-5409353ecc66", "slug": "qwen3-6-27b", "name": "Qwen3.6 27B (Reasoning)", "shortName": "Qwen3.6 27B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-22", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 5676, "release": {"slug": "qwen3-6-27b", "name": "Qwen3.6 27B"}, "deprecated": true, "deprecatedTo": "qwen3-8-27b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 27.8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.6-27B", "microevalsEnabled": true, "intelligenceIndex": 21.9050652240782, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 22.000175710568634, "strategyAndOps": 17.703321293935804, "legal": 23.88947275473734, "engineering": 23.73551703296704, "economics": 31.99240224358975}, "omniscience": -20.0166666666667, "omniscienceBreakdown": {"accuracy": 0.196, "hallucinationRate": 0.49274461028192373}, "harveyLab": 0.822984512954118, "gdpPdfAllPass": 0.11, "gdpval": 1068.87, "gdpvalNormalized": 0.28443499999999994, "itBenchSre": null, "tau2": 0.941520467836257, "tauBanking": 0.167010309278351, "terminalbenchHard": 0.348484848484849, "terminalBench21": 0.606741573033708, "terminalBench40": 0, "scicode": 0.428240740740741, "lcr": 0.773333333333333, "ifbench": 0.675510204081633, "hle": 0.230769230769231, "gpqa": 0.842424242424242, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": 0.746242774566474, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.11045223588713587, "price1mInputTokens": 0.6, "price1mOutputTokens": 3.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.615, "price1mBlended0To3To1": 1.35, "price1mBlended7To2To1": 0.9, "price1mBlended0To1To1": 2.1, "price1mBlended100To1To1": 0.6294117647058823, "price1mBlended0To100To1": 0.6297029702970297, "intelligenceIndexTimePerTask": 491.4306156642301, "intelligenceIndexCost": {"total": 1145.3568191999998, "input": 553.1742611999999, "nonCacheInput": 12.430896, "cacheRead": 0, "cacheWrite": 540.7433652, "output": 592.182558, "reasoning": 525.1388832, "answer": 67.04367479999999}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.621236893699357, "input": 0.505002563228487, "nonCacheInput": 0.008581242937394633, "cacheRead": 0, "cacheWrite": 0.4964213202910924, "output": 0.11623433047086991, "reasoning": 0.06779504424851446, "answer": 0.04843928622235546}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.15699048032967033}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.04417119681818182}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.018941717123287672}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.35353044818181817}, {"slug": "scicode", "weightedCostPerTask": 0.0019682327083333337}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.010809603225208525}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.009027726}, {"slug": "critpt", "weightedCostPerTask": 0.017462339142857143}, {"slug": "omniscience", "weightedCostPerTask": 0.0051014111699999995}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.003233739}]}, "canonicalIntelligenceIndexTokenCount": {"input": 921957102, "output": 164495155, "answer": 18623243, "reasoning": 145871912}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 18831.956735698463, "answer": 13455.357283987629, "output": 32287.31401968609}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 812.14, "lower95ci": 805.36, "upper95ci": 819.28}, "rubricPassRate": 0.17682926829268292, "analyticalQuality": {"elo": 668.19, "lower95ci": 655.12, "upper95ci": 681.49}, "presentation": {"elo": 926.45, "lower95ci": 913.99, "upper95ci": 939.83}}, "briefcaseTotalCost": 95.2408914, "timescaleData": {"medianOutputSpeed": 59.4400125356068, "medianTimeToFirstChunk": 3.6643563}, "outputSpeedVariance": {"p05": 49.6033618829803, "q25": 54.3240822913945, "median": 59.4400125356068, "q75": 63.2746584492115, "p95": 64.7217412317032}, "timeToFirstChunkVariance": {"p05": 3.34888869805001, "q25": 3.55545695874997, "median": 3.6643563, "q75": 3.88894330025002, "p95": 4.41356656845001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 58.5046815985873, "medianTimeToFirstChunk": 1.43510917699999, "medianTimeToFirstAnswerToken": 98.45298612134793, "medianEndToEndResponseTime": 106.99931072884863}, "long": {"medianOutputSpeed": 59.4400125356068, "medianTimeToFirstChunk": 3.6643563, "medianTimeToFirstAnswerToken": 99.15558784373265, "medianEndToEndResponseTime": 107.56742994589374}, "hundredK": {"medianOutputSpeed": 61.2158412586283, "medianTimeToFirstChunk": 32.920324936, "medianTimeToFirstAnswerToken": 125.64142266656454, "medianEndToEndResponseTime": 133.80924311499342}, "mediumParallel": {"medianOutputSpeed": 53.1552514292971, "medianTimeToFirstChunk": 1.42877648649994, "medianTimeToFirstAnswerToken": 108.21032388543878, "medianEndToEndResponseTime": 117.61673221867864}}, "endToEndResponseTime": {"input": 3.6643563, "reasoning": 95.49123154373265, "answer": 8.411842102161087, "total": 107.56742994589374}, "timeToFirstAnswerToken": {"input": 3.6643563, "reasoning": 95.49123154373265, "total": 99.15558784373265}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 5, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8c748e53-61ae-48b8-af8d-eb8298b1e9db", "slug": "nemotron-3-nano-omni-30b-a3b", "name": "Nemotron 3 Nano Omni 30B A3B Reasoning", "shortName": "Nemotron 3 Nano Omni 30B A3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-29", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "nemotron-3-nano-omni-30b-a3b", "name": "Nemotron 3 Nano Omni 30B A3B Reasoning"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "NVIDIA Open Model License Agreement", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", "microevalsEnabled": false, "intelligenceIndex": 10.2506761710987, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -57.4333333333333, "omniscienceBreakdown": {"accuracy": 0.152, "hallucinationRate": 0.8565251572327044}, "gdpval": 415.52, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.453216374269006, "tauBanking": null, "terminalbenchHard": 0.0833333333333333, "terminalBench21": 0.0674157303370786, "terminalBench40": null, "scicode": null, "lcr": 0.396666666666667, "ifbench": 0.631972789115646, "hle": 0.0481927710843374, "gpqa": 0.468686868686869, "critpt": 0, "apexAgents": null, "mmmuPro": 0.531791907514451, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.09, "price1mOutputTokens": 0.36, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.1575, "price1mBlended7To2To1": 0.11699999999999999, "price1mBlended0To1To1": 0.22499999999999998, "price1mBlended100To1To1": 0.0926470588235294, "price1mBlended0To100To1": 0.09267326732673267, "openness": {"opennessIndex": 55.55555555555556, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8ca48626-ff5e-48b3-8401-38081376d706", "slug": "hy3-preview", "name": "Hy3-preview (Reasoning)", "shortName": "Hy3-preview", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-23", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "hy3-preview", "name": "Hy3-preview"}, "deprecated": true, "deprecatedTo": "hy3", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 295, "inferenceParametersActiveBillions": 21, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "TENCENT HY COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://huggingface.co/tencent/Hy3-preview/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/tencent/Hy3-preview", "microevalsEnabled": false, "intelligenceIndex": 22.7362028668659, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -35.05, "omniscienceBreakdown": {"accuracy": 0.2793333333333333, "hallucinationRate": 0.873959296947271}, "gdpval": null, "itBenchSre": null, "tau2": 0.926900584795322, "tauBanking": null, "terminalbenchHard": 0.340909090909091, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.646666666666667, "ifbench": 0.631292517006803, "hle": 0.277571825764597, "gpqa": 0.866666666666667, "critpt": 0.0457142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.063, "price1mOutputTokens": 0.21, "cacheHitPrice": 0.021, "cacheHitDiscountPercent": 0.6666666666666666, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.09975, "price1mBlended7To2To1": 0.048299999999999996, "price1mBlended0To1To1": 0.1365, "price1mBlended100To1To1": 0.023264705882352944, "price1mBlended0To100To1": 0.06445544554455446, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 5, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "a4e5bd55-a6cd-4dcf-8d4a-1d9643cd3826", "slug": "tencent", "name": "Tencent", "logo": "/img/logos/tencent_small.svg", "color": "#5CB9FF", "country": "cn", "url": "https://hunyuan.tencent.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8d0cb231-7303-452c-9923-a9620b948475", "slug": "kimi-k2-7-code", "name": "Kimi K2.7 Code", "shortName": "Kimi K2.7 Code", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2229, "release": {"slug": "kimi-k2-7-code", "name": "Kimi K2.7 Code"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1000, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Modified MIT License", "licenseUrl": "https://huggingface.co/moonshotai/Kimi-K2.7-Code/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-K2.7-Code", "microevalsEnabled": true, "intelligenceIndex": 26.2686562401836, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 29.548115109355077, "strategyAndOps": 28.77717719909764, "legal": 28.260484700543316, "healthcareAndMedical": 27.102159676993665, "engineering": 29.554830767826555, "economics": 37.07649205617804}, "omniscience": -10.2166666666667, "omniscienceBreakdown": {"accuracy": 0.39566666666666667, "hallucinationRate": 0.8237727523441809}, "mlcrOverall": 0.161111111111111, "harveyLab": 0.850195397307859, "gdpPdfAllPass": 0.112, "gdpval": 1114.49, "gdpvalNormalized": 0.307245, "itBenchSre": null, "tau2": 0.900584795321637, "tauBanking": 0.202061855670103, "terminalbenchHard": 0.446969696969697, "terminalBench21": 0.674157303370786, "terminalBench40": 0.0101010101010101, "scicode": 0.478009259259259, "lcr": 0.793333333333333, "ifbench": 0.631292517006803, "hle": 0.35032437442076, "gpqa": 0.895959595959596, "critpt": 0.1, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.24454304615216713, "enterpriseOpsGym": 0.40226797970754996, "price1mInputTokens": 0.95, "price1mOutputTokens": 4, "cacheHitPrice": 0.19, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.7125, "price1mBlended7To2To1": 0.7230000000000001, "price1mBlended0To1To1": 2.475, "price1mBlended100To1To1": 0.23480392156862745, "price1mBlended0To100To1": 0.9801980198019802, "intelligenceIndexTimePerTask": 497.70156779742996, "intelligenceIndexCost": {"total": 992.8773926143488, "input": 504.35538061434875, "nonCacheInput": 21.35261705, "cacheRead": 379.83670553391283, "cacheWrite": 103.16605803043589, "output": 488.522012, "reasoning": 427.327248, "answer": 61.194764}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.541190247118529, "input": 0.4216473517585414, "nonCacheInput": 0.015247430078990633, "cacheRead": 0.33673698525556783, "cacheWrite": 0.06966293642398294, "output": 0.11954289535998766, "reasoning": 0.07672260754245461, "answer": 0.04282028781753307}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.11824961872702697}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.039648028772206384}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.01755072843237692}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.30520150096413984}, {"slug": "scicode", "weightedCostPerTask": 0.0023826147916666666}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.010470257108433734}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0140254643}, {"slug": "critpt", "weightedCostPerTask": 0.02563038357142857}, {"slug": "omniscience", "weightedCostPerTask": 0.0031848408512499993}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.004846809600000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2130212845, "output": 122130503, "answer": 15298691, "reasoning": 106831812}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 19180.65188561365, "answer": 10705.071954383264, "output": 29885.723839996914}, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 855.7, "lower95ci": 845.97, "upper95ci": 864.44}, "rubricPassRate": 0.2070393374741201, "analyticalQuality": {"elo": 836.62, "lower95ci": 820.03, "upper95ci": 852.75}, "presentation": {"elo": 827.36, "lower95ci": 811.88, "upper95ci": 843.68}}, "briefcaseTotalCost": 71.7381020277297, "timescaleData": {"medianOutputSpeed": 58.2238421065853, "medianTimeToFirstChunk": 2.8362024805}, "outputSpeedVariance": {"p05": 38.5177070807347, "q25": 44.0910333919051, "median": 58.2238421065853, "q75": 82.5364657142933, "p95": 106.967281385038}, "timeToFirstChunkVariance": {"p05": 2.73472136764998, "q25": 2.75784010225003, "median": 2.8362024805, "q75": 3.17263300350001, "p95": 3.92449004924991}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 52.9550490123072, "medianTimeToFirstChunk": 1.15351411999996, "medianTimeToFirstAnswerToken": 43.245817716621346, "medianEndToEndResponseTime": 52.68778801644669}, "long": {"medianOutputSpeed": 58.2238421065853, "medianTimeToFirstChunk": 2.8362024805, "medianTimeToFirstAnswerToken": 41.119488491058426, "medianEndToEndResponseTime": 49.7070358240684}, "hundredK": {"medianOutputSpeed": 33.8584992762883, "medianTimeToFirstChunk": 34.673819894, "medianTimeToFirstAnswerToken": 100.50662547144648, "medianEndToEndResponseTime": 115.27396633673283}, "mediumParallel": {"medianOutputSpeed": 62.8647178737208, "medianTimeToFirstChunk": 1.16474753750001, "medianTimeToFirstAnswerToken": 36.62183818216803, "medianEndToEndResponseTime": 44.57542513700608}}, "endToEndResponseTime": {"input": 2.8362024805, "reasoning": 38.28328601055843, "answer": 8.587547333009967, "total": 49.7070358240684}, "timeToFirstAnswerToken": {"input": 2.8362024805, "reasoning": 38.28328601055843, "total": 41.119488491058426}, "performanceDataSource": {"type": "firstParty", "providerName": "Kimi"}, "hostModelCount": 9, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8ddacd41-bf43-411b-aa30-43ebf0567dd8", "slug": "gemini-1-0-pro", "name": "Gemini 1.0 Pro", "shortName": "Gemini 1.0 Pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-12-06", "knowledgeCutoffDate": "2023-04-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-1-0-pro", "name": "Gemini 1.0 Pro"}, "deprecated": true, "deprecatedTo": "gemini-2-0-pro-experimental-02-05", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 32768, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.34239163352755, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0419, "gpqa": 0.276767676767677, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.116402116402116, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8decf027-5114-4721-9ee1-81c0552980a0", "slug": "agnes-2-5-pro-alpha", "name": "Agnes 2.5 Pro Alpha", "shortName": "Agnes 2.5 Pro Alpha", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "agnes-2-5-pro-alpha", "name": "Agnes 2.5 Pro Alpha"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 397, "inferenceParametersActiveBillions": 17, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Agnes-AI/Agnes-2.5-Pro-Alpha", "microevalsEnabled": false, "intelligenceIndex": 27.797299318772, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 30.217366349509614, "strategyAndOps": 32.883994982745946, "legal": 30.019477772142345, "engineering": 29.86530520563774, "economics": 34.74353108588198}, "omniscience": -25.1, "omniscienceBreakdown": {"accuracy": 0.3348333333333333, "hallucinationRate": 0.8807316462039589}, "gdpPdfAllPass": 0.09, "gdpval": 1087.81, "gdpvalNormalized": 0.29390499999999997, "itBenchSre": null, "tau2": null, "tauBanking": 0.123711340206186, "terminalbenchHard": null, "terminalBench21": 0.670411985018727, "terminalBench40": 0.0303030303030303, "scicode": 0.429398148148148, "lcr": 0.756666666666667, "ifbench": null, "hle": 0.33595922150139, "gpqa": 0.875757575757576, "critpt": 0.108571428571429, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.3843295195770323, "price1mInputTokens": 0.45, "price1mOutputTokens": 0.9, "cacheHitPrice": 0.01, "cacheHitDiscountPercent": 0.9777777777777777, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5625, "price1mBlended7To2To1": 0.187, "price1mBlended0To1To1": 0.675, "price1mBlended100To1To1": 0.02303921568627451, "price1mBlended0To100To1": 0.4544554455445544, "intelligenceIndexTimePerTask": 416.40214972818677, "canonicalIntelligenceIndexTokenCount": {"input": 3782275112, "output": 163800947, "answer": 26791839, "reasoning": 137009108}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 56648.74792419791, "answer": 21442.26923258872, "output": 78091.01715678663}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1195.25, "lower95ci": 1186.26, "upper95ci": 1204.48}, "rubricPassRate": 0.3747474747474748, "analyticalQuality": {"elo": 1286.11, "lower95ci": 1267.25, "upper95ci": 1305.37}, "presentation": {"elo": 1143.74, "lower95ci": 1129.94, "upper95ci": 1158.79}}, "timescaleData": {"medianOutputSpeed": 187.319535024557, "medianTimeToFirstChunk": 3.87238568899997}, "outputSpeedVariance": {"p05": 114.406639271812, "q25": 155.512452221494, "median": 187.319535024557, "q75": 234.865879567762, "p95": 264.512433192817}, "timeToFirstChunkVariance": {"p05": 2.65936250975001, "q25": 2.86319926575, "median": 3.87238568899997, "q75": 4.13623638550007, "p95": 4.76781520925}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 195.189108640959, "medianTimeToFirstChunk": 2.80156380750002, "medianTimeToFirstAnswerToken": 13.048037158013157, "medianEndToEndResponseTime": 15.609655495641443}, "long": {"medianOutputSpeed": 187.319535024557, "medianTimeToFirstChunk": 3.87238568899997, "medianTimeToFirstAnswerToken": 14.549328698375934, "medianEndToEndResponseTime": 17.218564450719924}, "hundredK": {"medianOutputSpeed": 197.993260328438, "medianTimeToFirstChunk": 19.480768723, "medianTimeToFirstAnswerToken": 29.582122661423618, "medianEndToEndResponseTime": 32.10746114602952}, "mediumParallel": {"medianOutputSpeed": 164.664778616154, "medianTimeToFirstChunk": 2.8195984745, "medianTimeToFirstAnswerToken": 14.965486725819067, "medianEndToEndResponseTime": 18.001958788648835}}, "endToEndResponseTime": {"input": 3.87238568899997, "reasoning": 10.676943009375965, "answer": 2.669235752343991, "total": 17.218564450719924}, "timeToFirstAnswerToken": {"input": 3.87238568899997, "reasoning": 10.676943009375965, "total": 14.549328698375934}, "performanceDataSource": {"type": "firstParty", "providerName": "Sapiens AI"}, "hostModelCount": 1, "creator": {"id": "5db3af1a-e372-4c62-98bd-f6027eeaf990", "slug": "agnes-ai", "name": "Sapiens AI", "logo": "/img/logos/sapiens.svg", "color": "#1521a9", "country": "sg", "url": "https://agnes-ai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8df710d3-9dae-4498-9b4e-9818238e6f31", "slug": "qwen3-8-2-4t-a95b", "name": "Qwen3.8 2.4T A95B", "shortName": "Qwen3.8 2.4T A95B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-8-2-4t-a95b", "name": "Qwen3.8 2.4T A95B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 2400, "inferenceParametersActiveBillions": 95, "sizeClass": "large", "contextWindowTokens": 983616, "licenseName": "Qwen3.8-Max License", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B", "microevalsEnabled": false, "intelligenceIndex": 40.0445723105325, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 42.74927343088517, "strategyAndOps": 44.21986385012881, "legal": 41.83836589761889, "healthcareAndMedical": 36.1538802003731, "engineering": 40.44027315415508, "economics": 49.112515137472954}, "omniscience": 4.31666666666667, "omniscienceBreakdown": {"accuracy": 0.3125, "hallucinationRate": 0.39175757575757575}, "mlcrOverall": 0, "gdpPdfAllPass": 0.156, "gdpval": 1627.82, "gdpvalNormalized": 0.56391, "itBenchSre": null, "tau2": null, "tauBanking": 0.490721649484536, "terminalbenchHard": null, "terminalBench21": 0.820224719101124, "terminalBench40": 0.111111111111111, "scicode": 0.540509259259259, "lcr": 0.803333333333333, "ifbench": null, "hle": 0.424467099165894, "gpqa": 0.935353535353535, "critpt": 0.2, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.572473765458222, "enterpriseOpsGym": 0.4735899731423456, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.875, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.175, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 0.3235294117647059, "price1mBlended0To100To1": 2.0396039603960396, "intelligenceIndexTimePerTask": 1349.515479121314, "intelligenceIndexCost": {"total": 2632.046374360719, "input": 1599.2662543607187, "nonCacheInput": 34.935438, "cacheRead": 1066.5356256627545, "cacheWrite": 497.79519069796424, "output": 1032.78012, "reasoning": 856.57362, "answer": 176.2065}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.1551619442434675, "input": 1.7440718525339405, "nonCacheInput": 0.0195894498991681, "cacheRead": 1.2243770642088534, "cacheWrite": 0.5001053384259188, "output": 0.41109009170952704, "reasoning": 0.27982202191423233, "answer": 0.13126806979529473}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.6232805970696558}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.2525492153320403}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.017657223299982552}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.148883545827578}, {"slug": "scicode", "weightedCostPerTask": 0.010060797916666666}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.020156975347544025}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.018964863999999998}, {"slug": "critpt", "weightedCostPerTask": 0.04827922}, {"slug": "omniscience", "weightedCostPerTask": 0.0042277244499999995}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.011101781000000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4532507817, "output": 172130020, "answer": 29367750, "reasoning": 142762270}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 46637.003652372056, "answer": 21878.01163254913, "output": 68515.01528492119}, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1438.5, "lower95ci": 1431.62, "upper95ci": 1446}, "rubricPassRate": 0.5, "analyticalQuality": {"elo": 1611.58, "lower95ci": 1598.83, "upper95ci": 1627.11}, "presentation": {"elo": 1323.95, "lower95ci": 1310.05, "upper95ci": 1337.13}}, "briefcaseTotalCost": 378.1235622222578, "timescaleData": {"medianOutputSpeed": 40.705270580605, "medianTimeToFirstChunk": 2.729914896}, "outputSpeedVariance": {"p05": 36.5211906844838, "q25": 39.2508874156048, "median": 40.705270580605, "q75": 42.0337586289984, "p95": 44.8054795625868}, "timeToFirstChunkVariance": {"p05": 2.45236436280007, "q25": 2.53728164900008, "median": 2.729914896, "q75": 3.158946376, "p95": 3.55739891839998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 39.4538720964954, "medianTimeToFirstChunk": 1.9300949, "medianTimeToFirstAnswerToken": 52.622204285574234, "medianEndToEndResponseTime": 65.2952316319678}, "long": {"medianOutputSpeed": 40.705270580605, "medianTimeToFirstChunk": 2.729914896, "medianTimeToFirstAnswerToken": 51.8636013074336, "medianEndToEndResponseTime": 64.14702291029201}, "hundredK": {"medianOutputSpeed": 45.2469151870554, "medianTimeToFirstChunk": 14.9107035129999, "medianTimeToFirstAnswerToken": 59.11261190237395, "medianEndToEndResponseTime": 70.16308899971746}, "mediumParallel": {"medianOutputSpeed": 37.3368522504258, "medianTimeToFirstChunk": 2.03307706199991, "medianTimeToFirstAnswerToken": 55.59945664283861, "medianEndToEndResponseTime": 68.99105153804828}}, "endToEndResponseTime": {"input": 2.729914896, "reasoning": 49.1336864114336, "answer": 12.2834216028584, "total": 64.14702291029201}, "timeToFirstAnswerToken": {"input": 2.729914896, "reasoning": 49.1336864114336, "total": 51.8636013074336}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 6, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8e78cf7a-5b76-4beb-beba-b99c6233b208", "slug": "solar-pro-2-preview-reasoning", "name": "Solar Pro 2 (Preview) (Reasoning)", "shortName": "Solar Pro 2 (Preview)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "solar-pro-2-preview", "name": "Solar Pro 2 (Preview)"}, "deprecated": true, "deprecatedTo": "solar-pro-2-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 30.9, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 64000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.06998982069512, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0607043558850788, "gpqa": 0.577777777777778, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.462433862433862, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "64ff7f06-c6fb-42ea-ba24-9cd103ab2d61", "slug": "upstage", "name": "Upstage", "logo": "/img/logos/upstage_small.svg", "color": "#7c59f5", "country": "kr", "url": "https://www.upstage.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8eb02396-f231-4189-ae15-05f7facebd9b", "slug": "gpt-5-nano-medium", "name": "GPT-5 nano (medium)", "shortName": "GPT-5 nano (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-05-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-5-nano", "name": "GPT-5 nano"}, "deprecated": true, "deprecatedTo": "gpt-5-4-nano-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.4802556704436, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -25.7833333333333, "omniscienceBreakdown": {"accuracy": 0.17583333333333334, "hallucinationRate": 0.5261880687563195}, "gdpval": null, "itBenchSre": null, "tau2": 0.304093567251462, "tauBanking": null, "terminalbenchHard": 0.174242424242424, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.436666666666667, "ifbench": 0.659183673469388, "hle": 0.0871177015755329, "gpqa": 0.66969696969697, "critpt": 0, "apexAgents": null, "mmmuPro": 0.582080924855491, "livecodebench": 0.762962962962963, "aime25": 0.783333333333333, "analystAgent": null, "price1mInputTokens": 0.05, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.005, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.13, "price1mBlended0To3To1": 0.1375, "price1mBlended7To2To1": 0.053500000000000006, "price1mBlended0To1To1": 0.225, "price1mBlended100To1To1": 0.009313725490196078, "price1mBlended0To100To1": 0.05346534653465347, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 152.880716946618, "medianTimeToFirstChunk": 36.910570129}, "outputSpeedVariance": {"p05": 100.675713611975, "q25": 129.892951277697, "median": 152.880716946618, "q75": 171.115365260046, "p95": 213.72098511134}, "timeToFirstChunkVariance": {"p05": 13.45704796765, "q25": 28.13756260325, "median": 36.910570129, "q75": 51.5070442565, "p95": 72.26355096365}, "performanceByPromptType": {"long": {"medianOutputSpeed": 152.880716946618, "medianTimeToFirstChunk": 36.910570129, "medianTimeToFirstAnswerToken": 36.910570129, "medianEndToEndResponseTime": 40.18109377636481}}, "endToEndResponseTime": {"input": 36.910570129, "reasoning": 0, "answer": 3.2705236473648083, "total": 40.18109377636481}, "timeToFirstAnswerToken": {"input": 36.910570129, "reasoning": 0, "total": 36.910570129}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8f0a75d6-8d00-4c2e-bcd4-8e88a570a93c", "slug": "deepseek-coder-v2", "name": "DeepSeek-Coder-V2", "shortName": "DeepSeek-Coder-V2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-06-17", "knowledgeCutoffDate": "2023-11-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-coder-v2", "name": "DeepSeek-Coder-V2"}, "deprecated": true, "deprecatedTo": "deepseek-v2-5-sep-2024", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 236, "inferenceParametersActiveBillions": 21, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "DEEPSEEK LICENSE AGREEMENT", "licenseUrl": "https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct-0724/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct", "microevalsEnabled": false, "intelligenceIndex": 5.98428477265092, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "8f74a6ed-f82f-4a2f-a96b-4914993e47da", "slug": "olmo-3-7b-instruct", "name": "Olmo 3 7B Instruct", "shortName": "Olmo 3 7B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-20", "knowledgeCutoffDate": "2024-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "olmo-3-7b-instruct", "name": "Olmo 3 7B Instruct"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 65536, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/allenai/Olmo-3-7B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 5.24099718758815, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -77.0666666666667, "omniscienceBreakdown": {"accuracy": 0.074, "hallucinationRate": 0.912167026637869}, "gdpval": null, "itBenchSre": null, "tau2": 0.125730994152047, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.327891156462585, "hle": 0.0579240037071362, "gpqa": 0.4, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.265608465608466, "aime25": 0.413333333333333, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.125, "price1mBlended7To2To1": 0.11000000000000001, "price1mBlended0To1To1": 0.15000000000000002, "price1mBlended100To1To1": 0.10098039215686273, "price1mBlended0To100To1": 0.10099009900990098, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "ab6c5270-d7b9-4c09-92fe-62662618c631", "slug": "ai2", "name": "Allen Institute for AI", "logo": "/img/logos/ai2_small.svg", "color": "#F0529C", "country": "us", "url": "https://allenai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "901ec71b-51ec-4f53-b807-06ee17b890b4", "slug": "jt-4-1-flash-236b-a21b", "name": "JT-4.1 Flash 236B A21B", "shortName": "JT-4.1 Flash 236B A21B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "jt-4-1-flash-236b-a21b", "name": "JT-4.1 Flash 236B A21B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 236, "inferenceParametersActiveBillions": 21, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 27.2926268381758, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -8.78333333333333, "omniscienceBreakdown": {"accuracy": 0.24283333333333335, "hallucinationRate": 0.436715826546335}, "gdpval": 1193.3, "gdpvalNormalized": 0.34664999999999996, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": 0.595505617977528, "terminalBench40": null, "scicode": null, "lcr": 0.713333333333333, "ifbench": null, "hle": 0.177942539388323, "gpqa": 0.845454545454545, "critpt": 0, "apexAgents": null, "mmmuPro": 0.641040462427746, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "7e7b7290-eacc-420e-a35f-7c8eb4e5205d", "slug": "china-mobile", "name": "China Mobile", "logo": "/img/logos/china_mobile_small.png", "color": "#00b8ea", "country": "cn", "url": "https://jiutian.10086.cn/portal/common-helpcenter#/document/1181?platformCode=DMX_TYZX"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "90c2a9cf-ad7e-4332-9be2-2fd1309833e2", "slug": "grok-4-3-non-reasoning", "name": "Grok 4.3 (Non-reasoning)", "shortName": "Grok 4.3 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "grok-4-3", "name": "Grok 4.3"}, "deprecated": true, "deprecatedTo": "grok-4-6-low", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 14.5407059505055, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 16.082849227444722, "strategyAndOps": 14.187846396315996, "legal": 18.812998059551706, "engineering": 15.395828544949028, "economics": 21.16459993821439}, "omniscience": -33.0833333333333, "omniscienceBreakdown": {"accuracy": 0.23716666666666666, "hallucinationRate": 0.7445925278566746}, "gdpPdfAllPass": 0.028, "gdpval": 1030.8, "gdpvalNormalized": 0.26539999999999997, "itBenchSre": null, "tau2": 0.657894736842105, "tauBanking": 0.0804123711340206, "terminalbenchHard": 0.189393939393939, "terminalBench21": 0.340823970037453, "terminalBench40": 0, "scicode": 0.393518518518519, "lcr": 0.323333333333333, "ifbench": 0.476190476190476, "hle": 0.0676552363299351, "gpqa": 0.657575757575758, "critpt": 0, "apexAgents": null, "mmmuPro": 0.647976878612717, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.009304541594200506, "price1mInputTokens": 1.25, "price1mOutputTokens": 2.5, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.84, "cacheWritePrice": 1.25, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5625, "price1mBlended7To2To1": 0.64, "price1mBlended0To1To1": 1.875, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.2623762376237624, "intelligenceIndexTimePerTask": 89.69911245166568, "intelligenceIndexCost": {"total": 203.06038497263972, "input": 173.15000747263971, "nonCacheInput": 29.63433875, "cacheRead": 82.60093476711626, "cacheWrite": 60.91473395552345, "output": 29.9103775, "reasoning": 0, "answer": 29.9103775}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.13744224560676677, "input": 0.11463760677974545, "nonCacheInput": 0.02062010518463874, "cacheRead": 0.0564003413860089, "cacheWrite": 0.03761716020909783, "output": 0.022804638827021287, "reasoning": 0, "answer": 0.022804638827021287}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.03186952479496352}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.01674368751053886}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.005398990949746402}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.061786256430568606}, {"slug": "scicode", "weightedCostPerTask": 0.0004003246527777778}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00026157391102873034}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.014189970000000001}, {"slug": "critpt", "weightedCostPerTask": 0.0009332428571428572}, {"slug": "omniscience", "weightedCostPerTask": 4.7635124999999996e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.005811039375}]}, "canonicalIntelligenceIndexTokenCount": {"input": 485443932, "output": 11964151, "answer": 11964151, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 9121.855530808516, "output": 9121.855530808516}, "briefcaseBreakdown": {"overall": {"elo": 724.4, "lower95ci": 714.25, "upper95ci": 734.39}, "rubricPassRate": 0.1404040404040404, "analyticalQuality": {"elo": 569.24, "lower95ci": 550.04, "upper95ci": 588.23}, "presentation": {"elo": 824.1, "lower95ci": 806.55, "upper95ci": 841.07}}, "briefcaseTotalCost": 19.334178375611202, "timescaleData": {"medianOutputSpeed": 105.750362946905, "medianTimeToFirstChunk": 0.816544978999957}, "outputSpeedVariance": {"p05": 78.4505039880293, "q25": 90.3200994955167, "median": 105.750362946905, "q75": 120.519545477297, "p95": 143.723014629409}, "timeToFirstChunkVariance": {"p05": 0.647818810749925, "q25": 0.691503661750076, "median": 0.816544978999957, "q75": 0.931772863999981, "p95": 1.50510498064999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 114.845998865238, "medianTimeToFirstChunk": 0.602571313999988, "medianTimeToFirstAnswerToken": 0.602571313999988, "medianEndToEndResponseTime": 4.956227557494438}, "long": {"medianOutputSpeed": 105.750362946905, "medianTimeToFirstChunk": 0.816544978999957, "medianTimeToFirstAnswerToken": 0.816544978999957, "medianEndToEndResponseTime": 5.544661139235164}, "hundredK": {"medianOutputSpeed": 146.46292549895, "medianTimeToFirstChunk": 3.99354187649999, "medianTimeToFirstAnswerToken": 3.99354187649999, "medianEndToEndResponseTime": 7.407375092630748}, "mediumParallel": {"medianOutputSpeed": 150.894050947751, "medianTimeToFirstChunk": 1.49526027500002, "medianTimeToFirstAnswerToken": 1.49526027500002, "medianEndToEndResponseTime": 4.80884352668919}}, "endToEndResponseTime": {"input": 0.816544978999957, "reasoning": 0, "answer": 4.728116160235207, "total": 5.544661139235164}, "timeToFirstAnswerToken": {"input": 0.816544978999957, "reasoning": 0, "total": 0.816544978999957}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 2, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "90e078f2-051b-4c63-8919-76618971cb3f", "slug": "claude-4-5-sonnet-thinking", "name": "Claude 4.5 Sonnet (Reasoning)", "shortName": "Claude 4.5 Sonnet", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-29", "knowledgeCutoffDate": "2025-07-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "claude-4-5-sonnet", "name": "Claude 4.5 Sonnet"}, "deprecated": true, "deprecatedTo": "claude-sonnet-4-6-adaptive", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 21.1763943537112, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 22.68514092032753, "strategyAndOps": 20.170272612190423, "legal": 26.240273869683108, "engineering": 23.26858858417534, "economics": 31.167280545257967}, "omniscience": -0.0833333333333333, "omniscienceBreakdown": {"accuracy": 0.32866666666666666, "hallucinationRate": 0.49081429990069514}, "gdpPdfAllPass": 0.052, "gdpval": 989.26, "gdpvalNormalized": 0.24463, "itBenchSre": null, "tau2": 0.780701754385965, "tauBanking": 0.245360824742268, "terminalbenchHard": 0.356060606060606, "terminalBench21": 0.558052434456929, "terminalBench40": 0, "scicode": 0.457175925925926, "lcr": 0.723333333333333, "ifbench": 0.572789115646258, "hle": 0.177942539388323, "gpqa": 0.834343434343434, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": 0.68728323699422, "livecodebench": 0.714285714285714, "aime25": 0.88, "analystAgent": null, "automationBenchPartialScore": 0.14075743049062714, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 3.75, "pricePer1k1mpImages": 4.002, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 2.31, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 0.47058823529411764, "price1mBlended0To100To1": 3.118811881188119, "intelligenceIndexTimePerTask": 329.1559016878362, "intelligenceIndexCost": {"total": 1501.2241751592273, "input": 524.0667251592272, "nonCacheInput": 56.894691, "cacheRead": 222.54221800789327, "cacheWrite": 244.6298161513339, "output": 977.15745, "reasoning": 728.845125, "answer": 248.31232500000002}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.5565810659988739, "input": 0.30422744426017434, "nonCacheInput": 0.035462784141119426, "cacheRead": 0.13915199484248564, "cacheWrite": 0.12961266527656928, "output": 0.25235362173869974, "reasoning": 0.09880011700890562, "answer": 0.1535535047297941}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.15457794803769206}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.050829509591058114}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.03129347847839917}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.19397409450990075}, {"slug": "scicode", "weightedCostPerTask": 0.012905480208333334}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.025633145227062087}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.023334474}, {"slug": "critpt", "weightedCostPerTask": 0.04516035857142857}, {"slug": "omniscience", "weightedCostPerTask": 0.001931047875}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.016941529499999997}]}, "canonicalIntelligenceIndexTokenCount": {"input": 826006908, "output": 65143830, "answer": 16554155, "reasoning": 48589675}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 6586.674467260375, "answer": 10236.900315319608, "output": 16823.574782579984}, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 711.96, "lower95ci": 701.86, "upper95ci": 720.95}, "rubricPassRate": 0.14646464646464646, "analyticalQuality": {"elo": 598.48, "lower95ci": 580.17, "upper95ci": 615.75}, "presentation": {"elo": 748.03, "lower95ci": 730.07, "upper95ci": 765.45}}, "briefcaseTotalCost": 93.77728847619986, "timescaleData": {"medianOutputSpeed": 42.1396868018328, "medianTimeToFirstChunk": 7.72562362499991}, "outputSpeedVariance": {"p05": 33.7956098983716, "q25": 38.6966502507856, "median": 42.1396868018328, "q75": 62.7006263981808, "p95": 91.9450909918063}, "timeToFirstChunkVariance": {"p05": 4.20239286925006, "q25": 5.97018176625011, "median": 7.72562362499991, "q75": 19.7605174034998, "p95": 31.6242915656}, "performanceByPromptType": {"long": {"medianOutputSpeed": 42.1396868018328, "medianTimeToFirstChunk": 7.72562362499991, "medianTimeToFirstAnswerToken": 7.72562362499991, "medianEndToEndResponseTime": 19.590923012518218}}, "endToEndResponseTime": {"input": 7.72562362499991, "reasoning": 0, "answer": 11.865299387518306, "total": 19.590923012518218}, "timeToFirstAnswerToken": {"input": 7.72562362499991, "reasoning": 0, "total": 7.72562362499991}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "91cb6144-4937-4e4e-aeda-b4341d355c10", "slug": "claude-4-5-sonnet", "name": "Claude 4.5 Sonnet (Non-reasoning)", "shortName": "Claude 4.5 Sonnet (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-29", "knowledgeCutoffDate": "2025-07-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-4-5-sonnet", "name": "Claude 4.5 Sonnet"}, "deprecated": true, "deprecatedTo": "claude-sonnet-4-6", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 19.3436534007474, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -9.36666666666667, "omniscienceBreakdown": {"accuracy": 0.2838333333333333, "hallucinationRate": 0.5271119385617873}, "gdpval": null, "itBenchSre": null, "tau2": 0.704678362573099, "tauBanking": null, "terminalbenchHard": 0.287878787878788, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.54, "ifbench": 0.426530612244898, "hle": 0.072289156626506, "gpqa": 0.727272727272727, "critpt": 0, "apexAgents": null, "mmmuPro": 0.652023121387283, "livecodebench": 0.59047619047619, "aime25": 0.37, "analystAgent": null, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 3.75, "pricePer1k1mpImages": 4.002, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 2.31, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 0.47058823529411764, "price1mBlended0To100To1": 3.118811881188119, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 41.9554119970423, "medianTimeToFirstChunk": 1.27970314799999}, "outputSpeedVariance": {"p05": 32.8488654146028, "q25": 35.9461011064914, "median": 41.9554119970423, "q75": 57.8488891930548, "p95": 72.977651001236}, "timeToFirstChunkVariance": {"p05": 1.05305354050001, "q25": 1.19222643025, "median": 1.27970314799999, "q75": 1.37006989725006, "p95": 3.3953924473}, "performanceByPromptType": {"long": {"medianOutputSpeed": 41.9554119970423, "medianTimeToFirstChunk": 1.27970314799999, "medianTimeToFirstAnswerToken": 1.27970314799999, "medianEndToEndResponseTime": 13.197116806939823}}, "endToEndResponseTime": {"input": 1.27970314799999, "reasoning": 0, "answer": 11.917413658939832, "total": 13.197116806939823}, "timeToFirstAnswerToken": {"input": 1.27970314799999, "reasoning": 0, "total": 1.27970314799999}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "91e3b45f-3f52-4511-8c15-8948854bebc5", "slug": "granite-4-1-3b", "name": "Granite 4.1 3B", "shortName": "Granite 4.1 3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-29", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "granite-4-1-3b", "name": "Granite 4.1 3B"}, "deprecated": true, "deprecatedTo": "granite-4-2-3b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.1-3b", "microevalsEnabled": false, "intelligenceIndex": 5.86186404175178, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -77.0333333333333, "omniscienceBreakdown": {"accuracy": 0.0925, "hallucinationRate": 0.9507805325987144}, "gdpval": 73.87, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.195906432748538, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": 0.0112359550561798, "terminalBench40": null, "scicode": null, "lcr": 0.06, "ifbench": 0.336734693877551, "hle": 0.0342910101946247, "gpqa": 0.314141414141414, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 61.111111111111114, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "91f3a4c8-b000-4513-942c-bfe283375c35", "slug": "ling-2-6-flash", "name": "Ling 2.6 Flash", "shortName": "Ling 2.6 Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-21", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "ling-2-6-flash", "name": "Ling 2.6 Flash"}, "deprecated": true, "deprecatedTo": "ling-3-0-flash", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 107, "inferenceParametersActiveBillions": 7.4, "sizeClass": "medium", "contextWindowTokens": 262144, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ling-2.6-flash", "microevalsEnabled": true, "intelligenceIndex": 9.67895987024967, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -66.1333333333333, "omniscienceBreakdown": {"accuracy": 0.1555, "hallucinationRate": 0.9672389974343794}, "gdpval": 492.76, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.859649122807018, "tauBanking": 0.0288659793814433, "terminalbenchHard": 0.212121212121212, "terminalBench21": 0.243445692883895, "terminalBench40": null, "scicode": null, "lcr": 0.313333333333333, "ifbench": 0.574149659863946, "hle": 0.0625579240037071, "gpqa": 0.592929292929293, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "922c69c7-9037-43c6-8bcf-a1c555e7f3eb", "slug": "llama-4-maverick", "name": "Llama 4 Maverick", "shortName": "Llama 4 Maverick", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-05", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-4-maverick", "name": "Llama 4 Maverick"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 402, "inferenceParametersActiveBillions": 17, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "LLAMA 4 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://www.llama.com/llama4/license/", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct", "microevalsEnabled": false, "intelligenceIndex": 9.29902687437199, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 9.010940913717922, "strategyAndOps": 7.557882717106475, "legal": 11.482693890006553, "healthcareAndMedical": 9.113308725618653, "engineering": 11.289293327154773, "economics": 12.986684430027802}, "omniscience": -41.85, "omniscienceBreakdown": {"accuracy": 0.249, "hallucinationRate": 0.888814913448735}, "mlcrOverall": 0.0222222222222222, "gdpPdfAllPass": 0.008, "gdpval": -44.77, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.178362573099415, "tauBanking": 0.0371134020618557, "terminalbenchHard": 0.0681818181818182, "terminalBench21": 0.0786516853932584, "terminalBench40": 0, "scicode": 0.31712962962963, "lcr": 0.5, "ifbench": 0.429931972789116, "hle": 0.0491195551436515, "gpqa": 0.670707070707071, "critpt": 0, "apexAgents": null, "mmmuPro": 0.621387283236994, "livecodebench": 0.396825396825397, "aime25": 0.193333333333333, "analystAgent": null, "automationBenchPartialScore": 0.002121918776569101, "price1mInputTokens": 0.26, "price1mOutputTokens": 0.9099999999999999, "cacheHitPrice": 0.245, "cacheHitDiscountPercent": 0.5142857142857142, "cacheWritePrice": null, "pricePer1k1mpImages": 0.34848, "price1mBlended0To3To1": 0.4225, "price1mBlended7To2To1": 0.31449999999999995, "price1mBlended0To1To1": 0.585, "price1mBlended100To1To1": 0.2516666666666667, "price1mBlended0To100To1": 0.26643564356435645, "intelligenceIndexTimePerTask": 18.561048809400134, "intelligenceIndexCost": {"total": 45.49869532, "input": 40.83005862, "nonCacheInput": 3.0886315200000003, "cacheRead": 0, "cacheWrite": 37.7414271, "output": 4.6686366999999995, "reasoning": 0, "answer": 4.6686366999999995}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.03973597786714752, "input": 0.03787297165288413, "nonCacheInput": 0.0014265718584920634, "cacheRead": 0, "cacheWrite": 0.03644639979439206, "output": 0.001863006214263387, "reasoning": 0, "answer": 0.001863006214263387}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.02678125285714286}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.009241291504545454}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.00015949602054794523}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.0018062739696969698}, {"slug": "scicode", "weightedCostPerTask": 8.718043750000002e-05}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00010668799999999999}, {"slug": "gdp-pdf", "weightedCostPerTask": 3.6061090000000005e-05}, {"slug": "critpt", "weightedCostPerTask": 0.0002532791857142857}, {"slug": "omniscience", "weightedCostPerTask": 8.867611999999999e-06}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00125558719}]}, "canonicalIntelligenceIndexTokenCount": {"input": 157038687, "output": 5130370, "answer": 5130370, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 2047.2595761136122, "output": 2047.2595761136122}, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "rubricPassRate": 0.00909090909090909, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 16.2472934, "timescaleData": {"medianOutputSpeed": 111.007989565547, "medianTimeToFirstChunk": 0.872769938000033}, "outputSpeedVariance": {"p05": 49.5165550519132, "q25": 70.3704355509066, "median": 111.007989565547, "q75": 246.148543366891, "p95": 515.394265453589}, "timeToFirstChunkVariance": {"p05": 0.464270446899957, "q25": 0.71855153749999, "median": 0.872769938000033, "q75": 1.06997885950013, "p95": 1.82423096630002}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 112.663524661725, "medianTimeToFirstChunk": 0.588227986999982, "medianTimeToFirstAnswerToken": 0.588227986999982, "medianEndToEndResponseTime": 5.02622157455427}, "long": {"medianOutputSpeed": 111.007989565547, "medianTimeToFirstChunk": 0.872769938000033, "medianTimeToFirstAnswerToken": 0.872769938000033, "medianEndToEndResponseTime": 5.376950240308494}, "hundredK": {"medianOutputSpeed": 108.351486742132, "medianTimeToFirstChunk": 3.124371887, "medianTimeToFirstAnswerToken": 3.124371887, "medianEndToEndResponseTime": 7.738983232296633}, "mediumParallel": {"medianOutputSpeed": 78.1430423635067, "medianTimeToFirstChunk": 0.679991433499922, "medianTimeToFirstAnswerToken": 0.679991433499922, "medianEndToEndResponseTime": 7.078513744342317}}, "endToEndResponseTime": {"input": 0.872769938000033, "reasoning": 0, "answer": 4.504180302308461, "total": 5.376950240308494}, "timeToFirstAnswerToken": {"input": 0.872769938000033, "reasoning": 0, "total": 0.872769938000033}, "performanceDataSource": {"type": "median"}, "hostModelCount": 6, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "92b19c88-fa87-4595-957e-fe9aa5fa5ad4", "slug": "jamba-1-6-large", "name": "Jamba 1.6 Large", "shortName": "Jamba 1.6 Large", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-06", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "jamba-1-6-large", "name": "Jamba 1.6 Large"}, "deprecated": true, "deprecatedTo": "jamba-1-7-large", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 398, "inferenceParametersActiveBillions": 94, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Jamba Open Model License Agreement", "licenseUrl": "https://www.ai21.com/licenses/jamba-open-model-license", "modelWeightsSourceUrl": "https://huggingface.co/ai21labs/AI21-Jamba-Large-1.6", "microevalsEnabled": false, "intelligenceIndex": 5.96740520286191, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0361, "gpqa": 0.386868686868687, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.172486772486772, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "6216c686-bc60-4dbb-9f25-83e9dba803d1", "slug": "ai21-labs", "name": "AI21 Labs", "logo": "/img/logos/ai21_small.svg", "color": "#d63864", "country": "il", "url": "https://www.ai21.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "92f245a7-43b4-4ffd-8bfb-866746bf824d", "slug": "glm-5-1-non-reasoning", "name": "GLM-5.1 (Non-reasoning)", "shortName": "GLM-5.1 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-07", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "glm-5-1", "name": "GLM-5.1"}, "deprecated": true, "deprecatedTo": "glm-5-2-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 744, "inferenceParametersActiveBillions": 40, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-5.1", "microevalsEnabled": false, "intelligenceIndex": 24.2412101500726, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -22.4333333333333, "omniscienceBreakdown": {"accuracy": 0.25183333333333335, "hallucinationRate": 0.6364446424593451}, "gdpval": null, "itBenchSre": null, "tau2": 0.970760233918129, "tauBanking": null, "terminalbenchHard": 0.356060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.533333333333333, "ifbench": 0.519727891156463, "hle": 0.279425393883225, "gpqa": 0.839393939393939, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.38, "price1mOutputTokens": 4.4, "cacheHitPrice": 0.26, "cacheHitDiscountPercent": 0.8081780538302277, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2.135, "price1mBlended7To2To1": 0.898, "price1mBlended0To1To1": 2.89, "price1mBlended100To1To1": 0.3115686274509804, "price1mBlended0To100To1": 1.40990099009901, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 33.4603717987896, "medianTimeToFirstChunk": 1.97475956400012}, "outputSpeedVariance": {"p05": 19.9633944646295, "q25": 26.0288300492632, "median": 33.4603717987896, "q75": 71.4752144100651, "p95": 145.846701227893}, "timeToFirstChunkVariance": {"p05": 0.669209590599985, "q25": 1.32468611700006, "median": 1.97475956400012, "q75": 2.71441945600009, "p95": 62.0033626547995}, "performanceByPromptType": {"long": {"medianOutputSpeed": 33.4603717987896, "medianTimeToFirstChunk": 1.97475956400012, "medianTimeToFirstAnswerToken": 1.97475956400012, "medianEndToEndResponseTime": 16.917809300766258}}, "endToEndResponseTime": {"input": 1.97475956400012, "reasoning": 0, "answer": 14.943049736766136, "total": 16.917809300766258}, "timeToFirstAnswerToken": {"input": 1.97475956400012, "reasoning": 0, "total": 1.97475956400012}, "performanceDataSource": {"type": "median"}, "hostModelCount": 5, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "94229066-9381-4ee1-bf70-a16d63756a6e", "slug": "gemini-1-5-flash-8b", "name": "Gemini 1.5 Flash-8B", "shortName": "Gemini 1.5 Flash-8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-10-03", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-1-5-flash-8b", "name": "Gemini 1.5 Flash-8B"}, "deprecated": true, "deprecatedTo": "gemini-2-0-flash-lite-001", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 1048576, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.15335094096311, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0469, "gpqa": 0.358585858585859, "critpt": null, "apexAgents": null, "mmmuPro": 0.365317919075144, "livecodebench": 0.216931216931217, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "946e7aab-db1c-4c3f-b0b3-7720d0cff187", "slug": "glm-4-6", "name": "GLM-4.6 (Non-reasoning)", "shortName": "GLM-4.6 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "glm-4-6", "name": "GLM-4.6"}, "deprecated": true, "deprecatedTo": "glm-4-7-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 357, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://github.com/zai-org/GLM-4.6", "microevalsEnabled": false, "intelligenceIndex": 14.9292992892622, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -31.6833333333333, "omniscienceBreakdown": {"accuracy": 0.21416666666666667, "hallucinationRate": 0.6757158006362672}, "gdpval": null, "itBenchSre": null, "tau2": 0.769005847953216, "tauBanking": null, "terminalbenchHard": 0.287878787878788, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.263333333333333, "ifbench": 0.36734693877551, "hle": 0.0546802594995366, "gpqa": 0.632323232323232, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.560846560846561, "aime25": 0.443333333333333, "analystAgent": null, "price1mInputTokens": 0.575, "price1mOutputTokens": 2.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.98125, "price1mBlended7To2To1": 0.7374999999999999, "price1mBlended0To1To1": 1.3875000000000002, "price1mBlended100To1To1": 0.5909313725490196, "price1mBlended0To100To1": 0.5910891089108911, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 35.9593400732721, "medianTimeToFirstChunk": 4.03653749900013}, "outputSpeedVariance": {"p05": 25.0410827690634, "q25": 31.5141347574155, "median": 35.9593400732721, "q75": 41.1115762275176, "p95": 57.9882079910127}, "timeToFirstChunkVariance": {"p05": 3.44177886329992, "q25": 3.81691007325005, "median": 4.03653749900013, "q75": 4.50826468325001, "p95": 8.51662434229987}, "performanceByPromptType": {"long": {"medianOutputSpeed": 35.9593400732721, "medianTimeToFirstChunk": 4.03653749900013, "medianTimeToFirstAnswerToken": 4.03653749900013, "medianEndToEndResponseTime": 17.941130825273117}}, "endToEndResponseTime": {"input": 4.03653749900013, "reasoning": 0, "answer": 13.904593326272986, "total": 17.941130825273117}, "timeToFirstAnswerToken": {"input": 4.03653749900013, "reasoning": 0, "total": 4.03653749900013}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "948892b5-db03-4118-a4a8-ccd51ed871ea", "slug": "grok-4-3", "name": "Grok 4.3 (high)", "shortName": "Grok 4.3 (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "grok-4-3", "name": "Grok 4.3"}, "deprecated": true, "deprecatedTo": "grok-4-5", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 25.3911441398002, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 27.768681841654555, "strategyAndOps": 17.69534429992964, "legal": 32.895837707779535, "healthcareAndMedical": 26.823799045945965, "engineering": 31.215524131488188, "economics": 41.3416329935125}, "omniscience": 17.9833333333333, "omniscienceBreakdown": {"accuracy": 0.3478333333333333, "hallucinationRate": 0.25760286225402507}, "mlcrOverall": 0.1, "harveyLab": 0.683890577507599, "gdpPdfAllPass": 0.058, "gdpval": 1018.49, "gdpvalNormalized": 0.259245, "itBenchSre": 0.327212806026365, "tau2": 0.976608187134503, "tauBanking": 0.123711340206186, "terminalbenchHard": 0.378787878787879, "terminalBench21": 0.397003745318352, "terminalBench40": 0, "scicode": 0.482638888888889, "lcr": 0.73, "ifbench": 0.812925170068027, "hle": 0.372103799814643, "gpqa": 0.901010101010101, "critpt": 0.08, "apexAgents": 0.170353982300885, "mmmuPro": 0.78092485549133, "livecodebench": null, "aime25": null, "analystAgent": 0.0875, "automationBenchPartialScore": 0.01375964614032744, "enterpriseOpsGym": 0.26260817666368247, "price1mInputTokens": 1.25, "price1mOutputTokens": 2.5, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.84, "cacheWritePrice": 1.25, "pricePer1k1mpImages": 1.28, "price1mBlended0To3To1": 1.5625, "price1mBlended7To2To1": 0.64, "price1mBlended0To1To1": 1.875, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.2623762376237624, "intelligenceIndexTimePerTask": 143.835228387637, "intelligenceIndexCost": {"total": 332.0039523595581, "input": 114.44814485955811, "nonCacheInput": 18.71370125, "cacheRead": 54.5439009791318, "cacheWrite": 41.19054263042631, "output": 217.55580750000001, "reasoning": 199.0361675, "answer": 18.51964}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.16529989544512777, "input": 0.12107489787048084, "nonCacheInput": 0.01093331430885033, "cacheRead": 0.06997531467482002, "cacheWrite": 0.040166268886810505, "output": 0.044224997574646895, "reasoning": 0.0283684421048914, "answer": 0.015856555469755507}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.035614378985215106}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.009755735936484553}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.00185474849043405}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.08549016712215884}, {"slug": "scicode", "weightedCostPerTask": 0.0013015503472222222}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.006173189237720111}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00503914625}, {"slug": "critpt", "weightedCostPerTask": 0.012743042857142855}, {"slug": "omniscience", "weightedCostPerTask": 0.00111998246875}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.006207953750000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 320642900, "output": 87022323, "answer": 7407856, "reasoning": 79614467}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 11347.37684195656, "answer": 6342.622187902203, "output": 17689.999029858765}, "briefcaseBreakdown": {"overall": {"elo": 761.59, "lower95ci": 754.26, "upper95ci": 768.84}, "rubricPassRate": 0.17272727272727273, "analyticalQuality": {"elo": 620.98, "lower95ci": 608.11, "upper95ci": 633.54}, "presentation": {"elo": 832.05, "lower95ci": 819.43, "upper95ci": 844.06}}, "briefcaseTotalCost": 21.60605658436383, "timescaleData": {"medianOutputSpeed": 125.503435706361, "medianTimeToFirstChunk": 20.574804376}, "outputSpeedVariance": {"p05": 89.5767020367318, "q25": 105.738699816614, "median": 125.503435706361, "q75": 144.838491873197, "p95": 170.420069515159}, "timeToFirstChunkVariance": {"p05": 5.54809572544997, "q25": 13.8734218085, "median": 20.574804376, "q75": 27.8609676234999, "p95": 66.8392393958999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 125.503435706361, "medianTimeToFirstChunk": 20.574804376, "medianTimeToFirstAnswerToken": 20.574804376, "medianEndToEndResponseTime": 24.558759055693745}}, "endToEndResponseTime": {"input": 20.574804376, "reasoning": 0, "answer": 3.983954679693745, "total": 24.558759055693745}, "timeToFirstAnswerToken": {"input": 20.574804376, "reasoning": 0, "total": 20.574804376}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 3, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "94a6d26e-a903-47f3-8323-ae422d237bb9", "slug": "olmo-3-1-32b-instruct", "name": "Olmo 3.1 32B Instruct", "shortName": "Olmo 3.1 32B Instruct", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-13", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "olmo-3-1-32b-instruct", "name": "Olmo 3.1 32B Instruct"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32.2, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 65536, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/allenai/Olmo-3.1-32B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 6.49671923993574, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -52.3666666666667, "omniscienceBreakdown": {"accuracy": 0.1205, "hallucinationRate": 0.7324237256016676}, "gdpval": null, "itBenchSre": null, "tau2": 0.213450292397661, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.391836734693878, "hle": 0.0500463392029657, "gpqa": 0.539393939393939, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "ab6c5270-d7b9-4c09-92fe-62662618c631", "slug": "ai2", "name": "Allen Institute for AI", "logo": "/img/logos/ai2_small.svg", "color": "#F0529C", "country": "us", "url": "https://allenai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "94d09368-9035-47cf-963a-b4310b433a16", "slug": "mimo-v2-omni", "name": "MiMo-V2-Omni", "shortName": "MiMo-V2-Omni", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "mimo-v2-omni", "name": "MiMo-V2-Omni"}, "deprecated": true, "deprecatedTo": "mimo-v2-omni-0327", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 23.9174211586356, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -20.1333333333333, "omniscienceBreakdown": {"accuracy": 0.193, "hallucinationRate": 0.4886410574142916}, "gdpval": null, "itBenchSre": null, "tau2": 0.912280701754386, "tauBanking": null, "terminalbenchHard": 0.348484848484849, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.75, "ifbench": 0.535374149659864, "hle": 0.221037998146432, "gpqa": 0.828282828282828, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": 0.698843930635838, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5147c8b4-61d5-4070-9324-8adf8aa144c2", "slug": "xiaomi", "name": "Xiaomi", "logo": "/img/logos/xiaomi_small.svg", "color": "#ff6900", "country": "cn", "url": "https://huggingface.co/XiaomiMiMo"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9741f3c2-cbb1-4a3f-99ee-7bd7384d9038", "slug": "ministral-3-8b", "name": "Ministral 3 8B", "shortName": "Ministral 3 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "ministral-3-8b", "name": "Ministral 3 8B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512", "microevalsEnabled": false, "intelligenceIndex": 5.47767370454416, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 5.236370781504772, "strategyAndOps": 4.091333929012995, "legal": 5.8765955491197825, "engineering": 6.659481000926786, "economics": 8.060455668829166}, "omniscience": -68.95, "omniscienceBreakdown": {"accuracy": 0.12983333333333333, "hallucinationRate": 0.9415820723999234}, "gdpPdfAllPass": 0.008, "gdpval": 404.6, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.266081871345029, "tauBanking": 0.0371134020618557, "terminalbenchHard": 0.0454545454545455, "terminalBench21": 0.0411985018726592, "terminalBench40": 0, "scicode": 0.207175925925926, "lcr": 0.256666666666667, "ifbench": 0.291156462585034, "hle": 0.0426320667284523, "gpqa": 0.470707070707071, "critpt": 0, "apexAgents": null, "mmmuPro": 0.459537572254335, "livecodebench": 0.302645502645503, "aime25": 0.316666666666667, "analystAgent": null, "automationBenchPartialScore": 0.00516749466666553, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.15, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15, "price1mBlended7To2To1": 0.15, "price1mBlended0To1To1": 0.15, "price1mBlended100To1To1": 0.15, "price1mBlended0To100To1": 0.15, "intelligenceIndexTimePerTask": 85.44057064388394, "intelligenceIndexCost": {"total": 168.95317035, "input": 166.013859, "nonCacheInput": 2.6803987499999997, "cacheRead": 0, "cacheWrite": 163.33346025, "output": 2.93931135, "reasoning": 0, "answer": 2.93931135}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.0655161894090132, "input": 0.06433174614321861, "nonCacheInput": 0.0017216395831816276, "cacheRead": 0, "cacheWrite": 0.06261010656003699, "output": 0.0011844432657945863, "reasoning": 0, "answer": 0.0011844432657945863}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.01676976997252747}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.006882210681818181}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.009069593664383561}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.030872694999999995}, {"slug": "scicode", "weightedCostPerTask": 5.732484375e-05}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 6.174596385542169e-05}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0008372458500000001}, {"slug": "critpt", "weightedCostPerTask": 0.0002506615714285714}, {"slug": "omniscience", "weightedCostPerTask": 3.89581125e-06}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00071104605}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1106759060, "output": 19595409, "answer": 19595409, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 7896.288438630577, "output": 7896.288438630577}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 99.22, "lower95ci": 88.49, "upper95ci": 108.83}, "rubricPassRate": 0.04564315352697095, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 3.55, "lower95ci": 0, "upper95ci": 23.52}}, "briefcaseTotalCost": 10.173660449999998, "timescaleData": {"medianOutputSpeed": 90.8976421083491, "medianTimeToFirstChunk": 0.753708093499995}, "outputSpeedVariance": {"p05": 43.8880097753301, "q25": 74.0083168626301, "median": 90.8976421083491, "q75": 105.990903964677, "p95": 126.459287955173}, "timeToFirstChunkVariance": {"p05": 0.669464078850075, "q25": 0.722469211500282, "median": 0.753708093499995, "q75": 0.800243562750026, "p95": 0.891037541599971}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 89.1025556541203, "medianTimeToFirstChunk": 0.536183370000003, "medianTimeToFirstAnswerToken": 0.536183370000003, "medianEndToEndResponseTime": 6.147694693433956}, "long": {"medianOutputSpeed": 90.8976421083491, "medianTimeToFirstChunk": 0.753708093499995, "medianTimeToFirstAnswerToken": 0.753708093499995, "medianEndToEndResponseTime": 6.254400833186299}, "hundredK": {"medianOutputSpeed": 79.9240661044194, "medianTimeToFirstChunk": 7.35703272300001, "medianTimeToFirstAnswerToken": 7.35703272300001, "medianEndToEndResponseTime": 13.61297069475884}, "mediumParallel": {"medianOutputSpeed": 77.4200623481437, "medianTimeToFirstChunk": 0.517972970000073, "medianTimeToFirstAnswerToken": 0.517972970000073, "medianEndToEndResponseTime": 6.9762472833375195}}, "endToEndResponseTime": {"input": 0.753708093499995, "reasoning": 0, "answer": 5.500692739686304, "total": 6.254400833186299}, "timeToFirstAnswerToken": {"input": 0.753708093499995, "reasoning": 0, "total": 0.753708093499995}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 2, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "976cc8ad-7904-4056-83c5-960181f47d5f", "slug": "llama-3-3-instruct-70b", "name": "Llama 3.3 Instruct 70B", "shortName": "Llama 3.3 70B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-06", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-3-instruct-70b", "name": "Llama 3.3 Instruct 70B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.3 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 7.66380859299009, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.1666666666667, "omniscienceBreakdown": {"accuracy": 0.1895, "hallucinationRate": 0.9021180341353074}, "gdpval": 49.51, "gdpvalNormalized": 0, "itBenchSre": 0.00564971751412429, "tau2": 0.266081871345029, "tauBanking": null, "terminalbenchHard": 0.0303030303030303, "terminalBench21": 0.048689138576779, "terminalBench40": null, "scicode": null, "lcr": 0.156666666666667, "ifbench": 0.470748299319728, "hle": 0.0356, "gpqa": 0.497979797979798, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.287830687830688, "aime25": 0.0766666666666667, "analystAgent": null, "price1mInputTokens": 0.71, "price1mOutputTokens": 0.72, "cacheHitPrice": 0.71, "cacheHitDiscountPercent": 0.5, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.7124999999999999, "price1mBlended7To2To1": 0.711, "price1mBlended0To1To1": 0.715, "price1mBlended100To1To1": 0.7100980392156861, "price1mBlended0To100To1": 0.7100990099009901, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 87.0238250592725, "medianTimeToFirstChunk": 1.62626690699994}, "outputSpeedVariance": {"p05": 16.8771589650272, "q25": 53.8578756513351, "median": 87.0238250592725, "q75": 150.663684543572, "p95": 327.603699930682}, "timeToFirstChunkVariance": {"p05": 0.653770147600028, "q25": 1.06710567499999, "median": 1.62626690699994, "q75": 2.22484230199996, "p95": 3.14699339239996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 99.8871427894985, "medianTimeToFirstChunk": 0.604863025999975, "medianTimeToFirstAnswerToken": 0.604863025999975, "medianEndToEndResponseTime": 5.610512262095321}, "long": {"medianOutputSpeed": 87.0238250592725, "medianTimeToFirstChunk": 1.62626690699994, "medianTimeToFirstAnswerToken": 1.62626690699994, "medianEndToEndResponseTime": 7.371819916873348}, "hundredK": {"medianOutputSpeed": 70.5027296547553, "medianTimeToFirstChunk": 8.78483417400003, "medianTimeToFirstAnswerToken": 8.78483417400003, "medianEndToEndResponseTime": 15.876758166850365}, "mediumParallel": {"medianOutputSpeed": 87.2144036847661, "medianTimeToFirstChunk": 0.795656481999949, "medianTimeToFirstAnswerToken": 0.795656481999949, "medianEndToEndResponseTime": 6.528654460260917}}, "endToEndResponseTime": {"input": 1.62626690699994, "reasoning": 0, "answer": 5.745553009873408, "total": 7.371819916873348}, "timeToFirstAnswerToken": {"input": 1.62626690699994, "reasoning": 0, "total": 1.62626690699994}, "performanceDataSource": {"type": "median"}, "hostModelCount": 13, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9815da7d-70f4-44d6-b539-9ffef0faa152", "slug": "nemotron-cascade-2-30b-a3b", "name": "Nemotron Cascade 2 30B A3B", "shortName": "Nemotron Cascade 2 30B A3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "nemotron-cascade-2-30b-a3b", "name": "Nemotron Cascade 2 30B A3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 31.6, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 1000000, "licenseName": "Nvidia Open Model License", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B", "microevalsEnabled": false, "intelligenceIndex": 11.6708359406601, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -51.4666666666667, "omniscienceBreakdown": {"accuracy": 0.18283333333333332, "hallucinationRate": 0.8535590454823577}, "gdpval": 447.27, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.532163742690059, "tauBanking": null, "terminalbenchHard": 0.212121212121212, "terminalBench21": 0.205992509363296, "terminalBench40": null, "scicode": null, "lcr": 0.393333333333333, "ifbench": 0.804081632653061, "hle": 0.120018535681186, "gpqa": 0.757575757575758, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 83.33333333333333, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "98e3230e-cee1-4c19-b9f8-b6b6a826ca93", "slug": "r1-1776", "name": "R1 1776", "shortName": "R1 1776", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-18", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "r1-1776", "name": "R1 1776"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 671, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/perplexity-ai/r1-1776", "microevalsEnabled": false, "intelligenceIndex": 6.43857605749744, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "941fc0f0-1d4e-405a-95b2-2d49494e0e6c", "slug": "perplexity", "name": "Perplexity", "logo": "/img/logos/perplexity.svg", "color": "#1B818E", "country": "us", "url": "https://perplexity.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "992b7b84-5069-4c6a-9295-834252553d50", "slug": "claude-opus-4-8", "name": "Claude Opus 4.8 (Adaptive Reasoning, Max Effort)", "shortName": "Claude Opus 4.8 (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "claude-opus-4-8", "name": "Claude Opus 4.8"}, "deprecated": true, "deprecatedTo": "claude-opus-5", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 41.9915603794639, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 46.29446205781388, "strategyAndOps": 44.436091193620555, "legal": 48.203039617006624, "healthcareAndMedical": 45.46476368177141, "engineering": 43.695507639232346, "economics": 54.034177923231375}, "omniscience": 28.75, "omniscienceBreakdown": {"accuracy": 0.48833333333333334, "hallucinationRate": 0.3925081433224756}, "mlcrOverall": 0.455555555555556, "harveyLab": 0.910840932117528, "gdpPdfAllPass": 0.228, "gdpval": 1489.04, "gdpvalNormalized": 0.49451999999999996, "itBenchSre": null, "tau2": 0.944444444444445, "tauBanking": 0.342268041237113, "terminalbenchHard": 0.583333333333333, "terminalBench21": 0.846441947565543, "terminalBench40": 0.217171717171717, "scicode": 0.543981481481482, "lcr": 0.776666666666667, "ifbench": 0.622448979591837, "hle": 0.486561631139944, "gpqa": 0.92020202020202, "critpt": 0.208571428571429, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.45, "automationBenchPartialScore": 0.45593436915277186, "enterpriseOpsGym": 0.4395702775290958, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "intelligenceIndexTimePerTask": 757.9001852196038, "intelligenceIndexCost": {"total": 6873.860602077013, "input": 2559.929177077013, "nonCacheInput": 175.09228000000002, "cacheRead": 1479.7600660150424, "cacheWrite": 905.0768310619704, "output": 4313.931425, "reasoning": 3584.8332, "answer": 729.098225}, "intelligenceIndexCostPerTask": {"cost": {"total": 4.080976976477826, "input": 2.317233666277887, "nonCacheInput": 0.12778395824797176, "cacheRead": 1.6049659738553066, "cacheWrite": 0.584483734174609, "output": 1.7637433101999382, "reasoning": 1.2953833612051697, "answer": 0.46835994899476846}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 1.2393038197356467}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.43409278872438173}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.12409415780437612}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.814795812162998}, {"slug": "scicode", "weightedCostPerTask": 0.02664386111111111}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.08230423517145503}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.12242256000000001}, {"slug": "critpt", "weightedCostPerTask": 0.19372910714285715}, {"slug": "omniscience", "weightedCostPerTask": 0.0036993621249999994}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0398912725}]}, "canonicalIntelligenceIndexTokenCount": {"input": 3139350881, "output": 172557257, "answer": 29163929, "reasoning": 143393328}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 51815.3344482068, "answer": 18734.397959790735, "output": 70549.73240799754}, "briefcaseBreakdown": {"overall": {"elo": 1315.95, "lower95ci": 1310.01, "upper95ci": 1321.63}, "rubricPassRate": 0.38686868686868686, "analyticalQuality": {"elo": 1298.18, "lower95ci": 1286.59, "upper95ci": 1309.87}, "presentation": {"elo": 1457.9, "lower95ci": 1447.3, "upper95ci": 1469.13}}, "briefcaseTotalCost": 751.8443173062924, "timescaleData": {"medianOutputSpeed": 58.651459342263, "medianTimeToFirstChunk": 16.4111844139998}, "outputSpeedVariance": {"p05": 38.9736704173416, "q25": 43.7785935269835, "median": 58.651459342263, "q75": 67.2545686652769, "p95": 74.6105535369019}, "timeToFirstChunkVariance": {"p05": 4.93475691750001, "q25": 6.31164856150007, "median": 16.4111844139998, "q75": 63.22239062625, "p95": 81.3795030808498}, "performanceByPromptType": {"long": {"medianOutputSpeed": 58.651459342263, "medianTimeToFirstChunk": 16.4111844139998, "medianTimeToFirstAnswerToken": 16.4111844139998, "medianEndToEndResponseTime": 24.936121484742223}}, "endToEndResponseTime": {"input": 16.4111844139998, "reasoning": 0, "answer": 8.524937070742425, "total": 24.936121484742223}, "timeToFirstAnswerToken": {"input": 16.4111844139998, "reasoning": 0, "total": 16.4111844139998}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 7, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9999672c-b687-4026-9c15-5cef02ff53bb", "slug": "muse-spark-1-3", "name": "Muse Spark 1.3 (max)", "shortName": "Muse Spark 1.3 (max)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-09-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "muse-spark-1-3", "name": "Muse Spark 1.3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 48.1690107719685, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 49.90581072856371, "strategyAndOps": 51.37931664047627, "legal": 51.073010906155034, "healthcareAndMedical": 49.4827310967774, "engineering": 49.47654677611546, "economics": 56.40162581093606}, "omniscience": 25, "omniscienceBreakdown": {"accuracy": 0.43583333333333335, "hallucinationRate": 0.3293943870014771}, "mlcrOverall": 0.411111111111111, "gdpPdfAllPass": 0.266, "gdpval": 1703.34, "gdpvalNormalized": 0.6016699999999999, "itBenchSre": null, "tau2": null, "tauBanking": 0.505154639175258, "terminalbenchHard": null, "terminalBench21": 0.842696629213483, "terminalBench40": 0.333333333333333, "scicode": 0.587962962962963, "lcr": 0.83, "ifbench": null, "hle": 0.487025023169602, "gpqa": 0.935353535353535, "critpt": 0.248571428571429, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5785343786538614, "price1mInputTokens": 1.25, "price1mOutputTokens": 4.25, "cacheHitPrice": 0.15, "cacheHitDiscountPercent": 0.88, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2, "price1mBlended7To2To1": 0.78, "price1mBlended0To1To1": 2.75, "price1mBlended100To1To1": 0.20098039215686275, "price1mBlended0To100To1": 1.2797029702970297, "intelligenceIndexTimePerTask": 236.54398276518742, "intelligenceIndexCost": {"total": 2000.3526584050005, "input": 1286.5236401550005, "nonCacheInput": 30.506425, "cacheRead": 768.9592325924999, "cacheWrite": 487.05798256250057, "output": 713.82901825, "reasoning": 571.3928565, "answer": 142.43616175000002}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.6048932100125866, "input": 1.3490425400961017, "nonCacheInput": 0.022484332141925304, "cacheRead": 0.8431508870964701, "cacheWrite": 0.4834073208577061, "output": 0.25585066991648475, "reasoning": 0.14503519838306006, "answer": 0.11081547153342473}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.6088525254560442}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.2039024888704546}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.018171071731354644}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.6938794507272731}, {"slug": "scicode", "weightedCostPerTask": 0.003927459895833333}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.013014089156626506}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.020510461}, {"slug": "critpt", "weightedCostPerTask": 0.032566309999999994}, {"slug": "omniscience", "weightedCostPerTask": 0.00342283205}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.006646521125000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 5540446410, "output": 167959769, "answer": 33514391, "reasoning": 134445378}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 34125.929031308246, "answer": 26074.228596099943, "output": 60200.15762740819}, "briefcaseBreakdown": {"overall": {"elo": 1589.18, "lower95ci": 1578.27, "upper95ci": 1600.32}, "rubricPassRate": 0.5868686868686869, "analyticalQuality": {"elo": 1725.44, "lower95ci": 1705.53, "upper95ci": 1743.72}, "presentation": {"elo": 1518.64, "lower95ci": 1499.29, "upper95ci": 1537.42}}, "briefcaseTotalCost": 369.37053211000017, "timescaleData": {"medianOutputSpeed": 255.179125253414, "medianTimeToFirstChunk": 27.0136551229999}, "outputSpeedVariance": {"p05": 154.940531931807, "q25": 180.132433000667, "median": 255.179125253414, "q75": 303.987323277615, "p95": 346.463775145387}, "timeToFirstChunkVariance": {"p05": 9.66318749705002, "q25": 17.312986059, "median": 27.0136551229999, "q75": 53.00757872375, "p95": 66.65233996015}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 250.506803273855, "medianTimeToFirstChunk": 23.9837828295, "medianTimeToFirstAnswerToken": 31.967597934966786, "medianEndToEndResponseTime": 33.96355171133348}, "long": {"medianOutputSpeed": 255.179125253414, "medianTimeToFirstChunk": 27.0136551229999, "medianTimeToFirstAnswerToken": 34.85128681804484, "medianEndToEndResponseTime": 36.810694741806074}, "hundredK": {"medianOutputSpeed": 225.851088393934, "medianTimeToFirstChunk": 29.512418231005, "medianTimeToFirstAnswerToken": 38.36781057922145, "medianEndToEndResponseTime": 40.58165866627556}, "mediumParallel": {"medianOutputSpeed": 227.382713799335, "medianTimeToFirstChunk": 24.1116107574999, "medianTimeToFirstAnswerToken": 32.907354139140594, "medianEndToEndResponseTime": 35.10628998455076}}, "endToEndResponseTime": {"input": 27.0136551229999, "reasoning": 7.837631695044939, "answer": 1.9594079237612347, "total": 36.810694741806074}, "timeToFirstAnswerToken": {"input": 27.0136551229999, "reasoning": 7.837631695044939, "total": 34.85128681804484}, "performanceDataSource": {"type": "firstParty", "providerName": "Meta"}, "hostModelCount": 1, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "99f376bf-cbcb-4124-bf3e-6b0a4e6e9bea", "slug": "claude-sonnet-5-xhigh", "name": "Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)", "shortName": "Claude Sonnet 5 (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "claude-sonnet-5", "name": "Claude Sonnet 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 34.707236557212, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 37.82991034876844, "strategyAndOps": 37.29763226176343, "legal": 38.51728431034728, "engineering": 35.76343310946083, "economics": 45.59312144732778}, "omniscience": 3.18333333333333, "omniscienceBreakdown": {"accuracy": 0.38966666666666666, "hallucinationRate": 0.5862916439104314}, "gdpPdfAllPass": 0.126, "gdpval": 1400.77, "gdpvalNormalized": 0.450385, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": 0.0707070707070707, "scicode": 0.540509259259259, "lcr": 0.766666666666667, "ifbench": null, "hle": 0.39017608897127, "gpqa": null, "critpt": 0.154285714285714, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.3447626889062095, "enterpriseOpsGym": 0.4386750223813787, "price1mInputTokens": 2, "price1mOutputTokens": 10, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": 4.116, "price1mBlended0To3To1": 4, "price1mBlended7To2To1": 1.54, "price1mBlended0To1To1": 6, "price1mBlended100To1To1": 0.3137254901960784, "price1mBlended0To100To1": 2.0792079207920793, "intelligenceIndexTimePerTask": 594.1739810140434, "intelligenceIndexCost": {"total": 3255.3967056548126, "input": 1908.034735654813, "nonCacheInput": 70.674486, "cacheRead": 1359.5916774213208, "cacheWrite": 477.76857223349197, "output": 1347.36197, "reasoning": 1045.72556, "answer": 301.63640999999996}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.8720437784323134, "input": 2.218475391829822, "nonCacheInput": 0.05148562254903644, "cacheRead": 1.725491207000738, "cacheWrite": 0.4414985622800483, "output": 0.6535683866024908, "reasoning": 0.4395872513700623, "answer": 0.21398113523242845}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 1.133573708641814}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.21418641688175882}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.03577381346172653}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.2798872430078123}, {"slug": "scicode", "weightedCostPerTask": 0.003986681944444445}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.027194436051899903}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.044525424}, {"slug": "critpt", "weightedCostPerTask": 0.11647595714285713}, {"slug": "omniscience", "weightedCostPerTask": 0.0006425093}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.015797588}]}, "canonicalIntelligenceIndexTokenCount": {"input": 7024403059, "output": 134736197, "answer": 30163641, "reasoning": 104572556}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 43958.72513700623, "answer": 21398.113523242846, "output": 65356.83866024908}, "briefcaseBreakdown": {"overall": {"elo": 1273.41, "lower95ci": 1267.53, "upper95ci": 1279.61}, "rubricPassRate": 0.4, "analyticalQuality": {"elo": 1318.31, "lower95ci": 1306.12, "upper95ci": 1329.56}, "presentation": {"elo": 1291.09, "lower95ci": 1280.27, "upper95ci": 1302.74}}, "briefcaseTotalCost": 687.7013832427006, "timescaleData": {"medianOutputSpeed": 67.0011950985985, "medianTimeToFirstChunk": 30.1874456109999}, "outputSpeedVariance": {"p05": 49.3461780979719, "q25": 54.0037766248089, "median": 67.0011950985985, "q75": 92.5339032232237, "p95": 105.659315994721}, "timeToFirstChunkVariance": {"p05": 1.3537371849, "q25": 14.6497885185, "median": 30.1874456109999, "q75": 64.7743170365, "p95": 217.8985576276}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 73.6468761814486, "medianTimeToFirstChunk": 24.25460521, "medianTimeToFirstAnswerToken": 24.25460521, "medianEndToEndResponseTime": 31.04375942705216}, "long": {"medianOutputSpeed": 67.0011950985985, "medianTimeToFirstChunk": 30.1874456109999, "medianTimeToFirstAnswerToken": 30.1874456109999, "medianEndToEndResponseTime": 37.64999906641519}, "hundredK": {"medianOutputSpeed": 78.2745016509286, "medianTimeToFirstChunk": 12.7155225145, "medianTimeToFirstAnswerToken": 12.7155225145, "medianEndToEndResponseTime": 19.10329873094645}, "mediumParallel": {"medianOutputSpeed": 72.8030978383432, "medianTimeToFirstChunk": 20.8939888945, "medianTimeToFirstAnswerToken": 20.8939888945, "medianEndToEndResponseTime": 27.761828517344526}}, "endToEndResponseTime": {"input": 30.1874456109999, "reasoning": 0, "answer": 7.462553455415287, "total": 37.64999906641519}, "timeToFirstAnswerToken": {"input": 30.1874456109999, "reasoning": 0, "total": 30.1874456109999}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9ac3908c-9eb2-44db-8c01-3ec7da6fc2ae", "slug": "qwen3-8-flash-next", "name": "Qwen3.8-Flash-Next", "shortName": "Qwen3.8-Flash-Next", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-26", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-8-flash-next", "name": "Qwen3.8-Flash-Next"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 180, "inferenceParametersActiveBillions": 6, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Qwen Community License 1.0", "licenseUrl": null, "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.8-Flash-Next", "microevalsEnabled": false, "intelligenceIndex": 39.9140521864741, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 41.087538626922445, "strategyAndOps": 44.628858027933376, "legal": 38.985596934004114, "engineering": 39.58898020453443, "economics": 47.16640330552982}, "omniscience": -9.71666666666667, "omniscienceBreakdown": {"accuracy": 0.245, "hallucinationRate": 0.4532008830022075}, "gdpPdfAllPass": 0.156, "gdpval": 1647.02, "gdpvalNormalized": 0.57351, "itBenchSre": null, "tau2": null, "tauBanking": 0.45360824742268, "terminalbenchHard": null, "terminalBench21": 0.861423220973783, "terminalBench40": 0.252525252525253, "scicode": 0.505787037037037, "lcr": 0.796666666666667, "ifbench": null, "hle": 0.380444856348471, "gpqa": 0.923232323232323, "critpt": 0.111428571428571, "apexAgents": null, "mmmuPro": 0.797687861271676, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.559083218951688, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.47, "cacheHitPrice": 0.016, "cacheHitDiscountPercent": 0.8933333333333333, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.22999999999999998, "price1mBlended7To2To1": 0.08819999999999999, "price1mBlended0To1To1": 0.31, "price1mBlended100To1To1": 0.02176470588235294, "price1mBlended0To100To1": 0.15316831683168317, "intelligenceIndexTimePerTask": 1543.9115501363954, "intelligenceIndexCost": {"total": 362.72318083357993, "input": 247.59810164357992, "nonCacheInput": 3.8334344999999996, "cacheRead": 200.55182933807998, "cacheWrite": 43.21283780549994, "output": 115.12507919, "reasoning": 94.77747776, "answer": 20.347601429999997}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.3721760025302965, "input": 0.32147019145696387, "nonCacheInput": 0.0026734210687464144, "cacheRead": 0.2717961254229642, "cacheWrite": 0.04700064496525313, "output": 0.05070581107333271, "reasoning": 0.03374942774834666, "answer": 0.01695638332498605}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.2407052670014505}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.029744017633263637}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0013336577756697106}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.08779630434427273}, {"slug": "scicode", "weightedCostPerTask": 0.001263321940972222}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002401265579703429}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00217417882}, {"slug": "critpt", "weightedCostPerTask": 0.005568777785714286}, {"slug": "omniscience", "weightedCostPerTask": 0.00031263765924999996}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00087657399}]}, "canonicalIntelligenceIndexTokenCount": {"input": 12848131149, "output": 244946977, "answer": 43292769, "reasoning": 201654208}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 71807.29308158865, "answer": 36077.41132975757, "output": 107884.70441134622}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 5, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1586.58, "lower95ci": 1576.81, "upper95ci": 1597.28}, "rubricPassRate": 0.5410010649627263, "analyticalQuality": {"elo": 1908.87, "lower95ci": 1890.01, "upper95ci": 1929.78}, "presentation": {"elo": 1438.5, "lower95ci": 1423.15, "upper95ci": 1453.87}}, "briefcaseTotalCost": 146.02786198087998, "timescaleData": {"medianOutputSpeed": 52.8047718048694, "medianTimeToFirstChunk": 2.69238996949997}, "outputSpeedVariance": {"p05": 38.2427468328291, "q25": 48.7293416628511, "median": 52.8047718048694, "q75": 63.4794175331501, "p95": 74.130904240624}, "timeToFirstChunkVariance": {"p05": 2.59376099475, "q25": 2.61775474974999, "median": 2.69238996949997, "q75": 3.18016620524999, "p95": 4.77621119614997}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 57.6672309140644, "medianTimeToFirstChunk": 1.315548245, "medianTimeToFirstAnswerToken": 35.99728982160521, "medianEndToEndResponseTime": 44.667725215756505}, "long": {"medianOutputSpeed": 52.8047718048694, "medianTimeToFirstChunk": 2.69238996949997, "medianTimeToFirstAnswerToken": 40.56775485869299, "medianEndToEndResponseTime": 50.036596080991245}, "hundredK": {"medianOutputSpeed": 70.7795511259695, "medianTimeToFirstChunk": 13.641685632, "medianTimeToFirstAnswerToken": 41.89843448366354, "medianEndToEndResponseTime": 48.96262169657943}, "mediumParallel": {"medianOutputSpeed": 47.0041017439443, "medianTimeToFirstChunk": 1.40300784450005, "medianTimeToFirstAnswerToken": 43.95248599206761, "medianEndToEndResponseTime": 54.589855528959504}}, "endToEndResponseTime": {"input": 2.69238996949997, "reasoning": 37.87536488919302, "answer": 9.468841222298256, "total": 50.036596080991245}, "timeToFirstAnswerToken": {"input": 2.69238996949997, "reasoning": 37.87536488919302, "total": 40.56775485869299}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9b166bf3-42db-4f63-8338-1c4a1244ffe8", "slug": "claude-fable-5-1-xhigh", "name": "Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)", "shortName": "Claude Fable 5.1 (xhigh with fallback)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "claude-fable-5-1", "name": "Claude Fable 5.1"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 53.1840337538944, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 56.27435836257534, "strategyAndOps": 58.453212499826236, "legal": 60.83043121464797, "engineering": 56.812269852637314, "economics": 62.402244555143646}, "omniscience": 42.3833333333333, "omniscienceBreakdown": {"accuracy": 0.6621666666666667, "hallucinationRate": 0.7054760730143068}, "harveyLab": 0.932696482848459, "gdpPdfAllPass": 0.262, "gdpval": 1745.29, "gdpvalNormalized": 0.622645, "itBenchSre": null, "tau2": null, "tauBanking": 0.457731958762887, "terminalbenchHard": null, "terminalBench21": 0.910112359550562, "terminalBench40": 0.55050505050505, "scicode": 0.608796296296296, "lcr": 0.83, "ifbench": null, "hle": 0.587117701575533, "gpqa": 0.934343434343434, "critpt": 0.311428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.57772425084896, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.975, "cacheWritePrice": 12.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.175, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 681.5911413424006, "intelligenceIndexCost": {"total": 9063.112201268303, "input": 3148.4733405419024, "nonCacheInput": 350.20515470460003, "cacheRead": 1022.5551576656806, "cacheWrite": 1775.7130281716218, "output": 5914.6388607264, "reasoning": 4131.349062864, "answer": 1783.2897978623998}, "intelligenceIndexCostPerTask": {"cost": {"total": 5.978304247388257, "input": 2.9577051117924302, "nonCacheInput": 0.2570566798783852, "cacheRead": 1.1945651098045833, "cacheWrite": 1.5060833221094618, "output": 3.0205991355958273, "reasoning": 1.7014414789572212, "answer": 1.319157656638606}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 2.669106492916484}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.7215166664909918}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.1100605851001527}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.5783099429315184}, {"slug": "scicode", "weightedCostPerTask": 0.024103836805555556}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.10254394518594254}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.23229670000000002}, {"slug": "critpt", "weightedCostPerTask": 0.4533751571428571}, {"slug": "omniscience", "weightedCostPerTask": 0.011600005814755626}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.07539091499999999}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4193251074, "output": 120524006, "answer": 36224523, "reasoning": 84299483}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 34067.40516593828, "answer": 26470.208625081556, "output": 60537.61379101984}, "briefcaseBreakdown": {"overall": {"elo": 1650.01, "lower95ci": 1640.57, "upper95ci": 1659.19}, "rubricPassRate": 0.6060606060606061, "analyticalQuality": {"elo": 1930, "lower95ci": 1912.87, "upper95ci": 1947.38}, "presentation": {"elo": 1456.91, "lower95ci": 1443.21, "upper95ci": 1471.87}}, "briefcaseTotalCost": 1619.2579390360002, "timescaleData": {"medianOutputSpeed": 58.1928231238941, "medianTimeToFirstChunk": 106.600246656}, "outputSpeedVariance": {"p05": 46.676945728954, "q25": 50.8726794157326, "median": 58.1928231238941, "q75": 66.8593817535144, "p95": 71.8514385160829}, "timeToFirstChunkVariance": {"p05": 21.3962934585, "q25": 52.6623472455, "median": 106.600246656, "q75": 217.688663368, "p95": 342.0281852115}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 64.4251569516188, "medianTimeToFirstChunk": 48.740068116, "medianTimeToFirstAnswerToken": 48.740068116, "medianEndToEndResponseTime": 56.50101156819033}, "long": {"medianOutputSpeed": 58.1928231238941, "medianTimeToFirstChunk": 106.600246656, "medianTimeToFirstAnswerToken": 106.600246656, "medianEndToEndResponseTime": 115.19237147756925}, "hundredK": {"medianOutputSpeed": 70.0470142169538, "medianTimeToFirstChunk": 32.866839907, "medianTimeToFirstAnswerToken": 32.866839907, "medianEndToEndResponseTime": 40.004902900682644}, "mediumParallel": {"medianOutputSpeed": 64.4135275831469, "medianTimeToFirstChunk": 88.1050792885, "medianTimeToFirstAnswerToken": 88.1050792885, "medianEndToEndResponseTime": 95.86742391951846}}, "endToEndResponseTime": {"input": 106.600246656, "reasoning": 0, "answer": 8.592124821569259, "total": 115.19237147756925}, "timeToFirstAnswerToken": {"input": 106.600246656, "reasoning": 0, "total": 106.600246656}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9b97a35e-6ac7-44d9-91c6-422fa678963e", "slug": "gpt-5-6-terra-non-reasoning", "name": "GPT-5.6 Terra (Non-reasoning)", "shortName": "GPT-5.6 Terra (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-5-6-terra", "name": "GPT-5.6 Terra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 21.2083013584503, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 21.508589316442063, "strategyAndOps": 23.518373906547826, "legal": 22.643423336890844, "engineering": 21.395074165192234, "economics": 24.326763708680872}, "omniscience": -23.2166666666667, "omniscienceBreakdown": {"accuracy": 0.36816666666666664, "hallucinationRate": 0.9501450804537062}, "gdpPdfAllPass": 0.112, "gdpval": 1145.71, "gdpvalNormalized": 0.322855, "itBenchSre": null, "tau2": null, "tauBanking": 0.156701030927835, "terminalbenchHard": null, "terminalBench21": 0.561797752808989, "terminalBench40": 0.00505050505050505, "scicode": 0.451388888888889, "lcr": 0.586666666666667, "ifbench": null, "hle": 0.113994439295644, "gpqa": 0.746464646464646, "critpt": 0.02, "apexAgents": null, "mmmuPro": 0.667052023121387, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.125407685673699, "price1mInputTokens": 2, "price1mOutputTokens": 12, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4.5, "price1mBlended7To2To1": 1.7399999999999998, "price1mBlended0To1To1": 7, "price1mBlended100To1To1": 0.3333333333333333, "price1mBlended0To100To1": 2.099009900990099, "intelligenceIndexTimePerTask": 34.55953840841026, "intelligenceIndexCost": {"total": 255.774127835583, "input": 185.957551835583, "nonCacheInput": 55.864946, "cacheRead": 58.074636231688444, "cacheWrite": 72.01796960389453, "output": 69.816576, "reasoning": 0, "answer": 69.816576}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.13972397093498629, "input": 0.10217123351802342, "nonCacheInput": 0.04302788974757639, "cacheRead": 0.02692936191690272, "cacheWrite": 0.03221398185354431, "output": 0.03755273741696287, "reasoning": 0, "answer": 0.03755273741696287}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.0473949019625091}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.012772426687915752}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.008952398302386448}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.0234792579366993}, {"slug": "scicode", "weightedCostPerTask": 0.000995851388888889}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0003016113994439296}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.03374418}, {"slug": "critpt", "weightedCostPerTask": 0.002552942857142857}, {"slug": "omniscience", "weightedCostPerTask": 4.79524e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.009482448}]}, "canonicalIntelligenceIndexTokenCount": {"input": 347112842, "output": 5818048, "answer": 5818048, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 3129.3947847469058, "output": 3129.3947847469058}, "briefcaseBreakdown": {"overall": {"elo": 947.67, "lower95ci": 940.04, "upper95ci": 955.77}, "rubricPassRate": 0.2111111111111111, "analyticalQuality": {"elo": 845.63, "lower95ci": 831.51, "upper95ci": 860.63}, "presentation": {"elo": 1087.88, "lower95ci": 1074.74, "upper95ci": 1101.64}}, "briefcaseTotalCost": 28.752907190588857, "timescaleData": {"medianOutputSpeed": 90.3739699485649, "medianTimeToFirstChunk": 0.916391271500061}, "outputSpeedVariance": {"p05": 57.9784642290351, "q25": 72.3602935943341, "median": 90.3739699485649, "q75": 99.366907425408, "p95": 128.702908196718}, "timeToFirstChunkVariance": {"p05": 0.693042517199927, "q25": 0.815126632749752, "median": 0.916391271500061, "q75": 1.2412723869998, "p95": 1.96704520829999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 82.2328384590477, "medianTimeToFirstChunk": 0.905557828999975, "medianTimeToFirstAnswerToken": 0.905557828999975, "medianEndToEndResponseTime": 6.985853844186197}, "long": {"medianOutputSpeed": 90.3739699485649, "medianTimeToFirstChunk": 0.916391271500061, "medianTimeToFirstAnswerToken": 0.916391271500061, "medianEndToEndResponseTime": 6.448957786886826}, "hundredK": {"medianOutputSpeed": 110.904980867708, "medianTimeToFirstChunk": 1.82755200300003, "medianTimeToFirstAnswerToken": 1.82755200300003, "medianEndToEndResponseTime": 6.335915794130569}, "mediumParallel": {"medianOutputSpeed": 72.6676433904257, "medianTimeToFirstChunk": 1.01300084700003, "medianTimeToFirstAnswerToken": 1.01300084700003, "medianEndToEndResponseTime": 7.893642308201968}}, "endToEndResponseTime": {"input": 0.916391271500061, "reasoning": 0, "answer": 5.532566515386765, "total": 6.448957786886826}, "timeToFirstAnswerToken": {"input": 0.916391271500061, "reasoning": 0, "total": 0.916391271500061}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9ca246a7-cf13-42c9-9182-5b5ad6b79026", "slug": "minimax-m1-80k", "name": "MiniMax M1 80k", "shortName": "MiniMax M1 80k", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-17", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "minimax-m1-80k", "name": "MiniMax M1 80k"}, "deprecated": true, "deprecatedTo": "minimax-m2", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 456, "inferenceParametersActiveBillions": 45.9, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/MiniMaxAI/MiniMax-M1-80k", "microevalsEnabled": false, "intelligenceIndex": 11.725328542655, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -48.5, "omniscienceBreakdown": {"accuracy": 0.22466666666666665, "hallucinationRate": 0.91530524505589}, "gdpval": null, "itBenchSre": null, "tau2": 0.342105263157895, "tauBanking": null, "terminalbenchHard": 0.0303030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.576666666666667, "ifbench": 0.417687074829932, "hle": 0.0889712696941613, "gpqa": 0.696969696969697, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.711111111111111, "aime25": 0.61, "analystAgent": null, "price1mInputTokens": 0.55, "price1mOutputTokens": 2.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.9625000000000001, "price1mBlended7To2To1": 0.7150000000000001, "price1mBlended0To1To1": 1.375, "price1mBlended100To1To1": 0.5661764705882354, "price1mBlended0To100To1": 0.5663366336633664, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "a31a9071-6144-4dbb-92dc-2e02d653ecea", "slug": "minimax", "name": "MiniMax", "logo": "/img/logos/minimax_small.svg", "color": "#EB3568", "country": "cn", "url": "https://minimaxi.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9ca71ac4-41c8-42c0-87dd-5704a9e5b94d", "slug": "llama-3-2-instruct-90b-vision", "name": "Llama 3.2 Instruct 90B (Vision)", "shortName": "Llama 3.2 90B (Vision)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-25", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-2-instruct-90b-vision", "name": "Llama 3.2 Instruct 90B (Vision)"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 90, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.2 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Llama-3.2-90B-Vision", "microevalsEnabled": false, "intelligenceIndex": 6.4088295766243, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0449, "gpqa": 0.432323232323232, "critpt": null, "apexAgents": null, "mmmuPro": 0.394797687861272, "livecodebench": 0.213756613756614, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9cc377dc-67ae-4042-bafc-0466b5f05089", "slug": "k-exaone-non-reasoning", "name": "K-EXAONE (Non-reasoning)", "shortName": "K-EXAONE (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-31", "knowledgeCutoffDate": "2024-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "k-exaone", "name": "K-EXAONE"}, "deprecated": true, "deprecatedTo": "k-exaone-2-0-0803", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 236, "inferenceParametersActiveBillions": 23, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "K Exaone", "licenseUrl": "https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B", "microevalsEnabled": false, "intelligenceIndex": 11.2077008943064, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -65.4, "omniscienceBreakdown": {"accuracy": 0.1365, "hallucinationRate": 0.9154603358425014}, "gdpval": null, "itBenchSre": null, "tau2": 0.590643274853801, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.533333333333333, "ifbench": 0.395918367346939, "hle": 0.0569972196478221, "gpqa": 0.694949494949495, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": 0.44, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "45157c16-fcbb-4110-b20f-7bca754b6554", "slug": "lg", "name": "LG AI Research", "logo": "/img/logos/lg_small.png", "color": "#df3b8a", "country": "kr", "url": "https://www.lgresearch.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9d7d72cd-d95d-45a0-b109-4ad292c9aabd", "slug": "claude-fable-5-1-high", "name": "Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)", "shortName": "Claude Fable 5.1 (high with fallback)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "claude-fable-5-1", "name": "Claude Fable 5.1"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 51.2094958852237, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 53.906142573151676, "strategyAndOps": 56.28112068550445, "legal": 58.20240053147126, "engineering": 54.59040014282907, "economics": 60.311579626197116}, "omniscience": 40.8, "omniscienceBreakdown": {"accuracy": 0.6493333333333333, "hallucinationRate": 0.688212927756654}, "harveyLab": 0.929512230424084, "gdpPdfAllPass": 0.268, "gdpval": 1649.77, "gdpvalNormalized": 0.574885, "itBenchSre": null, "tau2": null, "tauBanking": 0.430927835051546, "terminalbenchHard": null, "terminalBench21": 0.898876404494382, "terminalBench40": 0.52020202020202, "scicode": 0.586805555555556, "lcr": 0.836666666666667, "ifbench": null, "hle": 0.559314179796108, "gpqa": 0.906060606060606, "critpt": 0.302857142857143, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5532309746463979, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.975, "cacheWritePrice": 12.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.175, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 409.69570061502196, "intelligenceIndexCost": {"total": 5241.588289787318, "input": 2202.042734947243, "nonCacheInput": 349.7007441262799, "cacheRead": 585.681078641585, "cacheWrite": 1266.660912179378, "output": 3039.545554840075, "reasoning": 1670.010989605, "answer": 1369.534565235075}, "intelligenceIndexCostPerTask": {"cost": {"total": 3.912526554325558, "input": 2.010874096809779, "nonCacheInput": 0.2563549721894385, "cacheRead": 0.7007398694325817, "cacheWrite": 1.0537792551877592, "output": 1.9016524575157785, "reasoning": 0.9301648411230536, "answer": 0.971487616392725}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 1.709818883132658}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.34787048154705347}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.08830881879354777}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.163956277493384}, {"slug": "scicode", "weightedCostPerTask": 0.008909774305555555}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.039698426888250926}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.20204515}, {"slug": "critpt", "weightedCostPerTask": 0.27476601428571434}, {"slug": "omniscience", "weightedCostPerTask": 0.00310048787939425}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.07405224}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2443935298, "output": 61994670, "answer": 27804661, "reasoning": 34190009}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 18622.54895818041, "answer": 19431.730066504435, "output": 38054.279024684845}, "briefcaseBreakdown": {"overall": {"elo": 1578.19, "lower95ci": 1569.93, "upper95ci": 1587.02}, "rubricPassRate": 0.5717171717171717, "analyticalQuality": {"elo": 1846.32, "lower95ci": 1830.95, "upper95ci": 1863.68}, "presentation": {"elo": 1392.53, "lower95ci": 1377, "upper95ci": 1408.06}}, "briefcaseTotalCost": 1037.2901224338125, "timescaleData": {"medianOutputSpeed": 57.9952599193268, "medianTimeToFirstChunk": 11.1425649070001}, "outputSpeedVariance": {"p05": 42.2106759347231, "q25": 46.8526914259934, "median": 57.9952599193268, "q75": 63.9988070586862, "p95": 72.3243360679305}, "timeToFirstChunkVariance": {"p05": 4.71880625205009, "q25": 7.85510111799995, "median": 11.1425649070001, "q75": 20.8213415735, "p95": 36.1652763658001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 58.1525928683814, "medianTimeToFirstChunk": 14.1801766995, "medianTimeToFirstAnswerToken": 14.1801766995, "medianEndToEndResponseTime": 22.778245596129697}, "long": {"medianOutputSpeed": 57.9952599193268, "medianTimeToFirstChunk": 11.1425649070001, "medianTimeToFirstAnswerToken": 11.1425649070001, "medianEndToEndResponseTime": 19.763959150176447}, "hundredK": {"medianOutputSpeed": 64.2780667653921, "medianTimeToFirstChunk": 22.7832155424999, "medianTimeToFirstAnswerToken": 22.7832155424999, "medianEndToEndResponseTime": 30.561918685905646}, "mediumParallel": {"medianOutputSpeed": 55.5242151135301, "medianTimeToFirstChunk": 16.3791990575, "medianTimeToFirstAnswerToken": 16.3791990575, "medianEndToEndResponseTime": 25.38427907488795}}, "endToEndResponseTime": {"input": 11.1425649070001, "reasoning": 0, "answer": 8.621394243176347, "total": 19.763959150176447}, "timeToFirstAnswerToken": {"input": 11.1425649070001, "reasoning": 0, "total": 11.1425649070001}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9dba61f5-78ee-4190-8d1d-8e7063ffd386", "slug": "qwen3-8b-instruct-reasoning", "name": "Qwen3 8B (Reasoning)", "shortName": "Qwen3 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-8b-instruct", "name": "Qwen3 8B"}, "deprecated": true, "deprecatedTo": "qwen3-vl-8b-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8.19, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-8B", "microevalsEnabled": false, "intelligenceIndex": 5.16145716580451, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 5.139824075325074, "strategyAndOps": 3.7704400005177456, "legal": 4.303245213875025, "engineering": 8.604333333333335, "economics": 7.773443319838056}, "omniscience": -64.7333333333333, "omniscienceBreakdown": {"accuracy": 0.13633333333333333, "hallucinationRate": 0.9073716711694326}, "gdpPdfAllPass": 0.014, "gdpval": 165.39, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.277777777777778, "tauBanking": 0.0474226804123711, "terminalbenchHard": 0.0227272727272727, "terminalBench21": 0.0224719101123595, "terminalBench40": 0, "scicode": 0.278935185185185, "lcr": 0, "ifbench": 0.33469387755102, "hle": 0.0389, "gpqa": 0.588888888888889, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.406349206349206, "aime25": 0.19, "analystAgent": null, "automationBenchPartialScore": 0.003326067293298021, "price1mInputTokens": 0.18, "price1mOutputTokens": 2.1, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.66, "price1mBlended7To2To1": 0.372, "price1mBlended0To1To1": 1.1400000000000001, "price1mBlended100To1To1": 0.1988235294117647, "price1mBlended0To100To1": 0.19900990099009902, "briefcaseBreakdown": {"overall": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "rubricPassRate": 0.03232323232323232, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 5.70863718, "timescaleData": {"medianOutputSpeed": 37.452201511139, "medianTimeToFirstChunk": 3.80406084149999}, "outputSpeedVariance": {"p05": 25.0106366306534, "q25": 35.267234734226, "median": 37.452201511139, "q75": 43.2354486311377, "p95": 44.4235876388168}, "timeToFirstChunkVariance": {"p05": 3.5726514179, "q25": 3.66672149174998, "median": 3.80406084149999, "q75": 3.97892328975, "p95": 4.4921866173}, "performanceByPromptType": {"long": {"medianOutputSpeed": 37.452201511139, "medianTimeToFirstChunk": 3.80406084149999, "medianTimeToFirstAnswerToken": 57.20546100766009, "medianEndToEndResponseTime": 70.55581104920012}}, "endToEndResponseTime": {"input": 3.80406084149999, "reasoning": 53.4014001661601, "answer": 13.350350041540025, "total": 70.55581104920012}, "timeToFirstAnswerToken": {"input": 3.80406084149999, "reasoning": 53.4014001661601, "total": 57.20546100766009}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9e141c0d-fc82-4e07-bb2e-fe0003bc030b", "slug": "claude-21", "name": "Claude 2.1", "shortName": "Claude 2.1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-11-21", "knowledgeCutoffDate": "2023-01-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-21", "name": "Claude 2.1"}, "deprecated": true, "deprecatedTo": "claude-3-sonnet", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.58581054715502, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0389, "gpqa": 0.319191919191919, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.194708994708995, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9e30696f-16fa-4b4f-ba53-161895a85fed", "slug": "gpt-5-6-terra-xhigh", "name": "GPT-5.6 Terra (xhigh)", "shortName": "GPT-5.6 Terra (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-6-terra", "name": "GPT-5.6 Terra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 38.1856370742927, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 40.12960281541717, "strategyAndOps": 43.96097961154578, "legal": 40.064379098111715, "healthcareAndMedical": 37.91666023976717, "engineering": 38.04707600873022, "economics": 44.433473818350315}, "omniscience": -2.98333333333333, "omniscienceBreakdown": {"accuracy": 0.45516666666666666, "hallucinationRate": 0.890180483328235}, "mlcrOverall": 0.216666666666667, "gdpPdfAllPass": 0.246, "gdpval": 1478.6, "gdpvalNormalized": 0.48929999999999996, "itBenchSre": null, "tau2": 0.804093567251462, "tauBanking": 0.296907216494845, "terminalbenchHard": 0.628787878787879, "terminalBench21": 0.801498127340824, "terminalBench40": 0.101010101010101, "scicode": 0.523148148148148, "lcr": 0.79, "ifbench": 0.662585034013605, "hle": 0.418906394810009, "gpqa": 0.908080808080808, "critpt": 0.271428571428571, "apexAgents": null, "mmmuPro": 0.794797687861272, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.47136313405977687, "price1mInputTokens": 2, "price1mOutputTokens": 12, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4.5, "price1mBlended7To2To1": 1.7399999999999998, "price1mBlended0To1To1": 7, "price1mBlended100To1To1": 0.3333333333333333, "price1mBlended0To100To1": 2.099009900990099, "intelligenceIndexTimePerTask": 230.84381845897656, "intelligenceIndexCost": {"total": 1186.7727742306568, "input": 562.8298222306569, "nonCacheInput": 54.202688, "cacheRead": 282.6985487625516, "cacheWrite": 225.9285854681052, "output": 623.9429519999999, "reasoning": 455.19094799999993, "answer": 168.752004}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.6317911346924275, "input": 0.3873829635766309, "nonCacheInput": 0.0413864512825588, "cacheRead": 0.21824574109632405, "cacheWrite": 0.127750771197748, "output": 0.24440817111579674, "reasoning": 0.13813980062099288, "answer": 0.10626837049480381}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.2720757248397669}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.08043250998813686}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.026375741258357743}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.15724625917041873}, {"slug": "scicode", "weightedCostPerTask": 0.0032531624999999997}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.009565581464318814}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.041599882}, {"slug": "critpt", "weightedCostPerTask": 0.029071928571428575}, {"slug": "omniscience", "weightedCostPerTask": 0.0024293928999999997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.009740952}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1530965522, "output": 51995246, "answer": 14062667, "reasoning": 37932579}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 11511.650051749408, "answer": 8855.697541233654, "output": 20367.34759298306}, "briefcaseBreakdown": {"overall": {"elo": 1337.28, "lower95ci": 1328.63, "upper95ci": 1346.62}, "rubricPassRate": 0.35353535353535354, "analyticalQuality": {"elo": 1344.87, "lower95ci": 1328.26, "upper95ci": 1362.1}, "presentation": {"elo": 1508, "lower95ci": 1492.22, "upper95ci": 1526.52}}, "briefcaseTotalCost": 165.05927306945858, "timescaleData": {"medianOutputSpeed": 88.607645477025, "medianTimeToFirstChunk": 14.461006256}, "outputSpeedVariance": {"p05": 62.2579495239032, "q25": 78.2187946316833, "median": 88.607645477025, "q75": 102.210416473094, "p95": 120.995573592847}, "timeToFirstChunkVariance": {"p05": 3.75488550809995, "q25": 6.38008042175011, "median": 14.461006256, "q75": 45.4103924045002, "p95": 113.4379215106}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 84.8914965212153, "medianTimeToFirstChunk": 10.4000685534999, "medianTimeToFirstAnswerToken": 10.4000685534999, "medianEndToEndResponseTime": 16.289939983379153}, "long": {"medianOutputSpeed": 88.607645477025, "medianTimeToFirstChunk": 14.461006256, "medianTimeToFirstAnswerToken": 14.461006256, "medianEndToEndResponseTime": 20.10386018026599}, "hundredK": {"medianOutputSpeed": 114.922115486415, "medianTimeToFirstChunk": 8.23823203250001, "medianTimeToFirstAnswerToken": 8.23823203250001, "medianEndToEndResponseTime": 12.58900470914035}, "mediumParallel": {"medianOutputSpeed": 88.2207209702878, "medianTimeToFirstChunk": 52.1531234755001, "medianTimeToFirstAnswerToken": 52.1531234755001, "medianEndToEndResponseTime": 57.820726216679205}}, "endToEndResponseTime": {"input": 14.461006256, "reasoning": 0, "answer": 5.642853924265989, "total": 20.10386018026599}, "timeToFirstAnswerToken": {"input": 14.461006256, "reasoning": 0, "total": 14.461006256}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9e9fb958-87f5-4835-a761-26102ef25898", "slug": "k2-1b-final", "name": "K2 Horizon 0.9B", "shortName": "K2 Horizon 0.9B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-03", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "k2-horizon-0-9b", "name": "K2 Horizon 0.9B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 0.9, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/IFM/K2-Horizon-0.9B", "microevalsEnabled": false, "intelligenceIndex": 3.04760621054014, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 3.7392728631021424, "strategyAndOps": 1.6331362624438188, "legal": 4.704329590762182, "engineering": 6.371302131603336, "economics": 7.50053830707445}, "omniscience": -72.8166666666667, "omniscienceBreakdown": {"accuracy": 0.06933333333333333, "hallucinationRate": 0.8569126074498568}, "gdpPdfAllPass": 0.008, "gdpval": -173.76, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": null, "tauBanking": 0.0494845360824742, "terminalbenchHard": null, "terminalBench21": 0.0112359550561798, "terminalBench40": 0, "scicode": 0.0694444444444444, "lcr": 0.0633333333333333, "ifbench": null, "hle": 0.0537534754402224, "gpqa": 0.292929292929293, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.002038009788550524, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "canonicalIntelligenceIndexTokenCount": {"input": 4213221448, "output": 59591388, "answer": 32281443, "reasoning": 27309945}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 9426.961700116737, "answer": 22831.90881364575, "output": 32258.870513762486}, "briefcaseBreakdown": {"overall": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "rubricPassRate": 0, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "8b8b84fb-4b24-45be-b9e2-74ed50d00ff7", "slug": "mbzuai", "name": "MBZUAI Institute of Foundation Models", "logo": "/img/logos/mbzuai_small.svg", "color": "#1521a9", "country": "ae", "url": "https://mbzuai.ac.ae/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9eae4ec4-61b8-48bc-9843-3edd506ae933", "slug": "devstral-small", "name": "Devstral Small (Jul '25)", "shortName": "Devstral Small", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-10", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "devstral-small", "name": "Devstral Small (Jul '25)"}, "deprecated": true, "deprecatedTo": "devstral-small-2", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 24, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Devstral-Small-2507", "microevalsEnabled": false, "intelligenceIndex": 7.60237445255949, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -50.8333333333333, "omniscienceBreakdown": {"accuracy": 0.14733333333333334, "hallucinationRate": 0.7689601250977326}, "gdpval": null, "itBenchSre": null, "tau2": 0.283625730994152, "tauBanking": null, "terminalbenchHard": 0.0606060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.186666666666667, "ifbench": 0.345578231292517, "hle": 0.0375347544022243, "gpqa": 0.414141414141414, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.253968253968254, "aime25": 0.293333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9ee13921-62a4-425a-a22b-df3302198d93", "slug": "nvidia-nemotron-3-nano-4b", "name": "NVIDIA Nemotron 3 Nano 4B", "shortName": "Nemotron 3 Nano 4B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "nvidia-nemotron-3-nano-4b", "name": "NVIDIA Nemotron 3 Nano 4B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3.97, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 262000, "licenseName": "Nvidia Nemotron Open Model License", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-nemotron-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16", "microevalsEnabled": false, "intelligenceIndex": 7.38161312356127, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -70.5333333333333, "omniscienceBreakdown": {"accuracy": 0.09566666666666666, "hallucinationRate": 0.8857353483228898}, "gdpval": 159.11, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.280701754385965, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": 0.0374531835205993, "terminalBench40": null, "scicode": null, "lcr": 0.216666666666667, "ifbench": 0.582312925170068, "hle": 0.0486561631139944, "gpqa": 0.513131313131313, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 83.33333333333333, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9f7c7566-a704-49a2-a383-cb3181da33a4", "slug": "gpt-4-1-mini", "name": "GPT-4.1 mini", "shortName": "GPT-4.1 mini", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-14", "knowledgeCutoffDate": "2024-05-31", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4-1-mini", "name": "GPT-4.1 mini"}, "deprecated": true, "deprecatedTo": "gpt-5-mini-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 10.1588744766829, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -53.5666666666667, "omniscienceBreakdown": {"accuracy": 0.20316666666666666, "hallucinationRate": 0.9272118803597573}, "gdpval": 453.21, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.529239766081871, "tauBanking": 0.0536082474226804, "terminalbenchHard": 0.0757575757575758, "terminalBench21": 0.101123595505618, "terminalBench40": null, "scicode": null, "lcr": 0.44, "ifbench": 0.382993197278912, "hle": 0.0502, "gpqa": 0.663636363636364, "critpt": 0, "apexAgents": null, "mmmuPro": 0.58728323699422, "livecodebench": 0.482539682539683, "aime25": 0.463333333333333, "analystAgent": null, "price1mInputTokens": 0.4, "price1mOutputTokens": 1.6, "cacheHitPrice": 0.1, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": 0.6636, "price1mBlended0To3To1": 0.7000000000000001, "price1mBlended7To2To1": 0.31, "price1mBlended0To1To1": 1, "price1mBlended100To1To1": 0.11764705882352941, "price1mBlended0To100To1": 0.4118811881188119, "timescaleData": {"medianOutputSpeed": 118.86458321643, "medianTimeToFirstChunk": 0.84874717750003}, "outputSpeedVariance": {"p05": 64.7783219616269, "q25": 92.8164410472279, "median": 118.86458321643, "q75": 150.443318093233, "p95": 162.018254507606}, "timeToFirstChunkVariance": {"p05": 0.608040990999992, "q25": 0.761184942499952, "median": 0.84874717750003, "q75": 0.910624648249936, "p95": 0.958930603449974}, "performanceByPromptType": {"long": {"medianOutputSpeed": 118.86458321643, "medianTimeToFirstChunk": 0.84874717750003, "medianTimeToFirstAnswerToken": 0.84874717750003, "medianEndToEndResponseTime": 5.055214625331772}}, "endToEndResponseTime": {"input": 0.84874717750003, "reasoning": 0, "answer": 4.206467447831741, "total": 5.055214625331772}, "timeToFirstAnswerToken": {"input": 0.84874717750003, "reasoning": 0, "total": 0.84874717750003}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "9f873c2f-2c2d-4ccb-9e1b-71bf61b052be", "slug": "phi-4-mini", "name": "Phi-4 Mini Instruct", "shortName": "Phi-4 Mini", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-02-26", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "phi-4-mini", "name": "Phi-4 Mini Instruct"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3.84, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/microsoft/Phi-4-mini-instruct", "microevalsEnabled": false, "intelligenceIndex": 6.32860508899613, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -61.0833333333333, "omniscienceBreakdown": {"accuracy": 0.095, "hallucinationRate": 0.7799263351749539}, "gdpval": -171.32, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.0818713450292398, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": 0.00374531835205993, "terminalBench40": null, "scicode": null, "lcr": 0.153333333333333, "ifbench": 0.210884353741497, "hle": 0.0445, "gpqa": 0.331313131313131, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.125925925925926, "aime25": 0.0666666666666667, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 45.7738858319009, "medianTimeToFirstChunk": 0.883643120499926}, "outputSpeedVariance": {"p05": 42.2189897577048, "q25": 43.8317521763738, "median": 45.7738858319009, "q75": 46.4827461850988, "p95": 47.2781725001749}, "timeToFirstChunkVariance": {"p05": 0.826957942400034, "q25": 0.857032680499998, "median": 0.883643120499926, "q75": 0.943889843250005, "p95": 1.72312334859999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 45.8560024858188, "medianTimeToFirstChunk": 0.385465808500015, "medianTimeToFirstAnswerToken": 0.385465808500015, "medianEndToEndResponseTime": 11.28916375196178}, "long": {"medianOutputSpeed": 45.7738858319009, "medianTimeToFirstChunk": 0.883643120499926, "medianTimeToFirstAnswerToken": 0.883643120499926, "medianEndToEndResponseTime": 11.806901893770563}, "hundredK": {"medianOutputSpeed": 10.9130142003343, "medianTimeToFirstChunk": 16.9282306375001, "medianTimeToFirstAnswerToken": 16.9282306375001, "medianEndToEndResponseTime": 62.745086624426555}, "mediumParallel": {"medianOutputSpeed": 46.4074296128964, "medianTimeToFirstChunk": 0.372443710499965, "medianTimeToFirstAnswerToken": 0.372443710499965, "medianEndToEndResponseTime": 11.146580614239456}}, "endToEndResponseTime": {"input": 0.883643120499926, "reasoning": 0, "answer": 10.923258773270637, "total": 11.806901893770563}, "timeToFirstAnswerToken": {"input": 0.883643120499926, "reasoning": 0, "total": 0.883643120499926}, "performanceDataSource": {"type": "firstParty", "providerName": "Microsoft"}, "hostModelCount": 1, "creator": {"id": "ef5ce458-9986-4652-915a-e31fac5506b0", "slug": "azure", "name": "Microsoft", "logo": "/img/logos/microsoft_small.svg", "color": "#0078D5", "country": "us", "url": "https://azure.microsoft.com/en-us"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a04f5b78-f397-4fd8-a2b1-00dcab50324c", "slug": "grok-beta", "name": "Grok Beta", "shortName": "Grok Beta", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-08-13", "knowledgeCutoffDate": "2024-03-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "grok-beta", "name": "Grok Beta"}, "deprecated": true, "deprecatedTo": "grok-2-1212", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.88772203061345, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0445, "gpqa": 0.470707070707071, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.241269841269841, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a06bd3fc-86db-4a8e-ae6d-7459444d08c9", "slug": "grok-code-fast-1", "name": "Grok Code Fast 1", "shortName": "Grok Code Fast 1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "grok-code-fast-1", "name": "Grok Code Fast 1"}, "deprecated": true, "deprecatedTo": "grok-4-20", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 14.0584706489017, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -37.0666666666667, "omniscienceBreakdown": {"accuracy": 0.2355, "hallucinationRate": 0.7928929583605843}, "gdpval": null, "itBenchSre": null, "tau2": 0.757309941520468, "tauBanking": null, "terminalbenchHard": 0.174242424242424, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.53, "ifbench": 0.413605442176871, "hle": 0.0801668211306766, "gpqa": 0.727272727272727, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.657142857142857, "aime25": 0.433333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a20ae33a-46e1-41e6-81a0-fe8b00d2e538", "slug": "nova-2-0-pro", "name": "Nova 2.0 Pro Preview (Non-reasoning)", "shortName": "Nova 2.0 Pro Preview (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-27", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "nova-2-0-pro-preview", "name": "Nova 2.0 Pro Preview"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.95904965562327, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -49.5, "omniscienceBreakdown": {"accuracy": 0.16916666666666666, "hallucinationRate": 0.7993981945837513}, "gdpval": 508.59, "gdpvalNormalized": 0.004294999999999987, "itBenchSre": null, "tau2": 0.716374269005848, "tauBanking": null, "terminalbenchHard": 0.166666666666667, "terminalBench21": 0.172284644194757, "terminalBench40": null, "scicode": null, "lcr": 0.3, "ifbench": 0.520408163265306, "hle": 0.0393883225208526, "gpqa": 0.636363636363636, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.473015873015873, "aime25": 0.306666666666667, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 1.76, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 2.125, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 1.3357843137254901, "price1mBlended0To100To1": 1.3366336633663367, "timescaleData": {"medianOutputSpeed": 102.081938579971, "medianTimeToFirstChunk": 1.08206368599997}, "outputSpeedVariance": {"p05": 85.6381956047271, "q25": 90.7723407576734, "median": 102.081938579971, "q75": 117.608040272781, "p95": 132.046426160537}, "timeToFirstChunkVariance": {"p05": 0.902878348749948, "q25": 0.963908729000025, "median": 1.08206368599997, "q75": 1.16961952224979, "p95": 1.74687031874998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 139.799015308274, "medianTimeToFirstChunk": 0.686191108499983, "medianTimeToFirstAnswerToken": 0.686191108499983, "medianEndToEndResponseTime": 4.262754211590792}, "long": {"medianOutputSpeed": 102.081938579971, "medianTimeToFirstChunk": 1.08206368599997, "medianTimeToFirstAnswerToken": 1.08206368599997, "medianEndToEndResponseTime": 5.980089790865719}, "hundredK": {"medianOutputSpeed": 123.93490247885, "medianTimeToFirstChunk": 4.52685105, "medianTimeToFirstAnswerToken": 4.52685105, "medianEndToEndResponseTime": 8.561227081282446}, "mediumParallel": {"medianOutputSpeed": 112.588352392399, "medianTimeToFirstChunk": 1.84897408050001, "medianTimeToFirstAnswerToken": 1.84897408050001, "medianEndToEndResponseTime": 6.2899307991610405}}, "endToEndResponseTime": {"input": 1.08206368599997, "reasoning": 0, "answer": 4.89802610486575, "total": 5.980089790865719}, "timeToFirstAnswerToken": {"input": 1.08206368599997, "reasoning": 0, "total": 1.08206368599997}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a29e66d6-1c3c-456a-8770-59ee3845b35d", "slug": "ring-1t", "name": "Ring-1T", "shortName": "Ring-1T", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-13", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "ring-1t", "name": "Ring-1T"}, "deprecated": true, "deprecatedTo": "ring-2-6-1t", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1000, "inferenceParametersActiveBillions": 50, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ring-1T", "microevalsEnabled": false, "intelligenceIndex": 10.8974845417933, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -50.9166666666667, "omniscienceBreakdown": {"accuracy": 0.20466666666666666, "hallucinationRate": 0.8975272422464375}, "gdpval": null, "itBenchSre": null, "tau2": 0.263157894736842, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.546666666666667, "ifbench": 0.445578231292517, "hle": 0.111214087117702, "gpqa": 0.773737373737374, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.643386243386243, "aime25": 0.893333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a2c8e7b2-57bf-4d1e-96ea-7944d786d94d", "slug": "granite-4-0-nano-1b", "name": "Granite 4.0 1B", "shortName": "Granite 4.0 1B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "granite-4-0-nano-1b", "name": "Granite 4.0 1B"}, "deprecated": true, "deprecatedTo": "granite-4-1-3b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1.6, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.0-1b", "microevalsEnabled": false, "intelligenceIndex": 5.01437141074802, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -81.6166666666667, "omniscienceBreakdown": {"accuracy": 0.0615, "hallucinationRate": 0.9351802521754573}, "gdpval": null, "itBenchSre": null, "tau2": 0.228070175438596, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.06, "ifbench": 0.205442176870748, "hle": 0.0481927710843374, "gpqa": 0.280808080808081, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0465608465608466, "aime25": 0.0633333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 55.55555555555556, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a3043d4f-9b92-4261-8ea2-a2d391b09cf4", "slug": "motif-0714", "name": "Motif 3 (Beta)", "shortName": "Motif 3 (Beta)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-14", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "motif-0714", "name": "Motif 3 (Beta)"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 314, "inferenceParametersActiveBillions": 13, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 32.3147020976362, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -17.7666666666667, "omniscienceBreakdown": {"accuracy": 0.21016666666666667, "hallucinationRate": 0.49103186326229165}, "gdpval": 1182.62, "gdpvalNormalized": 0.34130999999999995, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": 0.707865168539326, "terminalBench40": null, "scicode": null, "lcr": 0.746666666666667, "ifbench": null, "hle": 0.403614457831325, "gpqa": 0.868686868686869, "critpt": 0.06, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "366bf3fc-4436-4baf-8d8f-acb7ec04d342", "slug": "motif-technologies", "name": "Motif Technologies", "logo": "/img/logos/motif_small.svg", "color": "#6a93eb", "country": "kr", "url": "https://model-hub.motiftech.io/en/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a38d719a-709c-4983-b3e7-7090389ae9a6", "slug": "k2-v2", "name": "K2-V2 (high)", "shortName": "K2-V2 (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-05", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "k2-v2", "name": "K2-V2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 512000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/LLM360/K2-V2-Instruct", "microevalsEnabled": false, "intelligenceIndex": 9.87390600007694, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -55.5833333333333, "omniscienceBreakdown": {"accuracy": 0.18533333333333332, "hallucinationRate": 0.9097790507364976}, "gdpval": null, "itBenchSre": null, "tau2": 0.277777777777778, "tauBanking": null, "terminalbenchHard": 0.0984848484848485, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.35, "ifbench": 0.601360544217687, "hle": 0.105189990732159, "gpqa": 0.680808080808081, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.694179894179894, "aime25": 0.783333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "8b8b84fb-4b24-45be-b9e2-74ed50d00ff7", "slug": "mbzuai", "name": "MBZUAI Institute of Foundation Models", "logo": "/img/logos/mbzuai_small.svg", "color": "#1521a9", "country": "ae", "url": "https://mbzuai.ac.ae/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a3f8100d-e38f-408b-b0fa-0085dae18dc1", "slug": "gpt-6-astra-low", "name": "GPT-6 Astra (low)", "shortName": "GPT-6 Astra (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-03", "knowledgeCutoffDate": "2026-04-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gpt-6-astra", "name": "GPT-6 Astra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 45.9944993120341, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 48.93861035381174, "strategyAndOps": 50.31927537735309, "legal": 53.21066525347466, "engineering": 47.97202096317337, "economics": 54.95171924235402}, "omniscience": 40.55, "omniscienceBreakdown": {"accuracy": 0.5953333333333334, "hallucinationRate": 0.4691103789126853}, "gdpPdfAllPass": 0.304, "gdpval": 1419.29, "gdpvalNormalized": 0.45964499999999997, "itBenchSre": null, "tau2": null, "tauBanking": 0.319587628865979, "terminalbenchHard": null, "terminalBench21": 0.880149812734082, "terminalBench40": 0.419191919191919, "scicode": 0.540509259259259, "lcr": 0.8, "ifbench": null, "hle": 0.492122335495829, "gpqa": 0.931313131313131, "critpt": 0.262857142857143, "apexAgents": null, "mmmuPro": 0.846242774566474, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5909672610445402, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 1, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 12.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.7, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 1.5686274509803921, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 86.81578202231023, "intelligenceIndexCost": {"total": 1536.7784368593284, "input": 1037.0426368593285, "nonCacheInput": 280.65325, "cacheRead": 350.1306033165801, "cacheWrite": 406.25878354274823, "output": 499.7358, "reasoning": 119.75255, "answer": 379.98325}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.8175139285656057, "input": 0.5958764887300737, "nonCacheInput": 0.2165716940950248, "cacheRead": 0.18536249244267217, "cacheWrite": 0.19394230219237674, "output": 0.22163743983553194, "reasoning": 0.04688430087765605, "answer": 0.17475313895787586}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.21644863739292058}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.08545092471972231}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.04995425794534181}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.22485580260976215}, {"slug": "scicode", "weightedCostPerTask": 0.004250701388888889}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.003886476830398517}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.16963186}, {"slug": "critpt", "weightedCostPerTask": 0.01448597142857143}, {"slug": "omniscience", "weightedCostPerTask": 0.0010444112499999997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.047504885000000004}]}, "canonicalIntelligenceIndexTokenCount": {"input": 410696631, "output": 9994716, "answer": 7599665, "reasoning": 2395051}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 937.6860175531208, "answer": 3495.0627791575184, "output": 4432.748796710639}, "briefcaseBreakdown": {"overall": {"elo": 1253.1, "lower95ci": 1244.4, "upper95ci": 1262.09}, "rubricPassRate": 0.402020202020202, "analyticalQuality": {"elo": 1400.99, "lower95ci": 1382.52, "upper95ci": 1418.45}, "presentation": {"elo": 1142.01, "lower95ci": 1126.22, "upper95ci": 1157.73}}, "briefcaseTotalCost": 131.31217335170516, "timescaleData": {"medianOutputSpeed": 50.9435208650546, "medianTimeToFirstChunk": 2.9638652399999}, "outputSpeedVariance": {"p05": 41.2712896368041, "q25": 45.7222333809817, "median": 50.9435208650546, "q75": 60.7468490843611, "p95": 70.8979605211996}, "timeToFirstChunkVariance": {"p05": 1.24563228500017, "q25": 2.44491627975, "median": 2.9638652399999, "q75": 3.42789610724986, "p95": 4.04084781820001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 51.5468974377458, "medianTimeToFirstChunk": 1.985325038, "medianTimeToFirstAnswerToken": 1.985325038, "medianEndToEndResponseTime": 11.685229879098532}, "long": {"medianOutputSpeed": 50.9435208650546, "medianTimeToFirstChunk": 2.9638652399999, "medianTimeToFirstAnswerToken": 2.9638652399999, "medianEndToEndResponseTime": 12.77865604184614}, "hundredK": {"medianOutputSpeed": 59.2604125899804, "medianTimeToFirstChunk": 5.805152918, "medianTimeToFirstAnswerToken": 5.805152918, "medianEndToEndResponseTime": 14.242488706724135}, "mediumParallel": {"medianOutputSpeed": 50.1183156171585, "medianTimeToFirstChunk": 2.70608624850004, "medianTimeToFirstAnswerToken": 2.70608624850004, "medianEndToEndResponseTime": 12.68247898722209}}, "endToEndResponseTime": {"input": 2.9638652399999, "reasoning": 0, "answer": 9.814790801846241, "total": 12.77865604184614}, "timeToFirstAnswerToken": {"input": 2.9638652399999, "reasoning": 0, "total": 2.9638652399999}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a5092ece-d5a7-461f-b036-3faef262423f", "slug": "gemini-3-deep-think", "name": "Gemini 3 Deep Think", "shortName": "Gemini 3 Deep Think", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-05", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "gemini-3-deep-think", "name": "Gemini 3 Deep Think"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": null, "intelligenceIndexIsEstimated": false, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": 0.257142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a518a64b-e337-48f3-85a1-ba7dc0e8f961", "slug": "ernie-5-0-thinking-preview", "name": "ERNIE 5.0 Thinking Preview", "shortName": "ERNIE 5.0 Thinking Preview", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-13", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "ernie-5-0-thinking-preview", "name": "ERNIE 5.0 Thinking Preview"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 14.2551784975475, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -45.6166666666667, "omniscienceBreakdown": {"accuracy": 0.22133333333333333, "hallucinationRate": 0.8700770547945206}, "gdpval": null, "itBenchSre": null, "tau2": 0.839181286549707, "tauBanking": null, "terminalbenchHard": 0.25, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.413605442176871, "hle": 0.132530120481928, "gpqa": 0.776767676767677, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": 0.645664739884393, "livecodebench": 0.811640211640211, "aime25": 0.85, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "bfb6e769-2456-4027-a6da-e9e05b627a21", "slug": "baidu", "name": "Baidu", "logo": "/img/logos/baidu_small.svg", "color": "#2436d8", "country": "cn", "url": "https://www.baidu.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a550ffca-f89e-4381-ade6-a85dc6a1fb4c", "slug": "kimi-k2-5", "name": "Kimi K2.5 (Reasoning)", "shortName": "Kimi K2.5", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-27", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2968, "release": {"slug": "kimi-k2-5", "name": "Kimi K2.5"}, "deprecated": true, "deprecatedTo": "kimi-k2-6", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1000, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Modified MIT License", "licenseUrl": "https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-K2.5", "microevalsEnabled": false, "intelligenceIndex": 23.458504975068, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -7.33333333333333, "omniscienceBreakdown": {"accuracy": 0.3521666666666667, "hallucinationRate": 0.6568047337278107}, "gdpval": 936.32, "gdpvalNormalized": 0.21816000000000002, "itBenchSre": null, "tau2": 0.95906432748538, "tauBanking": 0.142268041237113, "terminalbenchHard": 0.348484848484849, "terminalBench21": 0.456928838951311, "terminalBench40": null, "scicode": null, "lcr": 0.78, "ifbench": 0.702040816326531, "hle": 0.307228915662651, "gpqa": 0.878787878787879, "critpt": 0.0314285714285714, "apexAgents": 0.11504424778761062, "mmmuPro": 0.753757225433526, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.6, "price1mOutputTokens": 2.75, "cacheHitPrice": 0.35, "cacheHitDiscountPercent": 0.8444444444444444, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.1375, "price1mBlended7To2To1": 0.6399999999999999, "price1mBlended0To1To1": 1.675, "price1mBlended100To1To1": 0.37598039215686274, "price1mBlended0To100To1": 0.6212871287128713, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 6, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a6340098-d7ae-462d-b372-0a0a67fc44b4", "slug": "claude-4-5-haiku-reasoning", "name": "Claude 4.5 Haiku (Reasoning)", "shortName": "Claude 4.5 Haiku", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-15", "knowledgeCutoffDate": "2025-07-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "claude-4-5-haiku", "name": "Claude 4.5 Haiku"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 17.5868602291856, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 15.710485181752649, "strategyAndOps": 11.297850160648231, "legal": 19.733655419893815, "healthcareAndMedical": 16.571910940139144, "engineering": 20.19239721964782, "economics": 27.27078517917824}, "omniscience": -4.36666666666667, "omniscienceBreakdown": {"accuracy": 0.18016666666666667, "hallucinationRate": 0.2730229721488107}, "mlcrOverall": 0.0611111111111111, "harveyLab": 0.610508033000434, "gdpPdfAllPass": 0.038, "gdpval": 854.45, "gdpvalNormalized": 0.17722500000000002, "itBenchSre": 0.273069679849341, "tau2": 0.546783625730994, "tauBanking": 0.0927835051546392, "terminalbenchHard": 0.272727272727273, "terminalBench21": 0.441947565543071, "terminalBench40": 0, "scicode": 0.422453703703704, "lcr": 0.743333333333333, "ifbench": 0.542857142857143, "hle": 0.103799814643188, "gpqa": 0.671717171717172, "critpt": 0, "apexAgents": null, "mmmuPro": 0.585549132947977, "livecodebench": 0.614814814814815, "aime25": 0.836666666666667, "analystAgent": 0.15, "automationBenchPartialScore": 0.03248631462547438, "enterpriseOpsGym": 0.29394210683378097, "price1mInputTokens": 1, "price1mOutputTokens": 5, "cacheHitPrice": 0.1, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 1.25, "pricePer1k1mpImages": 1.334, "price1mBlended0To3To1": 2, "price1mBlended7To2To1": 0.77, "price1mBlended0To1To1": 3, "price1mBlended100To1To1": 0.1568627450980392, "price1mBlended0To100To1": 1.0396039603960396, "intelligenceIndexTimePerTask": 160.5622903772818, "intelligenceIndexCost": {"total": 524.2504021452806, "input": 136.0819571452806, "nonCacheInput": 20.629427, "cacheRead": 42.47464335693212, "cacheWrite": 72.97788678834848, "output": 388.168445, "reasoning": 317.65235, "answer": 70.51609499999999}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.2077123803588505, "input": 0.11528980329406806, "nonCacheInput": 0.013467572851558248, "cacheRead": 0.04203628131148371, "cacheWrite": 0.05978594913102611, "output": 0.09242257706478244, "reasoning": 0.03832474285398434, "answer": 0.05409783421079809}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.051594517344589474}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.019065553908559674}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.003976974259551475}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.08140631957609898}, {"slug": "scicode", "weightedCostPerTask": 0.005102059722222222}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.01244831594068582}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.010893745}, {"slug": "critpt", "weightedCostPerTask": 0.016479362857142858}, {"slug": "omniscience", "weightedCostPerTask": 0.00067818275}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0060673490000000005}]}, "canonicalIntelligenceIndexTokenCount": {"input": 503758170, "output": 77633689, "answer": 14103219, "reasoning": 63530470}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 7664.948570796869, "answer": 10819.566842159622, "output": 18484.51541295649}, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 614.13, "lower95ci": 607.24, "upper95ci": 621.25}, "rubricPassRate": 0.10808080808080808, "analyticalQuality": {"elo": 449.32, "lower95ci": 434.64, "upper95ci": 464.41}, "presentation": {"elo": 671.48, "lower95ci": 657.58, "upper95ci": 684.74}}, "briefcaseTotalCost": 31.300673855717616, "timescaleData": {"medianOutputSpeed": 88.2436070753566, "medianTimeToFirstChunk": 16.9057142914999}, "outputSpeedVariance": {"p05": 61.3392910927106, "q25": 80.4869888166357, "median": 88.2436070753566, "q75": 110.320870511325, "p95": 203.477998684831}, "timeToFirstChunkVariance": {"p05": 4.52282779280005, "q25": 12.564484743, "median": 16.9057142914999, "q75": 33.8137734005, "p95": 58.3044984899}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 101.179487319638, "medianTimeToFirstChunk": 9.266213732, "medianTimeToFirstAnswerToken": 9.266213732, "medianEndToEndResponseTime": 14.20792685237232}, "long": {"medianOutputSpeed": 88.2436070753566, "medianTimeToFirstChunk": 16.9057142914999, "medianTimeToFirstAnswerToken": 16.9057142914999, "medianEndToEndResponseTime": 22.57184713184288}, "hundredK": {"medianOutputSpeed": 86.9477854352418, "medianTimeToFirstChunk": 23.4520563080001, "medianTimeToFirstAnswerToken": 23.4520563080001, "medianEndToEndResponseTime": 29.20263405413944}, "mediumParallel": {"medianOutputSpeed": 104.855963894168, "medianTimeToFirstChunk": 13.7266180775, "medianTimeToFirstAnswerToken": 13.7266180775, "medianEndToEndResponseTime": 18.49506406217145}}, "endToEndResponseTime": {"input": 16.9057142914999, "reasoning": 0, "answer": 5.666132840342978, "total": 22.57184713184288}, "timeToFirstAnswerToken": {"input": 16.9057142914999, "reasoning": 0, "total": 16.9057142914999}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 5, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a68afa0b-7fe2-4e9d-bf3e-741cce3c6aeb", "slug": "granite-4-0-h-350m", "name": "Granite 4.0 H 350M", "shortName": "Granite 4.0 H 350M", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "granite-4-0-h-350m", "name": "Granite 4.0 H 350M"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 0.34, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.0-h-350m", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -80.9166666666667, "omniscienceBreakdown": {"accuracy": 0.038, "hallucinationRate": 0.8806306306306306}, "gdpval": null, "itBenchSre": null, "tau2": 0.146198830409357, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.175510204081633, "hle": 0.0644114921223355, "gpqa": 0.256565656565657, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.019047619047619, "aime25": 0.0133333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 55.55555555555556, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a6ea7ec0-0aca-4442-98fb-4296c6d18b31", "slug": "qwen3-5-0-8b", "name": "Qwen3.5 0.8B (Reasoning)", "shortName": "Qwen3.5 0.8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-5-0-8b", "name": "Qwen3.5 0.8B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 0.873, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-0.8B", "microevalsEnabled": false, "intelligenceIndex": 6.12847840160203, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.5166666666667, "omniscienceBreakdown": {"accuracy": 0.042333333333333334, "hallucinationRate": 0.6134702401670727}, "gdpval": -152.17, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.476608187134503, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": 0, "terminalBench40": null, "scicode": null, "lcr": 0.09, "ifbench": 0.214965986394558, "hle": 0.0106580166821131, "gpqa": 0.111111111111111, "critpt": 0, "apexAgents": null, "mmmuPro": 0.258381502890173, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a71c1a35-ccc8-43f0-a5a2-070a690b9a00", "slug": "apriel-v1-6-15b-thinker", "name": "Apriel-v1.6-15B-Thinker", "shortName": "Apriel-v1.6-15B-Thinker", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-25", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "apriel-v1-6-15b-thinker", "name": "Apriel-v1.6-15B-Thinker"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 15, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit/", "modelWeightsSourceUrl": "https://huggingface.co/ServiceNow-AI/Apriel-1.6-15b-Thinker", "microevalsEnabled": false, "intelligenceIndex": 13.401396407375, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -59.3666666666667, "omniscienceBreakdown": {"accuracy": 0.16966666666666666, "hallucinationRate": 0.9193095142513047}, "gdpval": null, "itBenchSre": null, "tau2": 0.692982456140351, "tauBanking": null, "terminalbenchHard": 0.143939393939394, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.691156462585034, "hle": 0.107970342910102, "gpqa": 0.733333333333333, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.807407407407407, "aime25": 0.88, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "7cc4f2b0-7e34-4459-82fd-667e93ca7f17", "slug": "servicenow", "name": "ServiceNow", "logo": "/img/logos/servicenow_small.svg", "color": "#80B6A1", "country": "us", "url": ""}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a7564055-f8ba-4c4b-9e2d-060f61263645", "slug": "claude-4-sonnet-thinking", "name": "Claude 4 Sonnet (Reasoning)", "shortName": "Claude 4 Sonnet", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-22", "knowledgeCutoffDate": "2025-03-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "claude-4-sonnet", "name": "Claude 4 Sonnet"}, "deprecated": true, "deprecatedTo": "claude-4-5-sonnet-thinking", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 18.9183251073899, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 0.166666666666667, "omniscienceBreakdown": {"accuracy": 0.22683333333333333, "hallucinationRate": 0.2912265574477258}, "gdpval": 818.93, "gdpvalNormalized": 0.15946499999999997, "itBenchSre": null, "tau2": 0.646198830409357, "tauBanking": 0.167010309278351, "terminalbenchHard": 0.310606060606061, "terminalBench21": 0.363295880149813, "terminalBench40": null, "scicode": null, "lcr": 0.703333333333333, "ifbench": 0.546938775510204, "hle": 0.107043558850788, "gpqa": 0.776767676767677, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.617919075144509, "livecodebench": 0.655026455026455, "aime25": 0.743333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a797eaf3-6d75-4f29-86a8-e1243ce52d43", "slug": "gemma-3n-e4b", "name": "Gemma 3n E4B Instruct", "shortName": "Gemma 3n E4B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-26", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-3n-e4b-instruct", "name": "Gemma 3n E4B Instruct"}, "deprecated": true, "deprecatedTo": "gemma-4-e4b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8.39, "inferenceParametersActiveBillions": 4, "sizeClass": "small", "contextWindowTokens": 32000, "licenseName": "Gemma license", "licenseUrl": "https://ai.google.dev/gemma/terms", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-3n-E4B-it", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -81.3333333333333, "omniscienceBreakdown": {"accuracy": 0.07983333333333334, "hallucinationRate": 0.97065748958522}, "gdpval": null, "itBenchSre": null, "tau2": 0.0497076023391813, "tauBanking": 0.00206185567010309, "terminalbenchHard": 0.0227272727272727, "terminalBench21": 0.00749063670411985, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.27891156462585, "hle": 0.0449490268767377, "gpqa": 0.295959595959596, "critpt": 0, "apexAgents": null, "mmmuPro": 0.26242774566474, "livecodebench": 0.146031746031746, "aime25": 0.143333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a803d3d0-d22e-49a0-ac2c-b9c6f1141065", "slug": "qwen3-vl-235b-a22b-reasoning", "name": "Qwen3 VL 235B A22B (Reasoning)", "shortName": "Qwen3 VL 235B A22B (Reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-23", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-vl-235b-a22b", "name": "Qwen3 VL 235B A22B (Reasoning)"}, "deprecated": true, "deprecatedTo": "qwen3-5-397b-a17b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 235, "inferenceParametersActiveBillions": 22, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 13.4375683732418, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -46.55, "omniscienceBreakdown": {"accuracy": 0.2085, "hallucinationRate": 0.8515476942514214}, "gdpval": null, "itBenchSre": null, "tau2": 0.54093567251462, "tauBanking": null, "terminalbenchHard": 0.113636363636364, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.636666666666667, "ifbench": 0.564625850340136, "hle": 0.119091751621872, "gpqa": 0.771717171717172, "critpt": 0, "apexAgents": null, "mmmuPro": 0.68728323699422, "livecodebench": 0.645502645502645, "aime25": 0.883333333333333, "analystAgent": null, "price1mInputTokens": 0.4, "price1mOutputTokens": 4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.716, "price1mBlended0To3To1": 1.3, "price1mBlended7To2To1": 0.76, "price1mBlended0To1To1": 2.2, "price1mBlended100To1To1": 0.43529411764705883, "price1mBlended0To100To1": 0.43564356435643564, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 53.7010846564182, "medianTimeToFirstChunk": 2.86419218449993}, "outputSpeedVariance": {"p05": 42.7851117896243, "q25": 50.397804743741, "median": 53.7010846564182, "q75": 57.5799713669016, "p95": 59.2245115505848}, "timeToFirstChunkVariance": {"p05": 2.66587752489998, "q25": 2.70818139675003, "median": 2.86419218449993, "q75": 4.05908618, "p95": 128.07582887865}, "performanceByPromptType": {"long": {"medianOutputSpeed": 53.7010846564182, "medianTimeToFirstChunk": 2.86419218449993, "medianTimeToFirstAnswerToken": 40.1073877883892, "medianEndToEndResponseTime": 49.41818668936152}}, "endToEndResponseTime": {"input": 2.86419218449993, "reasoning": 37.24319560388927, "answer": 9.310798900972317, "total": 49.41818668936152}, "timeToFirstAnswerToken": {"input": 2.86419218449993, "reasoning": 37.24319560388927, "total": 40.1073877883892}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a83f84b3-473a-4276-9ae1-8909da723159", "slug": "deepseek-r1", "name": "DeepSeek R1 0528 (May '25)", "shortName": "DeepSeek R1 0528", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-r1", "name": "DeepSeek R1 0528 (May '25)"}, "deprecated": true, "deprecatedTo": "deepseek-v3-1-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-0528", "microevalsEnabled": false, "intelligenceIndex": 13.1220574118753, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -27.4333333333333, "omniscienceBreakdown": {"accuracy": 0.30533333333333335, "hallucinationRate": 0.8344529750479847}, "gdpval": null, "itBenchSre": null, "tau2": 0.365497076023392, "tauBanking": null, "terminalbenchHard": 0.159090909090909, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.556666666666667, "ifbench": 0.395918367346939, "hle": 0.158480074142725, "gpqa": 0.813131313131313, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.77037037037037, "aime25": 0.76, "analystAgent": null, "price1mInputTokens": 1.35, "price1mOutputTokens": 3, "cacheHitPrice": 1.35, "cacheHitDiscountPercent": 0.30000000000000004, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.7625000000000002, "price1mBlended7To2To1": 1.5150000000000001, "price1mBlended0To1To1": 2.175, "price1mBlended100To1To1": 1.3661764705882353, "price1mBlended0To100To1": 1.3663366336633664, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 5, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a87fce42-eea3-4e45-a96d-fe057814f371", "slug": "qwen3-7-plus", "name": "Qwen3.7 Plus", "shortName": "Qwen3.7 Plus", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-7-plus", "name": "Qwen3.7 Plus"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 25.8186965821984, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 25.487538219401063, "strategyAndOps": 19.874431007663347, "legal": 28.111960156442223, "healthcareAndMedical": 23.80277951101066, "engineering": 29.445970785038256, "economics": 38.07069647822057}, "omniscience": 1.08333333333333, "omniscienceBreakdown": {"accuracy": 0.22516666666666665, "hallucinationRate": 0.2766186276618628}, "mlcrOverall": 0.0944444444444444, "harveyLab": 0.817918656824432, "gdpPdfAllPass": 0.122, "gdpval": 885.83, "gdpvalNormalized": 0.19291500000000003, "itBenchSre": null, "tau2": 0.929824561403509, "tauBanking": 0.175257731958763, "terminalbenchHard": 0.46969696969697, "terminalBench21": 0.610486891385768, "terminalBench40": 0.0101010101010101, "scicode": 0.460648148148148, "lcr": 0.73, "ifbench": 0.779591836734694, "hle": 0.356348470806302, "gpqa": 0.9, "critpt": 0.0914285714285714, "apexAgents": 0.224188790560472, "mmmuPro": 0.804624277456647, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.17391220980015495, "enterpriseOpsGym": 0.40555058191584603, "price1mInputTokens": 0.4, "price1mOutputTokens": 1.6, "cacheHitPrice": 0.04, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.5, "pricePer1k1mpImages": 0.4104, "price1mBlended0To3To1": 0.7000000000000001, "price1mBlended7To2To1": 0.268, "price1mBlended0To1To1": 1, "price1mBlended100To1To1": 0.058823529411764705, "price1mBlended0To100To1": 0.4118811881188119, "intelligenceIndexTimePerTask": 459.77730149699744, "intelligenceIndexCost": {"total": 568.4915682722101, "input": 352.84258267221, "nonCacheInput": 10.519236800000002, "cacheRead": 23.289274619807824, "cacheWrite": 319.0340712524022, "output": 215.6489856, "reasoning": 188.170528, "answer": 27.478457600000002}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.32527343198119174, "input": 0.2671200908688062, "nonCacheInput": 0.007673486946497344, "cacheRead": 0.018156045901524007, "cacheWrite": 0.24129055802078492, "output": 0.05815334111238546, "reasoning": 0.040276332042005, "answer": 0.017877009070380465}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.053743507803389046}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.00999878529996555}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.014946725880625341}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.20933565910123153}, {"slug": "scicode", "weightedCostPerTask": 0.0013954031944444446}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.006142359944392956}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0063633804}, {"slug": "critpt", "weightedCostPerTask": 0.02064777885714286}, {"slug": "omniscience", "weightedCostPerTask": 0.0004352883}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0022645432}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1246598100, "output": 134780616, "answer": 17174036, "reasoning": 117606580}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 25172.707526253125, "answer": 11173.130668987791, "output": 36345.83819524092}, "briefcaseBreakdown": {"overall": {"elo": 912.73, "lower95ci": 903.47, "upper95ci": 921.37}, "rubricPassRate": 0.22828282828282828, "analyticalQuality": {"elo": 835.11, "lower95ci": 817.27, "upper95ci": 853.67}, "presentation": {"elo": 973.99, "lower95ci": 957.11, "upper95ci": 991.2}}, "briefcaseTotalCost": 32.60439473405602, "timescaleData": {"medianOutputSpeed": 71.0857983548015, "medianTimeToFirstChunk": 2.27767521949994}, "outputSpeedVariance": {"p05": 56.7976605664051, "q25": 64.9554997680152, "median": 71.0857983548015, "q75": 77.0456944159057, "p95": 91.0007422575405}, "timeToFirstChunkVariance": {"p05": 1.87929625150002, "q25": 1.98962240025006, "median": 2.27767521949994, "q75": 2.46293948375006, "p95": 3.08138912679998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 67.1545960756211, "medianTimeToFirstChunk": 1.48419684199999, "medianTimeToFirstAnswerToken": 31.26622393881776, "medianEndToEndResponseTime": 38.711730713022206}, "long": {"medianOutputSpeed": 71.0857983548015, "medianTimeToFirstChunk": 2.27767521949994, "medianTimeToFirstAnswerToken": 30.41269017730705, "medianEndToEndResponseTime": 37.446443916758824}, "hundredK": {"medianOutputSpeed": 65.0481312167261, "medianTimeToFirstChunk": 6.503462168, "medianTimeToFirstAnswerToken": 37.249925787937656, "medianEndToEndResponseTime": 44.93654169292206}, "mediumParallel": {"medianOutputSpeed": 64.8987441233315, "medianTimeToFirstChunk": 1.49872914799994, "medianTimeToFirstAnswerToken": 32.315966476957556, "medianEndToEndResponseTime": 40.02027580919695}}, "endToEndResponseTime": {"input": 2.27767521949994, "reasoning": 28.13501495780711, "answer": 7.033753739451777, "total": 37.446443916758824}, "timeToFirstAnswerToken": {"input": 2.27767521949994, "reasoning": 28.13501495780711, "total": 30.41269017730705}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a89c4b28-2d8c-456e-88ea-255fb51fd2b6", "slug": "gpt-5-4", "name": "GPT-5.4 (xhigh)", "shortName": "GPT-5.4 (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-05", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-4", "name": "GPT-5.4"}, "deprecated": true, "deprecatedTo": "gpt-5-5", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1050000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 38.9755886799637, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 5.78333333333333, "omniscienceBreakdown": {"accuracy": 0.5085, "hallucinationRate": 0.916920990166158}, "gdpval": 1306.71, "gdpvalNormalized": 0.403355, "itBenchSre": null, "tau2": 0.871345029239766, "tauBanking": 0.395876288659794, "terminalbenchHard": 0.575757575757576, "terminalBench21": 0.782771535580524, "terminalBench40": null, "scicode": null, "lcr": 0.82, "ifbench": 0.739455782312925, "hle": 0.437442075996293, "gpqa": 0.92020202020202, "critpt": 0.2342857143, "apexAgents": 0.33259587020649, "mmmuPro": 0.784393063583815, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 2.5, "price1mOutputTokens": 15, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 2.56, "price1mBlended0To3To1": 5.625, "price1mBlended7To2To1": 2.175, "price1mBlended0To1To1": 8.75, "price1mBlended100To1To1": 0.4166666666666667, "price1mBlended0To100To1": 2.623762376237624, "timescaleData": {"medianOutputSpeed": 136.319277528051, "medianTimeToFirstChunk": 121.23336229}, "outputSpeedVariance": {"p05": 72.1685068100855, "q25": 111.86513447535, "median": 136.319277528051, "q75": 145.115712822422, "p95": 180.439035441591}, "timeToFirstChunkVariance": {"p05": 52.04282947, "q25": 61.781541112, "median": 121.23336229, "q75": 176.271378539, "p95": 222.854688676}, "performanceByPromptType": {"long": {"medianOutputSpeed": 136.319277528051, "medianTimeToFirstChunk": 121.23336229, "medianTimeToFirstAnswerToken": 121.23336229, "medianEndToEndResponseTime": 124.90122210459676}}, "endToEndResponseTime": {"input": 121.23336229, "reasoning": 0, "answer": 3.6678598145967496, "total": 124.90122210459676}, "timeToFirstAnswerToken": {"input": 121.23336229, "reasoning": 0, "total": 121.23336229}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 3, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a8c67863-9d66-44dd-8d27-f58654ecde03", "slug": "gemma-3n-e2b", "name": "Gemma 3n E2B Instruct", "shortName": "Gemma 3n E2B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-26", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-3n-e2b-instruct", "name": "Gemma 3n E2B Instruct"}, "deprecated": true, "deprecatedTo": "gemma-4-e2b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 5.98, "inferenceParametersActiveBillions": 2, "sizeClass": "small", "contextWindowTokens": 32000, "licenseName": "Gemma license", "licenseUrl": "https://ai.google.dev/gemma/terms", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-3n-E2B-it", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -80.1666666666667, "omniscienceBreakdown": {"accuracy": 0.06833333333333333, "hallucinationRate": 0.9338103756708408}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.220408163265306, "hle": 0.0417052826691381, "gpqa": 0.229292929292929, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0952380952380952, "aime25": 0.103333333333333, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a8efb564-9d17-4d7f-8f43-e9110657ce21", "slug": "deephermes-3-mistral-24b-preview", "name": "DeepHermes 3 - Mistral 24B Preview (Non-reasoning)", "shortName": "DeepHermes 3 - Mistral 24B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-13", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deephermes-3-mistral-24b-preview", "name": "DeepHermes 3 - Mistral 24B Preview"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 24, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/NousResearch/DeepHermes-3-Mistral-24B-Preview", "microevalsEnabled": false, "intelligenceIndex": 6.07426212371414, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0376, "gpqa": 0.381818181818182, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.194708994708995, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0a2f41cc-2cbc-4949-be54-9fef1319d4a9", "slug": "nous-research", "name": "Nous Research", "logo": "/img/logos/nousresearch_small.jpg", "color": "#006fa8", "country": "us", "url": "https://nousresearch.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "a971b0c0-4c0f-484a-b018-e36b5be3409e", "slug": "reka-flash", "name": "Reka Flash (Sep '24)", "shortName": "Reka Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-10-04", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "reka-flash", "name": "Reka Flash (Sep '24)"}, "deprecated": true, "deprecatedTo": "reka-flash-3", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 21, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.43110884456904, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.35000000000000003, "price1mBlended7To2To1": 0.26000000000000006, "price1mBlended0To1To1": 0.5, "price1mBlended100To1To1": 0.20588235294117646, "price1mBlended0To100To1": 0.20594059405940596, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Reka AI"}, "hostModelCount": 1, "creator": {"id": "4571a280-f096-486f-b220-dffc3e522b0f", "slug": "reka-ai", "name": "Reka AI", "logo": "/img/logos/reka_small.svg", "color": "#172136", "country": "us", "url": "http://reka.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "aa55297e-8fbf-4372-b4ab-9b068dc6396c", "slug": "gpt-5-6-luna-high", "name": "GPT-5.6 Luna (high)", "shortName": "GPT-5.6 Luna (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5-6-luna", "name": "GPT-5.6 Luna"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 32.4147953501091, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 34.543262534935664, "strategyAndOps": 37.31086733748905, "legal": 33.36244000979561, "healthcareAndMedical": 30.053763070323484, "engineering": 31.945086965243597, "economics": 38.37223953506333}, "omniscience": -12, "omniscienceBreakdown": {"accuracy": 0.41783333333333333, "hallucinationRate": 0.9238476953907816}, "mlcrOverall": 0.122222222222222, "gdpPdfAllPass": 0.222, "gdpval": 1375.25, "gdpvalNormalized": 0.437625, "itBenchSre": null, "tau2": null, "tauBanking": 0.251546391752577, "terminalbenchHard": null, "terminalBench21": 0.696629213483146, "terminalBench40": 0.0252525252525253, "scicode": 0.516203703703704, "lcr": 0.803333333333333, "ifbench": null, "hle": 0.334105653382762, "gpqa": 0.891919191919192, "critpt": 0.165714285714286, "apexAgents": null, "mmmuPro": 0.775722543352601, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.3558794293060383, "price1mInputTokens": 0.2, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.02, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.25, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.45, "price1mBlended7To2To1": 0.174, "price1mBlended0To1To1": 0.7, "price1mBlended100To1To1": 0.03333333333333334, "price1mBlended0To100To1": 0.2099009900990099, "intelligenceIndexTimePerTask": 127.3330425643314, "intelligenceIndexCost": {"total": 108.14782653765675, "input": 48.37301973765675, "nonCacheInput": 5.604589600000001, "cacheRead": 24.232064770638544, "cacheWrite": 18.5363653670182, "output": 59.7748068, "reasoning": 45.1028028, "answer": 14.672004}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.043981552251920096, "input": 0.02734702904029932, "nonCacheInput": 0.0043102190483345106, "cacheRead": 0.014294814351833315, "cacheWrite": 0.008741995640131497, "output": 0.01663452321162077, "reasoning": 0.008677733550091568, "answer": 0.007956789661529205}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.01750948496296342}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.004495179904454017}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.002810650635330154}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.010632169881952343}, {"slug": "scicode", "weightedCostPerTask": 0.00029259881944444446}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0009508855977757182}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0040393108}, {"slug": "critpt", "weightedCostPerTask": 0.0018981620000000001}, {"slug": "omniscience", "weightedCostPerTask": 0.00037499445}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0009781152000000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1313771648, "output": 49812339, "answer": 12226670, "reasoning": 37585669}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 7231.444625076305, "answer": 6630.658051274337, "output": 13862.102676350642}, "briefcaseBreakdown": {"overall": {"elo": 1173.05, "lower95ci": 1164.6, "upper95ci": 1181.37}, "rubricPassRate": 0.298989898989899, "analyticalQuality": {"elo": 1139.54, "lower95ci": 1125.22, "upper95ci": 1154.47}, "presentation": {"elo": 1322.73, "lower95ci": 1307.08, "upper95ci": 1338.19}}, "briefcaseTotalCost": 10.622420877531141, "timescaleData": {"medianOutputSpeed": 114.20091711512, "medianTimeToFirstChunk": 8.47044271949999}, "outputSpeedVariance": {"p05": 87.6647350058228, "q25": 99.2121771195027, "median": 114.20091711512, "q75": 128.810573340756, "p95": 163.673652118862}, "timeToFirstChunkVariance": {"p05": 4.07457026095002, "q25": 5.34460720900012, "median": 8.47044271949999, "q75": 16.0806803212499, "p95": 47.49089297495}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 118.167746453807, "medianTimeToFirstChunk": 8.36287819899999, "medianTimeToFirstAnswerToken": 8.36287819899999, "medianEndToEndResponseTime": 12.594151240967115}, "long": {"medianOutputSpeed": 114.20091711512, "medianTimeToFirstChunk": 8.47044271949999, "medianTimeToFirstAnswerToken": 8.47044271949999, "medianEndToEndResponseTime": 12.848691271531985}, "hundredK": {"medianOutputSpeed": 100.860457726173, "medianTimeToFirstChunk": 8.7934724075, "medianTimeToFirstAnswerToken": 8.7934724075, "medianEndToEndResponseTime": 13.750816556754753}, "mediumParallel": {"medianOutputSpeed": 118.659480515268, "medianTimeToFirstChunk": 32.1006947065001, "medianTimeToFirstAnswerToken": 32.1006947065001, "medianEndToEndResponseTime": 36.314433025838724}}, "endToEndResponseTime": {"input": 8.47044271949999, "reasoning": 0, "answer": 4.3782485520319945, "total": 12.848691271531985}, "timeToFirstAnswerToken": {"input": 8.47044271949999, "reasoning": 0, "total": 8.47044271949999}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "aa83359a-d804-4f0b-b5bf-dc637711c26f", "slug": "llama-3-instruct-70b", "name": "Llama 3 Instruct 70B", "shortName": "Llama 3 70B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-04-18", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-instruct-70b", "name": "Llama 3 Instruct 70B"}, "deprecated": true, "deprecatedTo": "llama-3-1-instruct-70b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 8192, "licenseName": "META LLAMA 3 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://llama.meta.com/llama3/license/", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 5.45277882640287, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.3166666666667, "omniscienceBreakdown": {"accuracy": 0.17716666666666667, "hallucinationRate": 0.8754304233340086}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.370748299319728, "hle": 0.0452, "gpqa": 0.378787878787879, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.197883597883598, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.65, "price1mOutputTokens": 2.75, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.175, "price1mBlended7To2To1": 0.86, "price1mBlended0To1To1": 1.7, "price1mBlended100To1To1": 0.6705882352941177, "price1mBlended0To100To1": 0.6707920792079208, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 3, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ab7f016c-a29b-4710-bdf6-6a5cd96aacca", "slug": "nvidia-nemotron-nano-12b-v2-vl", "name": "NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)", "shortName": "NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "nvidia-nemotron-nano-12b-v2-vl", "name": "NVIDIA Nemotron Nano 12B v2 VL"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 13.2, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Nvidia Open Model License", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16", "microevalsEnabled": false, "intelligenceIndex": 5.82045753777258, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -72.2333333333333, "omniscienceBreakdown": {"accuracy": 0.11916666666666667, "hallucinationRate": 0.9553453169347209}, "gdpval": null, "itBenchSre": null, "tau2": 0.192982456140351, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.206666666666667, "ifbench": 0.258503401360544, "hle": 0.0426320667284523, "gpqa": 0.439393939393939, "critpt": 0, "apexAgents": null, "mmmuPro": 0.445086705202312, "livecodebench": 0.344973544973545, "aime25": 0.266666666666667, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.30000000000000004, "price1mBlended7To2To1": 0.24000000000000005, "price1mBlended0To1To1": 0.4, "price1mBlended100To1To1": 0.20392156862745098, "price1mBlended0To100To1": 0.20396039603960398, "openness": {"opennessIndex": 72.22222222222223, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {"medianOutputSpeed": 197.365287650019, "medianTimeToFirstChunk": 1.73433330899997}, "outputSpeedVariance": {"p05": 13.6763958504586, "q25": 91.843505311191, "median": 197.365287650019, "q75": 203.396384140117, "p95": 252.786064871783}, "timeToFirstChunkVariance": {"p05": 1.03722209465009, "q25": 1.09687862800004, "median": 1.73433330899997, "q75": 9.05718837100005, "p95": 30.717383452}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 189.274462686916, "medianTimeToFirstChunk": 1.61068048400001, "medianTimeToFirstAnswerToken": 1.61068048400001, "medianEndToEndResponseTime": 4.252346944979817}, "long": {"medianOutputSpeed": 197.365287650019, "medianTimeToFirstChunk": 1.73433330899997, "medianTimeToFirstAnswerToken": 1.73433330899997, "medianEndToEndResponseTime": 4.267706861935137}, "hundredK": {"medianOutputSpeed": 122.418134858869, "medianTimeToFirstChunk": 7.77350271399996, "medianTimeToFirstAnswerToken": 7.77350271399996, "medianEndToEndResponseTime": 11.857864892662706}, "mediumParallel": {"medianOutputSpeed": 180.045480215529, "medianTimeToFirstChunk": 2.3347674255, "medianTimeToFirstAnswerToken": 2.3347674255, "medianEndToEndResponseTime": 5.111843525391313}}, "endToEndResponseTime": {"input": 1.73433330899997, "reasoning": 0, "answer": 2.5333735529351675, "total": 4.267706861935137}, "timeToFirstAnswerToken": {"input": 1.73433330899997, "reasoning": 0, "total": 1.73433330899997}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "aba82268-2bb7-4a0f-80be-9b7722e2145b", "slug": "devstral-medium", "name": "Devstral Medium", "shortName": "Devstral Medium", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-10", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "devstral-medium", "name": "Devstral Medium"}, "deprecated": true, "deprecatedTo": "devstral-2", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.0057933497923, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -31.5666666666667, "omniscienceBreakdown": {"accuracy": 0.18883333333333333, "hallucinationRate": 0.6219437024861311}, "gdpval": null, "itBenchSre": null, "tau2": 0.198830409356725, "tauBanking": null, "terminalbenchHard": 0.0909090909090909, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.32, "ifbench": 0.299319727891156, "hle": 0.0375347544022243, "gpqa": 0.491919191919192, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.336507936507937, "aime25": 0.0466666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "abe9f0c7-f4f6-430d-ba42-f45afdd4841b", "slug": "command-r-03-2024", "name": "Command-R (Mar '24)", "shortName": "Command-R (Mar)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-03-12", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "command-r-03-2024", "name": "Command-R (Mar '24)"}, "deprecated": true, "deprecatedTo": "command-r-plus-04-2024", "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 35, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "CC-BY-NC 4.0 License with Acceptable Use Addendum", "licenseUrl": "https://cohere.com/c4ai-cc-by-nc-license", "modelWeightsSourceUrl": "https://huggingface.co/CohereForAI/c4ai-command-r-v01", "microevalsEnabled": false, "intelligenceIndex": 5.03498213171439, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0479, "gpqa": 0.283838383838384, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0476190476190476, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "671d3708-c407-4b8f-b350-f728e4689d26", "slug": "cohere", "name": "Cohere", "logo": "/img/logos/cohere_small.svg", "color": "#D18EE2", "country": "ca", "url": "https://cohere.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ac1031bc-c53e-4af7-9c6e-2005e0ff44fa", "slug": "apriel-v1-5-15b-thinker", "name": "Apriel-v1.5-15B-Thinker", "shortName": "Apriel-v1.5-15B-Thinker", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "apriel-v1-5-15b-thinker", "name": "Apriel-v1.5-15B-Thinker"}, "deprecated": true, "deprecatedTo": "apriel-v1-6-15b-thinker", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 15, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/ServiceNow-AI/Apriel-1.5-15b-Thinker", "microevalsEnabled": false, "intelligenceIndex": 13.824080582574, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -54.8, "omniscienceBreakdown": {"accuracy": 0.1645, "hallucinationRate": 0.8527827648114902}, "gdpval": null, "itBenchSre": null, "tau2": 0.684210526315789, "tauBanking": null, "terminalbenchHard": 0.106060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.213333333333333, "ifbench": 0.617006802721088, "hle": 0.121408711770158, "gpqa": 0.713131313131313, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": 0.570520231213873, "livecodebench": 0.728042328042328, "aime25": 0.875, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 47.22222222222222, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "7cc4f2b0-7e34-4459-82fd-667e93ca7f17", "slug": "servicenow", "name": "ServiceNow", "logo": "/img/logos/servicenow_small.svg", "color": "#80B6A1", "country": "us", "url": ""}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ac48c49d-9e77-4394-ac4e-d1ee51fd5fee", "slug": "gemini-1-5-flash-may-2024", "name": "Gemini 1.5 Flash (May '24)", "shortName": "Gemini 1.5 Flash (May)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-05-14", "knowledgeCutoffDate": "2023-11-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-1-5-flash-may-24", "name": "Gemini 1.5 Flash (May '24)"}, "deprecated": true, "deprecatedTo": "gemini-1-5-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.93750542104558, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0436, "gpqa": 0.324242424242424, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.195767195767196, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "aca9c1ad-fc86-49f3-a312-b1e517ea100c", "slug": "claude-35-sonnet-june-24", "name": "Claude 3.5 Sonnet (June '24)", "shortName": "Claude 3.5 Sonnet (June)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-06-21", "knowledgeCutoffDate": "2024-04-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-35-sonnet-june-24", "name": "Claude 3.5 Sonnet (June '24)"}, "deprecated": true, "deprecatedTo": "claude-3-7-sonnet", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.20987771468693, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0323, "gpqa": 0.55959595959596, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 3.75, "pricePer1k1mpImages": 4, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 2.31, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 0.47058823529411764, "price1mBlended0To100To1": 3.118811881188119, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "acad0665-9457-4531-abd5-b59efd7a89ea", "slug": "step-3-vl-10b", "name": "Step3 VL 10B", "shortName": "Step3 VL 10B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "step3-vl-10b", "name": "Step3 VL 10B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 10.2, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 65536, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/stepfun-ai/Step3-VL-10B", "microevalsEnabled": false, "intelligenceIndex": 7.69391371030502, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -59, "omniscienceBreakdown": {"accuracy": 0.13266666666666665, "hallucinationRate": 0.8332052267486548}, "gdpval": null, "itBenchSre": null, "tau2": 0.160818713450292, "tauBanking": null, "terminalbenchHard": 0.053030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.502040816326531, "hle": 0.108433734939759, "gpqa": 0.68989898989899, "critpt": 0, "apexAgents": null, "mmmuPro": 0.639884393063584, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 41.666666666666664, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "ce2e2e8b-7a22-4020-98ec-8ef71000dd42", "slug": "stepfun", "name": "StepFun", "logo": "/img/logos/stepfun_small.svg", "color": "#017AFF", "country": "cn", "url": "https://www.stepfun.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ad173c8d-f14f-4230-90e9-60979b7720e7", "slug": "deepseek-v4-flash-0420-non-reasoning", "name": "DeepSeek V4 Flash 0420 (Non-reasoning)", "shortName": "DeepSeek V4 Flash (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-24", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v4-flash-0420", "name": "DeepSeek V4 Flash 0420"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 284, "inferenceParametersActiveBillions": 13, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash", "microevalsEnabled": false, "intelligenceIndex": 18.8769056307071, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -43.9666666666667, "omniscienceBreakdown": {"accuracy": 0.26, "hallucinationRate": 0.9454954954954955}, "gdpval": null, "itBenchSre": null, "tau2": 0.944444444444445, "tauBanking": null, "terminalbenchHard": 0.340909090909091, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.416666666666667, "ifbench": 0.472108843537415, "hle": 0.0778498609823911, "gpqa": 0.716161616161616, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.0938, "price1mOutputTokens": 0.195, "cacheHitPrice": 0.07, "cacheHitDiscountPercent": 0.6487206823027718, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.1191, "price1mBlended7To2To1": 0.08726, "price1mBlended0To1To1": 0.1444, "price1mBlended100To1To1": 0.07145882352941177, "price1mBlended0To100To1": 0.09480198019801979, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 3, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "adf9a85e-abc3-4f28-937b-db6655cc5238", "slug": "llama-4-scout", "name": "Llama 4 Scout", "shortName": "Llama 4 Scout", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-05", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-4-scout", "name": "Llama 4 Scout"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 109, "inferenceParametersActiveBillions": 17, "sizeClass": "medium", "contextWindowTokens": 10000000, "licenseName": "LLAMA 4 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://www.llama.com/llama4/license/", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Llama-4-Scout-17B-16E-Instruct", "microevalsEnabled": true, "intelligenceIndex": 6.45126865234633, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 6.6057241579558665, "strategyAndOps": 4.932647435628177, "legal": 8.061191096634094, "engineering": 9.457, "economics": 10.547999999999998}, "omniscience": -52.15, "omniscienceBreakdown": {"accuracy": 0.15166666666666667, "hallucinationRate": 0.793516699410609}, "gdpPdfAllPass": 0, "gdpval": 59.71, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.154970760233918, "tauBanking": 0.0329896907216495, "terminalbenchHard": 0.0151515151515152, "terminalBench21": 0.0374531835205993, "terminalBench40": 0, "scicode": 0.212962962962963, "lcr": 0.277, "ifbench": 0.395238095238095, "hle": 0.0378, "gpqa": 0.586868686868687, "critpt": 0, "apexAgents": null, "mmmuPro": 0.529479768786127, "livecodebench": 0.299470899470899, "aime25": 0.14, "analystAgent": null, "automationBenchPartialScore": 0.0019111706206154657, "price1mInputTokens": 0.19, "price1mOutputTokens": 0.6799999999999999, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.24684, "price1mBlended0To3To1": 0.3125, "price1mBlended7To2To1": 0.23899999999999996, "price1mBlended0To1To1": 0.43499999999999994, "price1mBlended100To1To1": 0.19480392156862747, "price1mBlended0To100To1": 0.19485148514851486, "intelligenceIndexTimePerTask": 19.719227200410216, "intelligenceIndexCost": {"total": 77.58221322000001, "input": 74.92945298000001, "nonCacheInput": 1.02363089, "cacheRead": 0, "cacheWrite": 73.90582209, "output": 2.6527602399999997, "reasoning": 0, "answer": 2.6527602399999997}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.11837614517613876, "input": 0.1170718316942674, "nonCacheInput": 0.00041902840768882123, "cacheRead": 0, "cacheWrite": 0.11665280328657858, "output": 0.0013043134818713667, "reasoning": 0, "answer": 0.0013043134818713667}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.11542735453846154}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0020163048090909093}, {"slug": "automationbench-aa", "weightedCostPerTask": 9.35284398782344e-06}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.00025229436363636366}, {"slug": "scicode", "weightedCostPerTask": 9.518728819444445e-05}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 7.246960194624651e-05}, {"slug": "gdp-pdf", "weightedCostPerTask": 3.129196e-05}, {"slug": "critpt", "weightedCostPerTask": 0.0001915831285714286}, {"slug": "omniscience", "weightedCostPerTask": 7.0251772499999995e-06}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.000273281465}]}, "canonicalIntelligenceIndexTokenCount": {"input": 394365542, "output": 3901118, "answer": 3901118, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 1918.1080615755395, "output": 1918.1080615755395}, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "rubricPassRate": 0.007164790174002047, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 70.02592842, "timescaleData": {"medianOutputSpeed": 103.025118718727, "medianTimeToFirstChunk": 0.85489867800004}, "outputSpeedVariance": {"p05": 17.1686536289728, "q25": 41.3604450518305, "median": 103.025118718727, "q75": 142.618490908039, "p95": 200.859088202488}, "timeToFirstChunkVariance": {"p05": 0.550058386499881, "q25": 0.74347628400001, "median": 0.85489867800004, "q75": 1.07290115499998, "p95": 2.4938240458}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 103.631419098727, "medianTimeToFirstChunk": 0.600078367000037, "medianTimeToFirstAnswerToken": 0.600078367000037, "medianEndToEndResponseTime": 5.424869963491279}, "long": {"medianOutputSpeed": 103.025118718727, "medianTimeToFirstChunk": 0.85489867800004, "medianTimeToFirstAnswerToken": 0.85489867800004, "medianEndToEndResponseTime": 5.708084058597077}, "hundredK": {"medianOutputSpeed": 94.0621998300261, "medianTimeToFirstChunk": 3.61333147000002, "medianTimeToFirstAnswerToken": 3.61333147000002, "medianEndToEndResponseTime": 8.928963051055094}, "mediumParallel": {"medianOutputSpeed": 69.0972619841313, "medianTimeToFirstChunk": 0.634662783999943, "medianTimeToFirstAnswerToken": 0.634662783999943, "medianEndToEndResponseTime": 7.870839524473809}}, "endToEndResponseTime": {"input": 0.85489867800004, "reasoning": 0, "answer": 4.853185380597036, "total": 5.708084058597077}, "timeToFirstAnswerToken": {"input": 0.85489867800004, "reasoning": 0, "total": 0.85489867800004}, "performanceDataSource": {"type": "median"}, "hostModelCount": 6, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "adfae555-f489-4f3e-9064-c6b7fcdd0783", "slug": "granite-4-2-8b", "name": "Granite 4.2 8B", "shortName": "Granite 4.2 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-25", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "granite-4-2-8b", "name": "Granite 4.2 8B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.2-8b", "microevalsEnabled": false, "intelligenceIndex": 11.8124212267815, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 11.271299787521082, "strategyAndOps": 6.2800385637723135, "legal": 14.946199453283823, "engineering": 17.37594115583212, "economics": 22.453900196941614}, "omniscience": -17.1666666666667, "omniscienceBreakdown": {"accuracy": 0.11216666666666666, "hallucinationRate": 0.3196921344096114}, "gdpPdfAllPass": 0.006, "gdpval": 645.07, "gdpvalNormalized": 0.07253500000000003, "itBenchSre": null, "tau2": null, "tauBanking": 0.0762886597938144, "terminalbenchHard": null, "terminalBench21": 0.183520599250936, "terminalBench40": 0, "scicode": 0.314814814814815, "lcr": 0.45, "ifbench": null, "hle": 0.0968489341983318, "gpqa": 0.631313131313131, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.020571262692004582, "price1mInputTokens": 0.06, "price1mOutputTokens": 0.25, "cacheHitPrice": 0.015, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.1075, "price1mBlended7To2To1": 0.0475, "price1mBlended0To1To1": 0.155, "price1mBlended100To1To1": 0.017745098039215687, "price1mBlended0To100To1": 0.06188118811881188, "intelligenceIndexTimePerTask": 374.07194355532454, "intelligenceIndexCost": {"total": 53.071828850058004, "input": 21.646939100058002, "nonCacheInput": 0.8761446, "cacheRead": 16.641923473313998, "cacheWrite": 4.128871026744005, "output": 31.424889750000002, "reasoning": 26.36749675, "answer": 5.057393}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.023596091491929188, "input": 0.015246413095103268, "nonCacheInput": 0.00046340370175782246, "cacheRead": 0.01185625788148534, "cacheWrite": 0.002926751511860106, "output": 0.008349678396825922, "reasoning": 0.005454998589594112, "answer": 0.00289467980723181}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.01326289280389121}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.002632363087024091}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0010967382962484022}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.003987194739707576}, {"slug": "scicode", "weightedCostPerTask": 0.00025393956944444446}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0005621514596848934}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00029667706}, {"slug": "critpt", "weightedCostPerTask": 0.0009213470714285716}, {"slug": "omniscience", "weightedCostPerTask": 0.0001900530545}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00039273434999999995}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1192878492, "output": 125699559, "answer": 20229572, "reasoning": 105469987}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 21819.994358376447, "answer": 11578.71922892724, "output": 33398.71358730369}, "openness": {"opennessIndex": 72.22222222222223, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "briefcaseBreakdown": {"overall": {"elo": 320.12, "lower95ci": 310.04, "upper95ci": 328.99}, "rubricPassRate": 0.07272727272727272, "analyticalQuality": {"elo": 171.15, "lower95ci": 152.36, "upper95ci": 188.74}, "presentation": {"elo": 157.12, "lower95ci": 138.61, "upper95ci": 175.1}}, "briefcaseTotalCost": 8.046154967694001, "timescaleData": {"medianOutputSpeed": 90.801211759614, "medianTimeToFirstChunk": 0.635346571000127}, "outputSpeedVariance": {"p05": 39.4799301193315, "q25": 57.4172223766402, "median": 90.801211759614, "q75": 114.828841515285, "p95": 144.146719153998}, "timeToFirstChunkVariance": {"p05": 0.533698753600027, "q25": 0.603610787999997, "median": 0.635346571000127, "q75": 0.667909362500041, "p95": 0.996666620599998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 78.1377602658843, "medianTimeToFirstChunk": 0.283875498, "medianTimeToFirstAnswerToken": 25.879694896898478, "medianEndToEndResponseTime": 32.278649746623095}, "long": {"medianOutputSpeed": 90.801211759614, "medianTimeToFirstChunk": 0.635346571000127, "medianTimeToFirstAnswerToken": 22.661484342099207, "medianEndToEndResponseTime": 28.168018784873976}, "hundredK": {"medianOutputSpeed": 66.2144093073562, "medianTimeToFirstChunk": 9.0320267204999, "medianTimeToFirstAnswerToken": 39.23693258496718, "medianEndToEndResponseTime": 46.788159051083994}, "mediumParallel": {"medianOutputSpeed": 66.6118857218661, "medianTimeToFirstChunk": 0.450382251000008, "medianTimeToFirstAnswerToken": 30.475053949244355, "medianEndToEndResponseTime": 37.981221873805445}}, "endToEndResponseTime": {"input": 0.635346571000127, "reasoning": 22.02613777109908, "answer": 5.50653444277477, "total": 28.168018784873976}, "timeToFirstAnswerToken": {"input": 0.635346571000127, "reasoning": 22.02613777109908, "total": 22.661484342099207}, "performanceDataSource": {"type": "firstParty", "providerName": "IBM"}, "hostModelCount": 2, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ae447455-940d-4d30-9139-a664fa896eaf", "slug": "gpt-5-4-mini-non-reasoning", "name": "GPT-5.4 mini (Non-Reasoning)", "shortName": "GPT-5.4 mini (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-17", "knowledgeCutoffDate": "2025-08-31", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-5-4-mini", "name": "GPT-5.4 mini"}, "deprecated": true, "deprecatedTo": "gpt-5-6-terra-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.1447193424847, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -45.4166666666667, "omniscienceBreakdown": {"accuracy": 0.2565, "hallucinationRate": 0.9558394978704327}, "gdpval": 734.27, "gdpvalNormalized": 0.11713499999999999, "itBenchSre": 0.186440677966102, "tau2": 0.233918128654971, "tauBanking": null, "terminalbenchHard": 0.181818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.37, "ifbench": 0.38843537414966, "hle": 0.0588507877664504, "gpqa": 0.606060606060606, "critpt": 0, "apexAgents": null, "mmmuPro": 0.604624277456647, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.75, "price1mOutputTokens": 4.5, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 1.24, "price1mBlended0To3To1": 1.6875, "price1mBlended7To2To1": 0.6525000000000001, "price1mBlended0To1To1": 2.625, "price1mBlended100To1To1": 0.125, "price1mBlended0To100To1": 0.7871287128712872, "timescaleData": {"medianOutputSpeed": 184.757803375044, "medianTimeToFirstChunk": 0.81300911749986}, "outputSpeedVariance": {"p05": 107.60767369066, "q25": 151.869928241443, "median": 184.757803375044, "q75": 207.505286652028, "p95": 238.983819209988}, "timeToFirstChunkVariance": {"p05": 0.569385672400233, "q25": 0.711969853749998, "median": 0.81300911749986, "q75": 0.979468862000033, "p95": 1.29263488150001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 184.757803375044, "medianTimeToFirstChunk": 0.81300911749986, "medianTimeToFirstAnswerToken": 0.81300911749986, "medianEndToEndResponseTime": 3.519254758367536}}, "endToEndResponseTime": {"input": 0.81300911749986, "reasoning": 0, "answer": 2.706245640867676, "total": 3.519254758367536}, "timeToFirstAnswerToken": {"input": 0.81300911749986, "reasoning": 0, "total": 0.81300911749986}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ae4fe623-80ab-4ea3-8921-70a18ea0fc7e", "slug": "ernie-4-5-300b-a47b", "name": "ERNIE 4.5 300B A47B", "shortName": "ERNIE 4.5 300B A47B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "ernie-4-5-300b-a47b", "name": "ERNIE 4.5 300B A47B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 300, "inferenceParametersActiveBillions": 47, "sizeClass": "large", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/baidu/ERNIE-4.5-300B-A47B-Paddle", "microevalsEnabled": false, "intelligenceIndex": 7.50448042633837, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -35.1333333333333, "omniscienceBreakdown": {"accuracy": 0.1905, "hallucinationRate": 0.6693432159769405}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.0606060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.391156462585034, "hle": 0.0333642261353105, "gpqa": 0.811111111111111, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.466666666666667, "aime25": 0.413333333333333, "analystAgent": null, "price1mInputTokens": 0.28, "price1mOutputTokens": 1.1, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.48500000000000004, "price1mBlended7To2To1": 0.36200000000000004, "price1mBlended0To1To1": 0.6900000000000001, "price1mBlended100To1To1": 0.28803921568627455, "price1mBlended0To100To1": 0.28811881188118815, "openness": {"opennessIndex": 55.55555555555556, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "bfb6e769-2456-4027-a6da-e9e05b627a21", "slug": "baidu", "name": "Baidu", "logo": "/img/logos/baidu_small.svg", "color": "#2436d8", "country": "cn", "url": "https://www.baidu.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "af134350-8ba3-4629-b56b-00bd6dcf60c4", "slug": "deepseek-v3-2-reasoning-0925", "name": "DeepSeek V3.2 Exp (Reasoning)", "shortName": "DeepSeek V3.2 Exp", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-29", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-v3-2-0925", "name": "DeepSeek V3.2 Exp"}, "deprecated": true, "deprecatedTo": "deepseek-v3-2-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2-Exp", "microevalsEnabled": false, "intelligenceIndex": 16.579440992188, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -30.9666666666667, "omniscienceBreakdown": {"accuracy": 0.2755, "hallucinationRate": 0.8076834598573729}, "gdpval": null, "itBenchSre": null, "tau2": 0.339181286549708, "tauBanking": null, "terminalbenchHard": 0.310606060606061, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.723333333333333, "ifbench": 0.541496598639456, "hle": 0.148748841519926, "gpqa": 0.796969696969697, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.789417989417989, "aime25": 0.876666666666667, "analystAgent": null, "price1mInputTokens": 0.28, "price1mOutputTokens": 0.42, "cacheHitPrice": 0.028, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.315, "price1mBlended7To2To1": 0.1176, "price1mBlended0To1To1": 0.35, "price1mBlended100To1To1": 0.03431372549019608, "price1mBlended0To100To1": 0.2813861386138614, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 2, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "af74f222-05c7-422d-a653-b9c0707c9c72", "slug": "molmo-7b-d", "name": "Molmo 7B-D", "shortName": "Molmo 7B-D", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-25", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "molmo-7b-d", "name": "Molmo 7B-D"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8.02, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 4096, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/allenai/Molmo-7B-D-0924", "microevalsEnabled": false, "intelligenceIndex": 5.56262049746202, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.196598639455782, "hle": 0.051436515291937, "gpqa": 0.24040404040404, "critpt": null, "apexAgents": null, "mmmuPro": 0.245086705202312, "livecodebench": 0.0391534391534391, "aime25": 0, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "ab6c5270-d7b9-4c09-92fe-62662618c631", "slug": "ai2", "name": "Allen Institute for AI", "logo": "/img/logos/ai2_small.svg", "color": "#F0529C", "country": "us", "url": "https://allenai.org/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b00ecd62-a53f-4aed-b833-3e9d6b0170ba", "slug": "qwen3-32b-instruct-reasoning", "name": "Qwen3 32B (Reasoning)", "shortName": "Qwen3 32B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-32b-instruct", "name": "Qwen3 32B"}, "deprecated": true, "deprecatedTo": "qwen3-30b-a3b-2507-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32.8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-32B", "microevalsEnabled": false, "intelligenceIndex": 7.21522513523226, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 6.972744764022645, "strategyAndOps": 4.409455873090455, "legal": 7.110879842218258, "engineering": 12.161857142857142, "economics": 11.5885}, "omniscience": -50.3666666666667, "omniscienceBreakdown": {"accuracy": 0.17433333333333334, "hallucinationRate": 0.8211546225272507}, "gdpPdfAllPass": 0.016, "gdpval": 239.65, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.298245614035088, "tauBanking": 0.0536082474226804, "terminalbenchHard": 0.0303030303030303, "terminalBench21": 0.052434456928839, "terminalBench40": 0, "scicode": 0.359953703703704, "lcr": 0, "ifbench": 0.363265306122449, "hle": 0.0741, "gpqa": 0.667676767676768, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.546031746031746, "aime25": 0.73, "analystAgent": null, "automationBenchPartialScore": 0.009711289785341921, "price1mInputTokens": 0.16, "price1mOutputTokens": 0.64, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.28, "price1mBlended7To2To1": 0.20800000000000002, "price1mBlended0To1To1": 0.4, "price1mBlended100To1To1": 0.16470588235294117, "price1mBlended0To100To1": 0.16475247524752476, "briefcaseBreakdown": {"overall": {"elo": 9.49, "lower95ci": 0, "upper95ci": 19.23}, "rubricPassRate": 0.03939393939393939, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 3.05104496, "timescaleData": {"medianOutputSpeed": 104.95967742636, "medianTimeToFirstChunk": 2.51087233850001}, "outputSpeedVariance": {"p05": 92.7975565060003, "q25": 100.043709741814, "median": 104.95967742636, "q75": 106.540652942099, "p95": 107.891375428964}, "timeToFirstChunkVariance": {"p05": 2.37005107429998, "q25": 2.4076420375, "median": 2.51087233850001, "q75": 2.83088963050001, "p95": 3.51909008269991}, "performanceByPromptType": {"long": {"medianOutputSpeed": 104.95967742636, "medianTimeToFirstChunk": 2.51087233850001, "medianTimeToFirstAnswerToken": 21.565808948830256, "medianEndToEndResponseTime": 26.329543101412813}}, "endToEndResponseTime": {"input": 2.51087233850001, "reasoning": 19.054936610330245, "answer": 4.763734152582561, "total": 26.329543101412813}, "timeToFirstAnswerToken": {"input": 2.51087233850001, "reasoning": 19.054936610330245, "total": 21.565808948830256}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 3, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b01dee41-c62b-48ed-8d16-984adc405e5c", "slug": "qwen3-8-27b", "name": "Qwen3.8 27B (xhigh)", "shortName": "Qwen3.8 27B (xhigh)", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-08-14", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "qwen3-8-27b", "name": "Qwen3.8 27B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 27, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.8-27B", "microevalsEnabled": true, "intelligenceIndex": 33.9015108057476, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 34.708955944738676, "strategyAndOps": 37.482710147238954, "legal": 34.9103943715945, "healthcareAndMedical": 34.73166931152048, "engineering": 33.523513533253904, "economics": 43.10879129981465}, "omniscience": -9.98333333333333, "omniscienceBreakdown": {"accuracy": 0.15583333333333332, "hallucinationRate": 0.30286278381046394}, "mlcrOverall": 0.216666666666667, "gdpPdfAllPass": 0.164, "gdpval": 1463.25, "gdpvalNormalized": 0.481625, "itBenchSre": null, "tau2": null, "tauBanking": 0.480412371134021, "terminalbenchHard": null, "terminalBench21": 0.797752808988764, "terminalBench40": 0.0555555555555556, "scicode": 0.466435185185185, "lcr": 0.82, "ifbench": null, "hle": 0.33920296570899, "gpqa": 0.905050505050505, "critpt": 0.0542857142857143, "apexAgents": null, "mmmuPro": 0.763005780346821, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.48242443682241926, "enterpriseOpsGym": 0.4422560429722471, "price1mInputTokens": 0.5, "price1mOutputTokens": 3, "cacheHitPrice": 0.05, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.125, "price1mBlended7To2To1": 0.43499999999999994, "price1mBlended0To1To1": 1.75, "price1mBlended100To1To1": 0.08333333333333333, "price1mBlended0To100To1": 0.5247524752475248, "intelligenceIndexTimePerTask": 1070.1029806839247, "intelligenceIndexCost": {"total": 1170.4762441505, "input": 575.6469901505001, "nonCacheInput": 13.2577295, "cacheRead": 165.6169557055, "cacheWrite": 396.77230494500003, "output": 594.829254, "reasoning": 512.301918, "answer": 82.52733599999999}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.8201941361505801, "input": 0.6198444445967706, "nonCacheInput": 0.009409775503558189, "cacheRead": 0.18729555800601444, "cacheWrite": 0.4231391110871978, "output": 0.20034969155380952, "reasoning": 0.14307484119862238, "answer": 0.057274850355187125}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.3402482930035715}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0919042206475}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.011175505282686453}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.3105989197818182}, {"slug": "scicode", "weightedCostPerTask": 0.006447482291666667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.013257006232622798}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0096274365}, {"slug": "critpt", "weightedCostPerTask": 0.032172249285714286}, {"slug": "omniscience", "weightedCostPerTask": 0.0016762956249999996}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0030867275000000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4132399183, "output": 198276418, "answer": 27509112, "reasoning": 170767306}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 47691.613732874124, "answer": 19091.61678506237, "output": 66783.23051793649}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1397.82, "lower95ci": 1391.1, "upper95ci": 1404.61}, "rubricPassRate": 0.4780388151174668, "analyticalQuality": {"elo": 1581.31, "lower95ci": 1567.95, "upper95ci": 1593.95}, "presentation": {"elo": 1278.57, "lower95ci": 1266.26, "upper95ci": 1290.48}}, "briefcaseTotalCost": 206.41729775550004, "timescaleData": {"medianOutputSpeed": 43.6575353602476, "medianTimeToFirstChunk": 4.06071905499999}, "outputSpeedVariance": {"p05": 37.1312078093117, "q25": 40.9644284418656, "median": 43.6575353602476, "q75": 47.0716289245914, "p95": 52.5240369478794}, "timeToFirstChunkVariance": {"p05": 3.76869009890011, "q25": 3.89842355599998, "median": 4.06071905499999, "q75": 4.25998183050001, "p95": 6.90981803090004}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 42.1825175384412, "medianTimeToFirstChunk": 1.22821350450001, "medianTimeToFirstAnswerToken": 48.64122052043705, "medianEndToEndResponseTime": 60.49447227442131}, "long": {"medianOutputSpeed": 43.6575353602476, "medianTimeToFirstChunk": 4.06071905499999, "medianTimeToFirstAnswerToken": 49.87182551111711, "medianEndToEndResponseTime": 61.324602125146384}, "hundredK": {"medianOutputSpeed": 82.9117901967699, "medianTimeToFirstChunk": 17.5409004710001, "medianTimeToFirstAnswerToken": 41.662922143111054, "medianEndToEndResponseTime": 47.69342756113879}, "mediumParallel": {"medianOutputSpeed": 41.3823577495039, "medianTimeToFirstChunk": 1.35554603100013, "medianTimeToFirstAnswerToken": 49.68532008849632, "medianEndToEndResponseTime": 61.76776360287036}}, "endToEndResponseTime": {"input": 4.06071905499999, "reasoning": 45.811106456117116, "answer": 11.452776614029279, "total": 61.324602125146384}, "timeToFirstAnswerToken": {"input": 4.06071905499999, "reasoning": 45.811106456117116, "total": 49.87182551111711}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 8, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b01eefb1-c9f8-412d-8353-571031a52f23", "slug": "motif-3", "name": "Motif 3", "shortName": "Motif 3", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "motif-3", "name": "Motif 3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 314, "inferenceParametersActiveBillions": 13.2, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 33.566562209723, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 10.1833333333333, "omniscienceBreakdown": {"accuracy": 0.3006666666666667, "hallucinationRate": 0.28431839847473783}, "gdpval": 1198.83, "gdpvalNormalized": 0.349415, "itBenchSre": null, "tau2": null, "tauBanking": 0.352577319587629, "terminalbenchHard": null, "terminalBench21": 0.749063670411985, "terminalBench40": null, "scicode": 0.422453703703704, "lcr": 0.76, "ifbench": null, "hle": 0.369786839666358, "gpqa": 0.834343434343434, "critpt": 0.0657142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "366bf3fc-4436-4baf-8d8f-acb7ec04d342", "slug": "motif-technologies", "name": "Motif Technologies", "logo": "/img/logos/motif_small.svg", "color": "#6a93eb", "country": "kr", "url": "https://model-hub.motiftech.io/en/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b0249961-b8b2-479d-8325-a29ea17c7b89", "slug": "qwen3-4b-2507-instruct", "name": "Qwen3 4B 2507 Instruct", "shortName": "Qwen3 4B 2507 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-06", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-4b-2507-instruct", "name": "Qwen3 4B 2507"}, "deprecated": true, "deprecatedTo": "qwen3-5-4b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 4.02, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507", "microevalsEnabled": false, "intelligenceIndex": 6.74457737576618, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -61.9333333333333, "omniscienceBreakdown": {"accuracy": 0.109, "hallucinationRate": 0.817433595211373}, "gdpval": null, "itBenchSre": null, "tau2": 0.266081871345029, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.113333333333333, "ifbench": 0.335374149659864, "hle": 0.0449490268767377, "gpqa": 0.517171717171717, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.376719576719577, "aime25": 0.523333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b07aef0a-b192-46a1-b1c9-40b06d1b9061", "slug": "gemma-4-e2b", "name": "Gemma 4 E2B (Reasoning)", "shortName": "Gemma 4 E2B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "gemma-4-e2b", "name": "Gemma 4 E2B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 5.1, "inferenceParametersActiveBillions": 2.3, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-4-E2B-it", "microevalsEnabled": false, "intelligenceIndex": 7.77445525187484, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -23.5833333333333, "omniscienceBreakdown": {"accuracy": 0.06633333333333333, "hallucinationRate": 0.32363441627990003}, "gdpval": 36.05, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.207602339181287, "tauBanking": null, "terminalbenchHard": 0.0303030303030303, "terminalBench21": 0.00374531835205993, "terminalBench40": null, "scicode": null, "lcr": 0.163333333333333, "ifbench": 0.380272108843537, "hle": 0.0477293790546803, "gpqa": 0.433333333333333, "critpt": 0, "apexAgents": null, "mmmuPro": 0.445664739884393, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": true, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b112af07-3bd5-4647-b09f-b23204361bb2", "slug": "qwen3-8-max", "name": "Qwen3.8 Max (0902)", "shortName": "Qwen3.8 Max (0902)", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-09-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-8-max-0902", "name": "Qwen3.8 Max (0902)"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 983616, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 45.4354834980521, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 45.59862156316724, "strategyAndOps": 47.27738805063787, "legal": 46.05507412090887, "engineering": 46.44004500419261, "economics": 52.283514732004946}, "omniscience": 11.9833333333333, "omniscienceBreakdown": {"accuracy": 0.31683333333333336, "hallucinationRate": 0.28836301536960235}, "gdpPdfAllPass": 0.228, "gdpval": 1688.96, "gdpvalNormalized": 0.59448, "itBenchSre": null, "tau2": null, "tauBanking": 0.478350515463918, "terminalbenchHard": null, "terminalBench21": 0.887640449438202, "terminalBench40": 0.388888888888889, "scicode": 0.520833333333333, "lcr": 0.803333333333333, "ifbench": null, "hle": 0.430954587581094, "gpqa": 0.928282828282828, "critpt": 0.177142857142857, "apexAgents": null, "mmmuPro": 0.827745664739884, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.561905381087678, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": 0.25, "cacheHitDiscountPercent": 0.875, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.175, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 0.3235294117647059, "price1mBlended0To100To1": 2.0396039603960396, "intelligenceIndexTimePerTask": 2096.0784213238812, "intelligenceIndexCost": {"total": 4934.789930721673, "input": 3783.009878721673, "nonCacheInput": 54.923078, "cacheRead": 2287.2161507540463, "cacheWrite": 1440.8706499676268, "output": 1151.780052, "reasoning": 892.9755480000001, "answer": 258.804504}, "intelligenceIndexCostPerTask": {"cost": {"total": 5.408509428374016, "input": 4.762128044435204, "nonCacheInput": 0.04039976820778719, "cacheRead": 2.9637284766204717, "cacheWrite": 1.7579997996069445, "output": 0.6463813839388131, "reasoning": 0.4249793026940497, "answer": 0.2214020812447632}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 2.936528640340602}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.4538143258221447}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.019911801266293043}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.86760733252611}, {"slug": "scicode", "weightedCostPerTask": 0.01130781875}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.02233803466172382}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.033310690000000004}, {"slug": "critpt", "weightedCostPerTask": 0.05089532285714286}, {"slug": "omniscience", "weightedCostPerTask": 0.0013550741499999998}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.011440388000000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 9896761467, "output": 191963342, "answer": 43134084, "reasoning": 148829258}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 70829.88378234163, "answer": 36900.3468741272, "output": 107730.23065646883}, "briefcaseBreakdown": {"overall": {"elo": 1621.59, "lower95ci": 1610.53, "upper95ci": 1632.68}, "rubricPassRate": 0.5795574288724974, "analyticalQuality": {"elo": 1984.78, "lower95ci": 1963.12, "upper95ci": 2007.03}, "presentation": {"elo": 1392.53, "lower95ci": 1372.48, "upper95ci": 1413}}, "briefcaseTotalCost": 1781.494041806632, "timescaleData": {"medianOutputSpeed": 40.4108411362042, "medianTimeToFirstChunk": 2.88666148149998}, "outputSpeedVariance": {"p05": 37.4371813311444, "q25": 38.6768623061821, "median": 40.4108411362042, "q75": 41.6847507630619, "p95": 44.9890981702459}, "timeToFirstChunkVariance": {"p05": 2.45774935305001, "q25": 2.53327339125002, "median": 2.88666148149998, "q75": 3.07834463350005, "p95": 3.56038878030003}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 40.6728479794928, "medianTimeToFirstChunk": 1.66483172649997, "medianTimeToFirstAnswerToken": 50.837685346398864, "medianEndToEndResponseTime": 63.130898751373586}, "long": {"medianOutputSpeed": 40.4108411362042, "medianTimeToFirstChunk": 2.88666148149998, "medianTimeToFirstAnswerToken": 52.3783311366558, "medianEndToEndResponseTime": 64.75124855044476}, "hundredK": {"medianOutputSpeed": 39.6713402832649, "medianTimeToFirstChunk": 8.95567436250002, "medianTimeToFirstAnswerToken": 59.369902511068204, "medianEndToEndResponseTime": 71.97345954821026}, "mediumParallel": {"medianOutputSpeed": 38.3022916111352, "medianTimeToFirstChunk": 1.80508769050005, "medianTimeToFirstAnswerToken": 54.02128457775267, "medianEndToEndResponseTime": 67.07533379956581}}, "endToEndResponseTime": {"input": 2.88666148149998, "reasoning": 49.491669655155825, "answer": 12.372917413788956, "total": 64.75124855044476}, "timeToFirstAnswerToken": {"input": 2.88666148149998, "reasoning": 49.491669655155825, "total": 52.3783311366558}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b13c1257-d746-4027-8fc8-4892dc14701c", "slug": "gpt-5-5-high", "name": "GPT-5.5 (high)", "shortName": "GPT-5.5 (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-23", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5-5", "name": "GPT-5.5"}, "deprecated": true, "deprecatedTo": "gpt-5-6-sol-high", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 922000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 37.2850237887731, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 40.54857671633369, "strategyAndOps": 43.99410961461927, "legal": 43.895632725222, "engineering": 38.92342787032245, "economics": 47.13345101560084}, "omniscience": 18.75, "omniscienceBreakdown": {"accuracy": 0.5703333333333334, "hallucinationRate": 0.8910007757951901}, "gdpPdfAllPass": 0.226, "gdpval": 1371.51, "gdpvalNormalized": 0.435755, "itBenchSre": null, "tau2": 0.929824561403509, "tauBanking": 0.36701030927835, "terminalbenchHard": 0.598484848484849, "terminalBench21": 0.794007490636704, "terminalBench40": 0.0909090909090909, "scicode": 0.561342592592593, "lcr": 0.843333333333333, "ifbench": 0.716326530612245, "hle": 0.450417052826691, "gpqa": 0.932323232323232, "critpt": 0.254285714285714, "apexAgents": null, "mmmuPro": 0.810982658959538, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.4434616323216385, "price1mInputTokens": 5, "price1mOutputTokens": 30, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 3.83, "price1mBlended0To3To1": 11.25, "price1mBlended7To2To1": 4.35, "price1mBlended0To1To1": 17.5, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 5.247524752475248, "intelligenceIndexTimePerTask": 163.967727043313, "intelligenceIndexCost": {"total": 3410.757124784552, "input": 1771.0533047845522, "nonCacheInput": 134.472995, "cacheRead": 409.67394502393864, "cacheWrite": 1226.9063647606135, "output": 1639.70382, "reasoning": 1299.22488, "answer": 340.47893999999997}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.541289049705234, "input": 1.0729565415026274, "nonCacheInput": 0.09869266641952426, "cacheRead": 0.2525183232119262, "cacheWrite": 0.7217455518711768, "output": 0.4683325082026068, "reasoning": 0.26678826991463805, "answer": 0.20154423828796872}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.49518942232105606}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.14073159129646287}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0904520432500106}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.5586921733622534}, {"slug": "scicode", "weightedCostPerTask": 0.010705229166666667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.022687830630213162}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.09255526}, {"slug": "critpt", "weightedCostPerTask": 0.09200237142857144}, {"slug": "omniscience", "weightedCostPerTask": 0.012882063249999997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.025391065}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1091623762, "output": 54656794, "answer": 11349298, "reasoning": 43307496}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 8892.942330487938, "answer": 6718.141276265624, "output": 15611.083606753562}, "briefcaseBreakdown": {"overall": {"elo": 1088.84, "lower95ci": 1082.97, "upper95ci": 1094.77}, "rubricPassRate": 0.30606060606060603, "analyticalQuality": {"elo": 1129.09, "lower95ci": 1117.8, "upper95ci": 1140.95}, "presentation": {"elo": 1077.63, "lower95ci": 1066.64, "upper95ci": 1089.23}}, "briefcaseTotalCost": 300.41491620810734, "timescaleData": {"medianOutputSpeed": 94.6849952394879, "medianTimeToFirstChunk": 13.6359918245}, "outputSpeedVariance": {"p05": 64.898383081997, "q25": 77.0077624036332, "median": 94.6849952394879, "q75": 111.064064447313, "p95": 131.866960732332}, "timeToFirstChunkVariance": {"p05": 6.27487743859984, "q25": 8.00650168049992, "median": 13.6359918245, "q75": 32.966701115, "p95": 86.666884602}, "performanceByPromptType": {"long": {"medianOutputSpeed": 94.6849952394879, "medianTimeToFirstChunk": 13.6359918245, "medianTimeToFirstAnswerToken": 13.6359918245, "medianEndToEndResponseTime": 18.91665956636706}}, "endToEndResponseTime": {"input": 13.6359918245, "reasoning": 0, "answer": 5.2806677418670604, "total": 18.91665956636706}, "timeToFirstAnswerToken": {"input": 13.6359918245, "reasoning": 0, "total": 13.6359918245}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 3, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b1fa84f8-1ed3-4124-b403-4655dafa4267", "slug": "llama-3-1-nemotron-nano-4b-reasoning", "name": "Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)", "shortName": "Llama 3.1 Nemotron Nano 4B v1.1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-20", "knowledgeCutoffDate": "2023-06-01", "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "llama-3-1-nemotron-nano-4b", "name": "Llama 3.1 Nemotron Nano 4B v1.1"}, "deprecated": true, "deprecatedTo": "nvidia-nemotron-3-nano-4b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 4.51, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "NVIDIA Open Model License Agreement", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1", "microevalsEnabled": false, "intelligenceIndex": 7.3075040848305, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.116959064327485, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.255102040816327, "hle": 0.0518999073215941, "gpqa": 0.408080808080808, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.493121693121693, "aime25": 0.5, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 52.77777777777778, "modelAvailability": 4, "transparencyMethodology": 4, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b2331108-72ed-415a-82d1-188633875bbc", "slug": "gemini-3-7-flash", "name": "Gemini 3.7 Flash (high)", "shortName": "Gemini 3.7 Flash (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-13", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gemini-3-7-flash", "name": "Gemini 3.7 Flash"}, "deprecated": true, "deprecatedTo": "gemini-3-8-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 39.4295316404896, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 45.42012092975085, "strategyAndOps": 48.942166583687055, "legal": 51.180758019946964, "healthcareAndMedical": 40.368448978673506, "engineering": 40.0601211878483, "economics": 51.07983466558543}, "omniscience": 26.4833333333333, "omniscienceBreakdown": {"accuracy": 0.5531666666666667, "hallucinationRate": 0.6452816113390526}, "mlcrOverall": 0.15, "harveyLab": 0.906643508467217, "gdpPdfAllPass": 0.236, "gdpval": 1433.14, "gdpvalNormalized": 0.46657000000000004, "itBenchSre": null, "tau2": null, "tauBanking": 0.327835051546392, "terminalbenchHard": null, "terminalBench21": 0.857677902621723, "terminalBench40": 0.136363636363636, "scicode": 0.571759259259259, "lcr": 0.816666666666667, "ifbench": null, "hle": 0.478683966635774, "gpqa": 0.945454545454545, "critpt": 0.142857142857143, "apexAgents": null, "mmmuPro": 0.854913294797688, "livecodebench": null, "aime25": null, "analystAgent": 0.6, "automationBenchPartialScore": 0.6202749292053469, "price1mInputTokens": 0.75, "price1mOutputTokens": 3.75, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.75, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5, "price1mBlended7To2To1": 0.5775, "price1mBlended0To1To1": 2.25, "price1mBlended100To1To1": 0.11764705882352941, "price1mBlended0To100To1": 0.7797029702970297, "intelligenceIndexTimePerTask": 170.56820672597826, "intelligenceIndexCost": {"total": 1084.4622196777668, "input": 693.9433284277667, "nonCacheInput": 16.38055275, "cacheRead": 266.43559164691476, "cacheWrite": 411.12718403085194, "output": 390.51889125, "reasoning": 224.602185, "answer": 165.91670625}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.9253359372385677, "input": 0.706384604961743, "nonCacheInput": 0.01110567733596529, "cacheRead": 0.2860523753235848, "cacheWrite": 0.409226552302193, "output": 0.2189513322768246, "reasoning": 0.07960479062355186, "answer": 0.13934654165327273}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.3232410311960026}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.1247819038271733}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.014723509650293188}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.43085475420842123}, {"slug": "scicode", "weightedCostPerTask": 0.0024521190104166667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0036775190685820205}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.009072407999999999}, {"slug": "critpt", "weightedCostPerTask": 0.01147868357142857}, {"slug": "omniscience", "weightedCostPerTask": 0.0005887618312500001}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.004465246875}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4122484871, "output": 104138371, "answer": 44244455, "reasoning": 59893916}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 21227.944166280493, "answer": 37159.07777420606, "output": 58387.02194048655}, "briefcaseBreakdown": {"overall": {"elo": 1115.67, "lower95ci": 1109.22, "upper95ci": 1122.71}, "rubricPassRate": 0.36363636363636365, "analyticalQuality": {"elo": 1026.62, "lower95ci": 1012.33, "upper95ci": 1040.87}, "presentation": {"elo": 1167.27, "lower95ci": 1154.77, "upper95ci": 1179.18}}, "briefcaseTotalCost": 196.0995589255749, "timescaleData": {"medianOutputSpeed": 328.16428023936, "medianTimeToFirstChunk": 13.3204372274999}, "outputSpeedVariance": {"p05": 226.023011651036, "q25": 269.137014103545, "median": 328.16428023936, "q75": 354.446569614856, "p95": 416.127059521021}, "timeToFirstChunkVariance": {"p05": 6.49759610024999, "q25": 9.30860240849997, "median": 13.3204372274999, "q75": 24.6044925617501, "p95": 53.4132566143}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 321.450492639523, "medianTimeToFirstChunk": 8.56887942999992, "medianTimeToFirstAnswerToken": 8.56887942999992, "medianEndToEndResponseTime": 10.124328904954384}, "long": {"medianOutputSpeed": 328.16428023936, "medianTimeToFirstChunk": 13.3204372274999, "medianTimeToFirstAnswerToken": 13.3204372274999, "medianEndToEndResponseTime": 14.844064356068873}, "hundredK": {"medianOutputSpeed": 232.972148157528, "medianTimeToFirstChunk": 21.8408923735, "medianTimeToFirstAnswerToken": 21.8408923735, "medianEndToEndResponseTime": 23.98707166554961}, "mediumParallel": {"medianOutputSpeed": 320.488868617867, "medianTimeToFirstChunk": 6.3363625335, "medianTimeToFirstAnswerToken": 6.3363625335, "medianEndToEndResponseTime": 7.896479120875682}}, "endToEndResponseTime": {"input": 13.3204372274999, "reasoning": 0, "answer": 1.5236271285689735, "total": 14.844064356068873}, "timeToFirstAnswerToken": {"input": 13.3204372274999, "reasoning": 0, "total": 13.3204372274999}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 4, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b23e6c69-96e5-44c9-8f58-4b42e0c399d5", "slug": "hy3", "name": "Hy3", "shortName": "Hy3", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-06", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "hy3", "name": "Hy3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 299, "inferenceParametersActiveBillions": 21, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/tencent/Hy3", "microevalsEnabled": true, "intelligenceIndex": 25.7716025731571, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 28.050031904400953, "strategyAndOps": 24.76687471966513, "legal": 27.041787204514023, "engineering": 27.123414685515293, "economics": 35.744979089434665}, "omniscience": -18.4666666666667, "omniscienceBreakdown": {"accuracy": 0.31966666666666665, "hallucinationRate": 0.7413032827045566}, "gdpPdfAllPass": 0.112, "gdpval": 1135.96, "gdpvalNormalized": 0.31798000000000004, "itBenchSre": null, "tau2": null, "tauBanking": 0.228865979381443, "terminalbenchHard": null, "terminalBench21": 0.644194756554307, "terminalBench40": 0.00505050505050505, "scicode": 0.486111111111111, "lcr": 0.79, "ifbench": null, "hle": 0.334569045412419, "gpqa": 0.896969696969697, "critpt": 0.0485714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.18409128371172395, "price1mInputTokens": 0.14, "price1mOutputTokens": 0.58, "cacheHitPrice": 0.035, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.25, "price1mBlended7To2To1": 0.1105, "price1mBlended0To1To1": 0.36, "price1mBlended100To1To1": 0.04137254901960785, "price1mBlended0To100To1": 0.14435643564356437, "intelligenceIndexTimePerTask": 512.0010760676583, "intelligenceIndexCost": {"total": 155.51285811630612, "input": 55.21101921630611, "nonCacheInput": 2.15852756, "cacheRead": 38.48082914789797, "cacheWrite": 14.571662508408139, "output": 100.30183889999999, "reasoning": 91.34687321999999, "answer": 8.954965679999999}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.07430984031498059, "input": 0.04753646609855005, "nonCacheInput": 0.0012551562095617342, "cacheRead": 0.036044728017935096, "cacheWrite": 0.010236581871053214, "output": 0.026773374216430546, "reasoning": 0.020767644077532014, "answer": 0.006005730138898529}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.01758071531744346}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.003715639204351546}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.002668377626275173}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.04146861157307258}, {"slug": "scicode", "weightedCostPerTask": 0.0006881154305555555}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.002094158927710843}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0009344880200000001}, {"slug": "critpt", "weightedCostPerTask": 0.0038428214285714285}, {"slug": "omniscience", "weightedCostPerTask": 0.0005476063569999998}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0007693064300000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1218953619, "output": 172934205, "answer": 15439596, "reasoning": 157494609}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 35806.28289229658, "answer": 10354.707136031948, "output": 46160.990028328524}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 5, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 949.65, "lower95ci": 939.78, "upper95ci": 959.19}, "rubricPassRate": 0.2672858617131063, "analyticalQuality": {"elo": 868.31, "lower95ci": 849.94, "upper95ci": 886.06}, "presentation": {"elo": 984.18, "lower95ci": 967.71, "upper95ci": 1003.13}}, "briefcaseTotalCost": 10.665633959249032, "timescaleData": {"medianOutputSpeed": 86.4119058966112, "medianTimeToFirstChunk": 2.82102227000001}, "outputSpeedVariance": {"p05": 25.4919210619761, "q25": 67.6207702476743, "median": 86.4119058966112, "q75": 97.9254383926338, "p95": 131.599156214744}, "timeToFirstChunkVariance": {"p05": 0.794941339149979, "q25": 2.21767298675, "median": 2.82102227000001, "q75": 3.07188779950013, "p95": 3.97229365904998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 88.9760276592255, "medianTimeToFirstChunk": 1.699996934, "medianTimeToFirstAnswerToken": 24.17796153430692, "medianEndToEndResponseTime": 29.79745268438365}, "long": {"medianOutputSpeed": 86.4119058966112, "medianTimeToFirstChunk": 2.82102227000001, "medianTimeToFirstAnswerToken": 25.965981049093827, "medianEndToEndResponseTime": 31.75222074386728}, "hundredK": {"medianOutputSpeed": 90.2746284907412, "medianTimeToFirstChunk": 14.7288288449999, "medianTimeToFirstAnswerToken": 36.88344784966438, "medianEndToEndResponseTime": 42.4221026008305}, "mediumParallel": {"medianOutputSpeed": 85.2969540106085, "medianTimeToFirstChunk": 1.63955683400013, "medianTimeToFirstAnswerToken": 25.087052974967335, "medianEndToEndResponseTime": 30.94892701020914}}, "endToEndResponseTime": {"input": 2.82102227000001, "reasoning": 23.144958779093816, "answer": 5.786239694773454, "total": 31.75222074386728}, "timeToFirstAnswerToken": {"input": 2.82102227000001, "reasoning": 23.144958779093816, "total": 25.965981049093827}, "performanceDataSource": {"type": "median"}, "hostModelCount": 4, "creator": {"id": "a4e5bd55-a6cd-4dcf-8d4a-1d9643cd3826", "slug": "tencent", "name": "Tencent", "logo": "/img/logos/tencent_small.svg", "color": "#5CB9FF", "country": "cn", "url": "https://hunyuan.tencent.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b26ff709-1773-4595-ae44-78e0a5bac29c", "slug": "deepseek-r1-distill-qwen-14b", "name": "DeepSeek R1 Distill Qwen 14B", "shortName": "DeepSeek R1 Distill Qwen 14B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-r1-distill-qwen-14b", "name": "DeepSeek R1 Distill Qwen 14B"}, "deprecated": true, "deprecatedTo": "deepseek-v3-0324", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 14, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "microevalsEnabled": false, "intelligenceIndex": 7.84674495869131, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.103333333333333, "ifbench": 0.22108843537415, "hle": 0.0413, "gpqa": 0.483838383838384, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.375661375661376, "aime25": 0.556666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b2dd592a-fbc5-458a-b26d-f3964cbab82f", "slug": "qwen3-8b-instruct", "name": "Qwen3 8B (Non-reasoning)", "shortName": "Qwen3 8B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-8b-instruct", "name": "Qwen3 8B"}, "deprecated": true, "deprecatedTo": "qwen3-vl-8b-instruct", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8.19, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-8B", "microevalsEnabled": false, "intelligenceIndex": 5.99207537851227, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -73.95, "omniscienceBreakdown": {"accuracy": 0.11083333333333334, "hallucinationRate": 0.9563261480787254}, "gdpval": null, "itBenchSre": null, "tau2": 0.248538011695906, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.285714285714286, "hle": 0.0195, "gpqa": 0.451515151515152, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.202116402116402, "aime25": 0.243333333333333, "analystAgent": null, "price1mInputTokens": 0.18, "price1mOutputTokens": 0.7, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.31, "price1mBlended7To2To1": 0.23200000000000004, "price1mBlended0To1To1": 0.43999999999999995, "price1mBlended100To1To1": 0.18509803921568627, "price1mBlended0To100To1": 0.18514851485148515, "timescaleData": {"medianOutputSpeed": 36.8701770548385, "medianTimeToFirstChunk": 3.70271138000001}, "outputSpeedVariance": {"p05": 29.2498254811791, "q25": 34.9851391260495, "median": 36.8701770548385, "q75": 39.5160124723892, "p95": 43.4490482581586}, "timeToFirstChunkVariance": {"p05": 3.60223926750005, "q25": 3.61870702525006, "median": 3.70271138000001, "q75": 3.8800854215, "p95": 4.7045243263}, "performanceByPromptType": {"long": {"medianOutputSpeed": 36.8701770548385, "medianTimeToFirstChunk": 3.70271138000001, "medianTimeToFirstAnswerToken": 3.70271138000001, "medianEndToEndResponseTime": 17.263807093110632}}, "endToEndResponseTime": {"input": 3.70271138000001, "reasoning": 0, "answer": 13.561095713110621, "total": 17.263807093110632}, "timeToFirstAnswerToken": {"input": 3.70271138000001, "reasoning": 0, "total": 3.70271138000001}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b2e68f0a-8f66-4e4c-9821-2b786cea601b", "slug": "claude-3-sonnet", "name": "Claude 3 Sonnet", "shortName": "Claude 3 Sonnet", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-03-04", "knowledgeCutoffDate": "2023-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-3-sonnet", "name": "Claude 3 Sonnet"}, "deprecated": true, "deprecatedTo": "claude-35-sonnet-june-24", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.87716084595884, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0362, "gpqa": 0.4, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.174603174603175, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b2f3191f-77d6-4155-8be6-330f0baa1ae5", "slug": "gemini-3-pro-low", "name": "Gemini 3 Pro Preview (low)", "shortName": "Gemini 3 Pro Preview (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-18", "knowledgeCutoffDate": "2025-01-01", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gemini-3-pro-preview", "name": "Gemini 3 Pro Preview"}, "deprecated": true, "deprecatedTo": "gemini-3-1-pro-preview", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 22.3196165324532, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 1.8, "omniscienceBreakdown": {"accuracy": 0.4831666666666667, "hallucinationRate": 0.9000322476620445}, "gdpval": null, "itBenchSre": null, "tau2": 0.681286549707602, "tauBanking": null, "terminalbenchHard": 0.340909090909091, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.74, "ifbench": 0.496598639455782, "hle": 0.294717330861909, "gpqa": 0.886868686868687, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.857142857142857, "aime25": 0.866666666666667, "analystAgent": null, "price1mInputTokens": 2, "price1mOutputTokens": 12, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 1.12, "price1mBlended0To3To1": 4.5, "price1mBlended7To2To1": 1.7399999999999998, "price1mBlended0To1To1": 7, "price1mBlended100To1To1": 0.3333333333333333, "price1mBlended0To100To1": 2.099009900990099, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b36ff8f3-0323-49d1-a063-ab09704fdb0c", "slug": "nova-2-0-omni-reasoning-low", "name": "Nova 2.0 Omni (low)", "shortName": "Nova 2.0 Omni (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-26", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "nova-2-0-omni", "name": "Nova 2.0 Omni"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.1140626232787, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -50.3166666666667, "omniscienceBreakdown": {"accuracy": 0.18616666666666667, "hallucinationRate": 0.8470202744214622}, "gdpval": null, "itBenchSre": null, "tau2": 0.678362573099415, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.576666666666667, "ifbench": 0.617687074829932, "hle": null, "gpqa": 0.698989898989899, "critpt": 0, "apexAgents": null, "mmmuPro": 0.598265895953757, "livecodebench": 0.591534391534391, "aime25": 0.56, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.42, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.52, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.32156862745098036, "price1mBlended0To100To1": 0.3217821782178218, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b3735511-c6ff-4928-8d72-2181444a4eb3", "slug": "arctic-instruct", "name": "Arctic Instruct", "shortName": "Arctic", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-04-24", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "arctic-instruct", "name": "Arctic Instruct"}, "deprecated": true, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 480, "inferenceParametersActiveBillions": 17, "sizeClass": "large", "contextWindowTokens": 4000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Snowflake/snowflake-arctic-instruct", "microevalsEnabled": false, "intelligenceIndex": 5.4363632246188, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "15568026-a4e1-4088-9709-566d3fb3aee1", "slug": "snowflake", "name": "Snowflake", "logo": "/img/logos/snowflake_small.svg", "color": "#4e9cd7", "country": "us", "url": "https://www.snowflake.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b4784397-aa28-411b-b011-9c4331bfa9c8", "slug": "gpt-4o-chatgpt", "name": "GPT-4o (ChatGPT)", "shortName": "GPT-4o (ChatGPT)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-15", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4o-chatgpt", "name": "GPT-4o (ChatGPT)"}, "deprecated": true, "deprecatedTo": "gpt-5-chatgpt", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.18657581032721, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.56, "ifbench": null, "hle": 0.0273, "gpqa": 0.511111111111111, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b4ddb4c8-1400-44ab-8c2b-e2472088e7ff", "slug": "jamba-1-5-large", "name": "Jamba 1.5 Large", "shortName": "Jamba 1.5 Large", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-08-22", "knowledgeCutoffDate": "2024-03-05", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "jamba-1-5-large", "name": "Jamba 1.5 Large"}, "deprecated": true, "deprecatedTo": "jamba-1-6-large", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 398, "inferenceParametersActiveBillions": 94, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Jamba Open Model License Agreement", "licenseUrl": "https://www.ai21.com/licenses/jamba-open-model-license", "modelWeightsSourceUrl": "https://huggingface.co/ai21labs/AI21-Jamba-1.5-Large", "microevalsEnabled": false, "intelligenceIndex": 6.01209130693622, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0407, "gpqa": 0.427272727272727, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.142857142857143, "aime25": null, "analystAgent": null, "price1mInputTokens": 2, "price1mOutputTokens": 8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3.5, "price1mBlended7To2To1": 2.6, "price1mBlended0To1To1": 5, "price1mBlended100To1To1": 2.0588235294117645, "price1mBlended0To100To1": 2.0594059405940595, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "6216c686-bc60-4dbb-9f25-83e9dba803d1", "slug": "ai21-labs", "name": "AI21 Labs", "logo": "/img/logos/ai21_small.svg", "color": "#d63864", "country": "il", "url": "https://www.ai21.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b4f14013-37dd-4c75-bd8a-378365d9ed77", "slug": "jamba-1-7-mini", "name": "Jamba 1.7 Mini", "shortName": "Jamba 1.7 Mini", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-07", "knowledgeCutoffDate": "2024-08-22", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "jamba-1-7-mini", "name": "Jamba 1.7 Mini"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 52, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 258000, "licenseName": "Jamba Open Model License Agreement", "licenseUrl": "https://www.ai21.com/licenses/jamba-open-model-license", "modelWeightsSourceUrl": "https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.7", "microevalsEnabled": false, "intelligenceIndex": 5.21767706986744, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -73.1166666666667, "omniscienceBreakdown": {"accuracy": 0.11266666666666666, "hallucinationRate": 0.9509767092411721}, "gdpval": null, "itBenchSre": null, "tau2": 0.125730994152047, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.16, "ifbench": 0.313605442176871, "hle": 0.0444856348470806, "gpqa": 0.322222222222222, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0613756613756614, "aime25": 0.00333333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 22.22222222222222, "modelAvailability": 4, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "6216c686-bc60-4dbb-9f25-83e9dba803d1", "slug": "ai21-labs", "name": "AI21 Labs", "logo": "/img/logos/ai21_small.svg", "color": "#d63864", "country": "il", "url": "https://www.ai21.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b4f7d7a4-869a-4ee7-b17a-4046cd1e79fd", "slug": "qwen2-5-72b-instruct", "name": "Qwen2.5 Instruct 72B", "shortName": "Qwen2.5 72B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-19", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen2-5-72b-instruct", "name": "Qwen2.5 Instruct 72B"}, "deprecated": true, "deprecatedTo": "qwen3-235b-a22b-instruct", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 72, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 131072, "licenseName": "Qwen License Agreement", "licenseUrl": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 7.73490670575182, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -53.0666666666667, "omniscienceBreakdown": {"accuracy": 0.17466666666666666, "hallucinationRate": 0.8546042003231018}, "gdpval": null, "itBenchSre": null, "tau2": 0.345029239766082, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.368707482993197, "hle": 0.0356, "gpqa": 0.490909090909091, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.276190476190476, "aime25": 0.14, "analystAgent": null, "price1mInputTokens": 0.475, "price1mOutputTokens": 0.495, "cacheHitPrice": 0.355, "cacheHitDiscountPercent": 0.6666666666666667, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.48, "price1mBlended7To2To1": 0.39299999999999996, "price1mBlended0To1To1": 0.485, "price1mBlended100To1To1": 0.35754901960784313, "price1mBlended0To100To1": 0.4751980198019802, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b515503d-4d65-4a3f-8a4a-6c731e2b079f", "slug": "o1-mini", "name": "o1-mini", "shortName": "o1-mini", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-12", "knowledgeCutoffDate": "2023-10-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "o1-mini", "name": "o1-mini"}, "deprecated": true, "deprecatedTo": "o4-mini", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.77059897024848, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0357, "gpqa": 0.603030303030303, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.575661375661376, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b58b8272-cd3f-44b9-9b68-612f40779ce2", "slug": "hy3-non-reasoning", "name": "Hy3-preview (Non-reasoning)", "shortName": "Hy3-preview (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-23", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "hy3-preview", "name": "Hy3-preview"}, "deprecated": true, "deprecatedTo": "hy3", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 295, "inferenceParametersActiveBillions": 21, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "TENCENT HY COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://huggingface.co/tencent/Hy3-preview/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/tencent/Hy3-preview", "microevalsEnabled": false, "intelligenceIndex": 17.0361964508377, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -34.95, "omniscienceBreakdown": {"accuracy": 0.23183333333333334, "hallucinationRate": 0.756780212627468}, "gdpval": null, "itBenchSre": null, "tau2": 0.675438596491228, "tauBanking": null, "terminalbenchHard": 0.318181818181818, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.42, "ifbench": 0.479591836734694, "hle": 0.0695088044485635, "gpqa": 0.732323232323232, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.063, "price1mOutputTokens": 0.21, "cacheHitPrice": 0.021, "cacheHitDiscountPercent": 0.6666666666666666, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.09975, "price1mBlended7To2To1": 0.048299999999999996, "price1mBlended0To1To1": 0.1365, "price1mBlended100To1To1": 0.023264705882352944, "price1mBlended0To100To1": 0.06445544554455446, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 5, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "a4e5bd55-a6cd-4dcf-8d4a-1d9643cd3826", "slug": "tencent", "name": "Tencent", "logo": "/img/logos/tencent_small.svg", "color": "#5CB9FF", "country": "cn", "url": "https://hunyuan.tencent.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b5c1c91a-7474-4409-9a9c-9c2ac45d9eb6", "slug": "gpt-4o-mini", "name": "GPT-4o mini", "shortName": "GPT-4o mini", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-07-18", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4o-mini", "name": "GPT-4o mini"}, "deprecated": true, "deprecatedTo": "gpt-5-mini-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.66432562957107, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "mlcrOverall": 0, "gdpval": 188.06, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": null, "tauBanking": 0.0288659793814433, "terminalbenchHard": null, "terminalBench21": 0.0561797752808989, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.30952380952381, "hle": 0.042, "gpqa": 0.426262626262626, "critpt": null, "apexAgents": null, "mmmuPro": 0.415028901734104, "livecodebench": 0.233862433862434, "aime25": 0.146666666666667, "analystAgent": null, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.6, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.5, "cacheWritePrice": null, "pricePer1k1mpImages": 0.11475, "price1mBlended0To3To1": 0.26249999999999996, "price1mBlended7To2To1": 0.1425, "price1mBlended0To1To1": 0.375, "price1mBlended100To1To1": 0.08088235294117647, "price1mBlended0To100To1": 0.15445544554455445, "timescaleData": {"medianOutputSpeed": 147.19668788912, "medianTimeToFirstChunk": 0.866725640000084}, "outputSpeedVariance": {"p05": 115.124573201101, "q25": 134.443494548123, "median": 147.19668788912, "q75": 155.411318455886, "p95": 166.176975572734}, "timeToFirstChunkVariance": {"p05": 0.723197827699988, "q25": 0.78394358300011, "median": 0.866725640000084, "q75": 0.993713353749988, "p95": 1.3997120063}, "performanceByPromptType": {"long": {"medianOutputSpeed": 147.19668788912, "medianTimeToFirstChunk": 0.866725640000084, "medianTimeToFirstAnswerToken": 0.866725640000084, "medianEndToEndResponseTime": 4.263541201343685}}, "endToEndResponseTime": {"input": 0.866725640000084, "reasoning": 0, "answer": 3.396815561343601, "total": 4.263541201343685}, "timeToFirstAnswerToken": {"input": 0.866725640000084, "reasoning": 0, "total": 0.866725640000084}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 3, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b6d2e43d-3082-43f5-9318-0f4dbcb54163", "slug": "trinity-large-thinking", "name": "Trinity Large Thinking", "shortName": "Trinity Large Thinking", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "trinity-large-thinking", "name": "Trinity Large Thinking"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 399, "inferenceParametersActiveBillions": 13, "sizeClass": "large", "contextWindowTokens": 512000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/arcee-ai/Trinity-Large-Thinking", "microevalsEnabled": true, "intelligenceIndex": 10.8821425924218, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 10.541936919747704, "strategyAndOps": 6.841017001595535, "legal": 11.33920842062502, "engineering": 16.25443011646988, "economics": 16.636677594995373}, "omniscience": -44.0666666666667, "omniscienceBreakdown": {"accuracy": 0.225, "hallucinationRate": 0.8589247311827957}, "gdpPdfAllPass": 0.012, "gdpval": 511.58, "gdpvalNormalized": 0.005789999999999992, "itBenchSre": null, "tau2": 0.900584795321637, "tauBanking": 0.0577319587628866, "terminalbenchHard": 0.227272727272727, "terminalBench21": 0.205992509363296, "terminalBench40": 0.00505050505050505, "scicode": 0.40625, "lcr": 0.38, "ifbench": 0.562585034013605, "hle": 0.158480074142725, "gpqa": 0.751515151515151, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.013069234137838785, "price1mInputTokens": 0.25, "price1mOutputTokens": 0.9, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.4125, "price1mBlended7To2To1": 0.315, "price1mBlended0To1To1": 0.575, "price1mBlended100To1To1": 0.2563725490196078, "price1mBlended0To100To1": 0.25643564356435644, "intelligenceIndexTimePerTask": 140.609920477196, "intelligenceIndexCost": {"total": 518.07310555, "input": 373.45272024999997, "nonCacheInput": 3.7057175, "cacheRead": 0, "cacheWrite": 369.74700275, "output": 144.6203853, "reasoning": 136.3984839, "answer": 8.2219014}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.3533614843871682, "input": 0.31636222980628853, "nonCacheInput": 0.0020953666135794095, "cacheRead": 0, "cacheWrite": 0.31426686319270913, "output": 0.0369992545808797, "reasoning": 0.03179953878677829, "answer": 0.005199715794101411}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.07094151684065934}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0489854160909091}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.007977152876712329}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.2070882893939394}, {"slug": "scicode", "weightedCostPerTask": 0.001397281076388889}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.003597984358202039}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.001103214}, {"slug": "critpt", "weightedCostPerTask": 0.010205472642857143}, {"slug": "omniscience", "weightedCostPerTask": 0.0008348222574999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00123033485}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1493810881, "output": 160689317, "answer": 9135446, "reasoning": 151553871}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 35332.8208741981, "answer": 5777.461993446014, "output": 41110.28286764411}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 271.11, "lower95ci": 260.77, "upper95ci": 280.35}, "rubricPassRate": 0.05761316872427984, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 8.26}, "presentation": {"elo": 228.67, "lower95ci": 209.62, "upper95ci": 246.2}}, "briefcaseTotalCost": 43.03785355, "timescaleData": {"medianOutputSpeed": 311.48152909168, "medianTimeToFirstChunk": 1.28503914200008}, "outputSpeedVariance": {"p05": 219.533027297488, "q25": 283.546360708195, "median": 311.48152909168, "q75": 350.308421730048, "p95": 397.425448546155}, "timeToFirstChunkVariance": {"p05": 0.814788464350038, "q25": 1.01532808175001, "median": 1.28503914200008, "q75": 1.37594671499997, "p95": 1.54214595364999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 335.981601207578, "medianTimeToFirstChunk": 1.094218066, "medianTimeToFirstAnswerToken": 7.04692497855605, "medianEndToEndResponseTime": 8.535101706695064}, "long": {"medianOutputSpeed": 311.48152909168, "medianTimeToFirstChunk": 1.28503914200008, "medianTimeToFirstAnswerToken": 7.705965627857061, "medianEndToEndResponseTime": 9.311197249321307}, "hundredK": {"medianOutputSpeed": 284.754804926542, "medianTimeToFirstChunk": 3.3805745735, "medianTimeToFirstAnswerToken": 10.404161060533777, "medianEndToEndResponseTime": 12.160057682292223}, "mediumParallel": {"medianOutputSpeed": 296.33601674184, "medianTimeToFirstChunk": 1.16899067550003, "medianTimeToFirstAnswerToken": 7.918085915388964, "medianEndToEndResponseTime": 9.605359725361199}}, "endToEndResponseTime": {"input": 1.28503914200008, "reasoning": 6.420926485856982, "answer": 1.6052316214642455, "total": 9.311197249321307}, "timeToFirstAnswerToken": {"input": 1.28503914200008, "reasoning": 6.420926485856982, "total": 7.705965627857061}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "7f460cea-a532-4021-b9ca-50ac183ecd4a", "slug": "arcee", "name": "Arcee AI", "logo": "/img/logos/arcee_small.svg", "color": "#008c8d", "country": "us", "url": "https://www.arcee.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b7726745-9c77-40c3-8452-974cb53d6fbc", "slug": "deephermes-3-llama-3-1-8b-preview", "name": "DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)", "shortName": "DeepHermes 3 - Llama-3.1 8B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-13", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deephermes-3-llama-3-1-8b-preview", "name": "DeepHermes 3 - Llama-3.1 8B Preview"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.1 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/NousResearch/DeepHermes-3-Llama-3-8B-Preview", "microevalsEnabled": false, "intelligenceIndex": 5.08032603461277, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0426, "gpqa": 0.26969696969697, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0846560846560847, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 5, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0a2f41cc-2cbc-4949-be54-9fef1319d4a9", "slug": "nous-research", "name": "Nous Research", "logo": "/img/logos/nousresearch_small.jpg", "color": "#006fa8", "country": "us", "url": "https://nousresearch.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b89c4faf-219e-4171-a1aa-e3bd2fd0a924", "slug": "solar-pro-3", "name": "Solar Pro 3", "shortName": "Solar Pro 3", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-06", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "solar-pro-3", "name": "Solar Pro 3"}, "deprecated": true, "deprecatedTo": "solar-pro4", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 102, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.81551744502774, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 8.11544306781783, "strategyAndOps": 5.380877450701308, "legal": 9.148226169717658, "healthcareAndMedical": 8.151261795071711, "engineering": 11.483095458758111, "economics": 12.864722737102255}, "omniscience": -53.4, "omniscienceBreakdown": {"accuracy": 0.185, "hallucinationRate": 0.8822085889570552}, "mlcrOverall": 0.00555555555555556, "gdpPdfAllPass": 0.016, "gdpval": 446.94, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.862573099415205, "tauBanking": 0.0865979381443299, "terminalbenchHard": 0.0757575757575758, "terminalBench21": 0.119850187265918, "terminalBench40": 0, "scicode": 0.25462962962963, "lcr": 0.323333333333333, "ifbench": 0.712018140589569, "hle": 0.102873030583874, "gpqa": 0.724242424242424, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.004973424202262958, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.6, "cacheHitPrice": 0.015, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.26249999999999996, "price1mBlended7To2To1": 0.10049999999999999, "price1mBlended0To1To1": 0.375, "price1mBlended100To1To1": 0.022058823529411766, "price1mBlended0To100To1": 0.15445544554455445, "intelligenceIndexTimePerTask": 292.7172573102862, "intelligenceIndexCost": {"total": 159.22094392081266, "input": 72.25049032081264, "nonCacheInput": 2.2645908, "cacheRead": 8.012373658798595, "cacheWrite": 61.97352586201405, "output": 86.9704536, "reasoning": 76.7554692, "answer": 10.2149844}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.07942705217350178, "input": 0.05374527360227124, "nonCacheInput": 0.0012863516109106756, "cacheRead": 0.006053784272558073, "cacheWrite": 0.0464051377188025, "output": 0.02568177857123052, "reasoning": 0.017502436024962095, "answer": 0.008179342546268424}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.02026784517977828}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.018097335728230617}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0027521129743742338}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.02934066054499348}, {"slug": "scicode", "weightedCostPerTask": 0.0006869813541666666}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0016582657437442074}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0010372411499999998}, {"slug": "critpt", "weightedCostPerTask": 0.004513687285714286}, {"slug": "omniscience", "weightedCostPerTask": 0.0001967587125}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0008761635}]}, "canonicalIntelligenceIndexTokenCount": {"input": 962412355, "output": 144950756, "answer": 17024974, "reasoning": 127925782}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 29170.726708270166, "answer": 13632.237577114041, "output": 42802.96428538421}, "briefcaseBreakdown": {"overall": {"elo": 121.9, "lower95ci": 112.6, "upper95ci": 130.43}, "rubricPassRate": 0.049029622063329927, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 15.58}}, "briefcaseTotalCost": 12.295826075732156, "timescaleData": {"medianOutputSpeed": 147.289243730933, "medianTimeToFirstChunk": 2.7032672895001}, "outputSpeedVariance": {"p05": 115.654041351428, "q25": 129.651851658614, "median": 147.289243730933, "q75": 161.077473958602, "p95": 170.656504677165}, "timeToFirstChunkVariance": {"p05": 2.22534730770005, "q25": 2.29108629900004, "median": 2.7032672895001, "q75": 2.9394375737499, "p95": 4.17949857575003}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 148.462815539269, "medianTimeToFirstChunk": 1.09179732400003, "medianTimeToFirstAnswerToken": 14.563184032754668, "medianEndToEndResponseTime": 17.93103070994333}, "long": {"medianOutputSpeed": 147.289243730933, "medianTimeToFirstChunk": 2.7032672895001, "medianTimeToFirstAnswerToken": 16.281991365601588, "medianEndToEndResponseTime": 19.676672384626958}, "hundredK": {"medianOutputSpeed": 130.128932521127, "medianTimeToFirstChunk": 9.77836519000001, "medianTimeToFirstAnswerToken": 25.147737406092624, "medianEndToEndResponseTime": 28.990080460115777}, "mediumParallel": {"medianOutputSpeed": 121.676113737925, "medianTimeToFirstChunk": 1.61734470500005, "medianTimeToFirstAnswerToken": 18.054424576795988, "medianEndToEndResponseTime": 22.16369454474497}}, "endToEndResponseTime": {"input": 2.7032672895001, "reasoning": 13.578724076101487, "answer": 3.394681019025372, "total": 19.676672384626958}, "timeToFirstAnswerToken": {"input": 2.7032672895001, "reasoning": 13.578724076101487, "total": 16.281991365601588}, "performanceDataSource": {"type": "firstParty", "providerName": "Upstage"}, "hostModelCount": 1, "creator": {"id": "64ff7f06-c6fb-42ea-ba24-9cd103ab2d61", "slug": "upstage", "name": "Upstage", "logo": "/img/logos/upstage_small.svg", "color": "#7c59f5", "country": "kr", "url": "https://www.upstage.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b8fc61f7-5e9a-49e6-8547-6ac56db24627", "slug": "claude-opus-5", "name": "Claude Opus 5 (Adaptive Reasoning, Max Effort)", "shortName": "Claude Opus 5 (max)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-07-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "claude-opus-5", "name": "Claude Opus 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 50.7001865797629, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 54.879570063518685, "strategyAndOps": 56.62163224573655, "legal": 57.291863099419025, "healthcareAndMedical": 53.33111338335008, "engineering": 54.014034523937966, "economics": 60.82956987565646}, "omniscience": 37.0666666666667, "omniscienceBreakdown": {"accuracy": 0.6086666666666667, "hallucinationRate": 0.6081771720613288}, "mlcrOverall": 0.555555555555556, "harveyLab": 0.93457808655377, "gdpPdfAllPass": 0.216, "gdpval": 1735.09, "gdpvalNormalized": 0.617545, "itBenchSre": null, "tau2": null, "tauBanking": 0.420618556701031, "terminalbenchHard": null, "terminalBench21": 0.891385767790262, "terminalBench40": 0.48989898989899, "scicode": 0.563657407407407, "lcr": 0.793333333333333, "ifbench": null, "hle": 0.548656163113994, "gpqa": 0.932323232323232, "critpt": 0.291428571428571, "apexAgents": null, "mmmuPro": 0.847398843930636, "livecodebench": null, "aime25": null, "analystAgent": 0.5375, "automationBenchPartialScore": 0.565735557649325, "enterpriseOpsGym": 0.474783646672635, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.86, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "intelligenceIndexTimePerTask": 836.8915519737683, "intelligenceIndexCost": {"total": 7274.7418382622345, "input": 3765.8444132622344, "nonCacheInput": 177.56108999999998, "cacheRead": 2670.2262311293707, "cacheWrite": 918.0570921328634, "output": 3508.897425, "reasoning": 2517.588475, "answer": 991.30895}, "intelligenceIndexCostPerTask": {"cost": {"total": 5.858396237036018, "input": 4.045610010784609, "nonCacheInput": 0.12917416473418766, "cacheRead": 3.1554299546716544, "cacheWrite": 0.7610058913787667, "output": 1.8127862262514098, "reasoning": 1.069818103416972, "answer": 0.7429681228344376}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 2.6689972791636283}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.6766011819009691}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.06580202812402931}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.9289100239966006}, {"slug": "scicode", "weightedCostPerTask": 0.01177131076388889}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.06735533456904541}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.108566965}, {"slug": "critpt", "weightedCostPerTask": 0.28845440714285714}, {"slug": "omniscience", "weightedCostPerTask": 0.003882061375}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.038055645}]}, "canonicalIntelligenceIndexTokenCount": {"input": 5522853815, "output": 140355897, "answer": 39652358, "reasoning": 100703539}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 42792.72413667888, "answer": 29718.724913377504, "output": 72511.44905005638}, "briefcaseBreakdown": {"overall": {"elo": 1644.9, "lower95ci": 1638.09, "upper95ci": 1652.49}, "rubricPassRate": 0.5717171717171717, "analyticalQuality": {"elo": 1905.19, "lower95ci": 1891.43, "upper95ci": 1920.09}, "presentation": {"elo": 1542.52, "lower95ci": 1531.28, "upper95ci": 1555.21}}, "briefcaseTotalCost": 1619.1916826926013, "timescaleData": {"medianOutputSpeed": 53.2587683474965, "medianTimeToFirstChunk": 52.5751065395}, "outputSpeedVariance": {"p05": 40.4862660361526, "q25": 44.0504670353344, "median": 53.2587683474965, "q75": 61.4391987663928, "p95": 79.495839839843}, "timeToFirstChunkVariance": {"p05": 6.66046766899979, "q25": 15.2377773567499, "median": 52.5751065395, "q75": 83.38315228025, "p95": 148.4067930717}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 55.3996847583961, "medianTimeToFirstChunk": 39.0940024075, "medianTimeToFirstAnswerToken": 39.0940024075, "medianEndToEndResponseTime": 48.11932452224764}, "long": {"medianOutputSpeed": 53.2587683474965, "medianTimeToFirstChunk": 52.5751065395, "medianTimeToFirstAnswerToken": 52.5751065395, "medianEndToEndResponseTime": 61.96323201656059}, "hundredK": {"medianOutputSpeed": 60.3815603037695, "medianTimeToFirstChunk": 13.869872853, "medianTimeToFirstAnswerToken": 13.869872853, "medianEndToEndResponseTime": 22.150546579955446}, "mediumParallel": {"medianOutputSpeed": 59.8841165611146, "medianTimeToFirstChunk": 63.0531874400001, "medianTimeToFirstAnswerToken": 63.0531874400001, "medianEndToEndResponseTime": 71.4026468411374}}, "endToEndResponseTime": {"input": 52.5751065395, "reasoning": 0, "answer": 9.388125477060589, "total": 61.96323201656059}, "timeToFirstAnswerToken": {"input": 52.5751065395, "reasoning": 0, "total": 52.5751065395}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 7, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b97ef678-2d31-4375-9416-67ea97f87204", "slug": "qwen3-omni-30b-a3b-reasoning", "name": "Qwen3 Omni 30B A3B (Reasoning)", "shortName": "Qwen3 Omni 30B A3B (Reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-22", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-omni-30b-a3b", "name": "Qwen3 Omni 30B A3B (Reasoning)"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 35.3, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 65536, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Thinking", "microevalsEnabled": false, "intelligenceIndex": 7.76082961984319, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -61.4, "omniscienceBreakdown": {"accuracy": 0.146, "hallucinationRate": 0.8899297423887588}, "gdpval": null, "itBenchSre": null, "tau2": 0.213450292397661, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.434013605442177, "hle": 0.0746061167747915, "gpqa": 0.726262626262626, "critpt": 0, "apexAgents": null, "mmmuPro": 0.602312138728324, "livecodebench": 0.679365079365079, "aime25": 0.74, "analystAgent": null, "price1mInputTokens": 0.25, "price1mOutputTokens": 0.97, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.43, "price1mBlended7To2To1": 0.32199999999999995, "price1mBlended0To1To1": 0.61, "price1mBlended100To1To1": 0.25705882352941173, "price1mBlended0To100To1": 0.25712871287128714, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 99.9635865078674, "medianTimeToFirstChunk": 1.90963216949998}, "outputSpeedVariance": {"p05": 88.3809547395035, "q25": 97.2320607736468, "median": 99.9635865078674, "q75": 101.712392714192, "p95": 103.207153533841}, "timeToFirstChunkVariance": {"p05": 1.84269993565005, "q25": 1.874675866, "median": 1.90963216949998, "q75": 2.10097536949996, "p95": 2.4047170365}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 108.338529213067, "medianTimeToFirstChunk": 0.923893123499965, "medianTimeToFirstAnswerToken": 19.384546175810137, "medianEndToEndResponseTime": 23.999709438887677}, "long": {"medianOutputSpeed": 99.9635865078674, "medianTimeToFirstChunk": 1.90963216949998, "medianTimeToFirstAnswerToken": 21.91691752077731, "medianEndToEndResponseTime": 26.918738858596644}, "mediumParallel": {"medianOutputSpeed": 65.2686241867109, "medianTimeToFirstChunk": 0.549942053499933, "medianTimeToFirstAnswerToken": 31.19253679057749, "medianEndToEndResponseTime": 38.853185474846875}}, "endToEndResponseTime": {"input": 1.90963216949998, "reasoning": 20.007285351277332, "answer": 5.001821337819333, "total": 26.918738858596644}, "timeToFirstAnswerToken": {"input": 1.90963216949998, "reasoning": 20.007285351277332, "total": 21.91691752077731}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "b9dc72c6-7bea-4936-a55a-4b0c835fc755", "slug": "qwen-2-5-max", "name": "Qwen2.5 Max", "shortName": "Qwen2.5 Max", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen-2-5-max", "name": "Qwen2.5 Max"}, "deprecated": true, "deprecatedTo": "qwen3-max", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 32000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.01995268843494, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0382, "gpqa": 0.586868686868687, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.358730158730159, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ba0224cf-0351-4f56-8508-b3f1a740ae4a", "slug": "claude-sonnet-5-high", "name": "Claude Sonnet 5 (Adaptive Reasoning, High Effort)", "shortName": "Claude Sonnet 5 (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "claude-sonnet-5", "name": "Claude Sonnet 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 32.0283996664651, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 33.96426133587019, "strategyAndOps": 34.05428010435366, "legal": 35.34776874043704, "engineering": 32.392083151988565, "economics": 41.727279753629894}, "omniscience": -3.68333333333333, "omniscienceBreakdown": {"accuracy": 0.37433333333333335, "hallucinationRate": 0.6571656899307405}, "gdpPdfAllPass": 0.094, "gdpval": 1308.45, "gdpvalNormalized": 0.404225, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": 0.0505050505050505, "scicode": 0.542824074074074, "lcr": 0.766666666666667, "ifbench": null, "hle": 0.357275254865616, "gpqa": null, "critpt": 0.151428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.32096638814380396, "price1mInputTokens": 2, "price1mOutputTokens": 10, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": 4.116, "price1mBlended0To3To1": 4, "price1mBlended7To2To1": 1.54, "price1mBlended0To1To1": 6, "price1mBlended100To1To1": 0.3137254901960784, "price1mBlended0To100To1": 2.0792079207920793, "intelligenceIndexTimePerTask": 392.4566864540878, "intelligenceIndexCost": {"total": 2086.0433261999005, "input": 1197.8038261999006, "nonCacheInput": 70.39093, "cacheRead": 799.8154398956608, "cacheWrite": 327.5974563042398, "output": 888.2395000000001, "reasoning": 646.1794500000001, "answer": 242.06005000000002}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.7924692244111728, "input": 1.3490557506136662, "nonCacheInput": 0.05131807364962929, "cacheRead": 1.0120890703528487, "cacheWrite": 0.2856486066111881, "output": 0.4434134737975068, "reasoning": 0.2801513645018374, "answer": 0.1632621092956693}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.564703388959535}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.10174550722614487}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.028651751442573953}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.9401018692598622}, {"slug": "scicode", "weightedCostPerTask": 0.00254946875}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.017395588044485634}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.041982038}, {"slug": "critpt", "weightedCostPerTask": 0.07993123142857142}, {"slug": "omniscience", "weightedCostPerTask": 0.00029408729999999994}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.015114294}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4165311647, "output": 88823950, "answer": 24206005, "reasoning": 64617945}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 28015.136450183745, "answer": 16326.210929566934, "output": 44341.34737975068}, "briefcaseBreakdown": {"overall": {"elo": 1177.84, "lower95ci": 1171.72, "upper95ci": 1184.05}, "rubricPassRate": 0.35454545454545455, "analyticalQuality": {"elo": 1198.61, "lower95ci": 1186.97, "upper95ci": 1210.28}, "presentation": {"elo": 1187.48, "lower95ci": 1174.69, "upper95ci": 1198.98}}, "briefcaseTotalCost": 342.5867226354512, "timescaleData": {"medianOutputSpeed": 67.5020009666245, "medianTimeToFirstChunk": 4.09502054149999}, "outputSpeedVariance": {"p05": 48.9611858286653, "q25": 55.2781451493995, "median": 67.5020009666245, "q75": 83.3688139885051, "p95": 92.9224129831173}, "timeToFirstChunkVariance": {"p05": 1.16411547214991, "q25": 1.99034026375, "median": 4.09502054149999, "q75": 11.325004511, "p95": 19.9441373098999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 70.9283886391563, "medianTimeToFirstChunk": 5.43624377650002, "medianTimeToFirstAnswerToken": 5.43624377650002, "medianEndToEndResponseTime": 12.485607361280135}, "long": {"medianOutputSpeed": 67.5020009666245, "medianTimeToFirstChunk": 4.09502054149999, "medianTimeToFirstAnswerToken": 4.09502054149999, "medianEndToEndResponseTime": 11.502208370601807}, "hundredK": {"medianOutputSpeed": 71.9135677995802, "medianTimeToFirstChunk": 13.134849241, "medianTimeToFirstAnswerToken": 13.134849241, "medianEndToEndResponseTime": 20.087640144011193}, "mediumParallel": {"medianOutputSpeed": 64.4097702886686, "medianTimeToFirstChunk": 8.77447259000002, "medianTimeToFirstAnswerToken": 8.77447259000002, "medianEndToEndResponseTime": 16.537270031430477}}, "endToEndResponseTime": {"input": 4.09502054149999, "reasoning": 0, "answer": 7.407187829101817, "total": 11.502208370601807}, "timeToFirstAnswerToken": {"input": 4.09502054149999, "reasoning": 0, "total": 4.09502054149999}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ba04694d-326a-4a6a-8f1b-46316f872a7f", "slug": "kimi-k2-5-non-reasoning", "name": "Kimi K2.5 (Non-reasoning)", "shortName": "Kimi K2.5 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-27", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "kimi-k2-5", "name": "Kimi K2.5"}, "deprecated": true, "deprecatedTo": "kimi-k2-6-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1000, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Modified MIT License", "licenseUrl": "https://huggingface.co/moonshotai/Kimi-K2.5/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-K2.5", "microevalsEnabled": false, "intelligenceIndex": 19.4343313470652, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -13.7666666666667, "omniscienceBreakdown": {"accuracy": 0.24133333333333334, "hallucinationRate": 0.4995606326889279}, "gdpval": null, "itBenchSre": null, "tau2": 0.812865497076023, "tauBanking": null, "terminalbenchHard": 0.189393939393939, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.673333333333333, "ifbench": 0.436734693877551, "hle": 0.131603336422614, "gpqa": 0.788888888888889, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": 0.730635838150289, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.6, "price1mOutputTokens": 3, "cacheHitPrice": 0.6, "cacheHitDiscountPercent": 0.8333333333333333, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.2, "price1mBlended7To2To1": 0.8400000000000001, "price1mBlended0To1To1": 1.8, "price1mBlended100To1To1": 0.6235294117647059, "price1mBlended0To100To1": 0.6237623762376238, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 3, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ba242e40-83b7-4cd3-a0e0-b56237984914", "slug": "gpt-5-4-mini", "name": "GPT-5.4 mini (xhigh)", "shortName": "GPT-5.4 mini (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-17", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-4-mini", "name": "GPT-5.4 mini"}, "deprecated": true, "deprecatedTo": "gpt-5-6-terra-xhigh", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 24.5789419231964, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 24.906268292165187, "strategyAndOps": 26.218176423584328, "legal": 26.86897788400278, "healthcareAndMedical": 22.747445637627887, "engineering": 24.896114733058116, "economics": 30.330888670064887}, "omniscience": -18.9166666666667, "omniscienceBreakdown": {"accuracy": 0.37466666666666665, "hallucinationRate": 0.9016524520255863}, "mlcrOverall": 0.0388888888888889, "harveyLab": 0.607468519322623, "gdpPdfAllPass": 0.134, "gdpval": 1094.54, "gdpvalNormalized": 0.29727, "itBenchSre": 0.352165725047081, "tau2": 0.833333333333333, "tauBanking": 0.255670103092783, "terminalbenchHard": 0.522727272727273, "terminalBench21": 0.591760299625468, "terminalBench40": 0.0202020202020202, "scicode": 0.520833333333333, "lcr": 0.77, "ifbench": 0.73265306122449, "hle": 0.281278962001854, "gpqa": 0.874747474747475, "critpt": 0.1, "apexAgents": 0.281710914454277, "mmmuPro": 0.732947976878613, "livecodebench": null, "aime25": null, "analystAgent": 0.15, "automationBenchPartialScore": 0.26204887225711754, "enterpriseOpsGym": 0.3461653237839451, "price1mInputTokens": 0.75, "price1mOutputTokens": 4.5, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 1.24, "price1mBlended0To3To1": 1.6875, "price1mBlended7To2To1": 0.6525000000000001, "price1mBlended0To1To1": 2.625, "price1mBlended100To1To1": 0.125, "price1mBlended0To100To1": 0.7871287128712872, "intelligenceIndexTimePerTask": 269.5787190864157, "intelligenceIndexCost": {"total": 1437.799687843545, "input": 410.92485184354496, "nonCacheInput": 17.28392325, "cacheRead": 169.999064628495, "cacheWrite": 223.64186396504994, "output": 1026.874836, "reasoning": 974.8114245, "answer": 52.0634115}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.40970114992092954, "input": 0.1772433196014105, "nonCacheInput": 0.012423292166406008, "cacheRead": 0.07429466734664664, "cacheWrite": 0.0905253600883579, "output": 0.23245783031951894, "reasoning": 0.20190901815193307, "answer": 0.03054881216758588}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.05057045754331206}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0591139298768956}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.02903110862497661}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.14170767518571614}, {"slug": "scicode", "weightedCostPerTask": 0.021084019010416667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.015109767052826692}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.023660861999999994}, {"slug": "critpt", "weightedCostPerTask": 0.05597143071428571}, {"slug": "omniscience", "weightedCostPerTask": 0.0085667996625}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00488510025}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2587888578, "output": 228194408, "answer": 11569647, "reasoning": 216624761}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 44868.67070042957, "answer": 6788.624926130197, "output": 51657.29562655977}, "briefcaseBreakdown": {"overall": {"elo": 719.24, "lower95ci": 712.17, "upper95ci": 726.09}, "rubricPassRate": 0.1254355400696864, "analyticalQuality": {"elo": 617.94, "lower95ci": 605.63, "upper95ci": 631.24}, "presentation": {"elo": 782.1, "lower95ci": 768.84, "upper95ci": 795.5}}, "briefcaseTotalCost": 30.679410909609317, "timescaleData": {"medianOutputSpeed": 213.069585811646, "medianTimeToFirstChunk": 141.28010342}, "outputSpeedVariance": {"p05": 153.19418570669, "q25": 184.52912377595, "median": 213.069585811646, "q75": 235.217181580017, "p95": 267.960692380437}, "timeToFirstChunkVariance": {"p05": 80.241391019, "q25": 130.396465261, "median": 141.28010342, "q75": 164.0168582375, "p95": 178.9173536625}, "performanceByPromptType": {"long": {"medianOutputSpeed": 213.069585811646, "medianTimeToFirstChunk": 141.28010342, "medianTimeToFirstAnswerToken": 141.28010342, "medianEndToEndResponseTime": 143.62675462362134}}, "endToEndResponseTime": {"input": 141.28010342, "reasoning": 0, "answer": 2.3466512036213425, "total": 143.62675462362134}, "timeToFirstAnswerToken": {"input": 141.28010342, "reasoning": 0, "total": 141.28010342}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bb3d7e75-8e22-4082-b9d6-1db0803e042f", "slug": "k2-horizon-375b-a23b", "name": "K2 Horizon 375B A23B", "shortName": "K2 Horizon 375B A23B", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-09-03", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "k2-horizon-375b-a23b", "name": "K2 Horizon 375B A23B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 375, "inferenceParametersActiveBillions": 23, "sizeClass": "large", "contextWindowTokens": 524288, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/IFM/K2-Horizon-375B-A23B", "microevalsEnabled": false, "intelligenceIndex": 30.7949302696723, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 32.28819943751969, "strategyAndOps": 32.566729800431204, "legal": 32.17214154234174, "engineering": 33.065794519937896, "economics": 42.640542516218716}, "omniscience": -2.96666666666667, "omniscienceBreakdown": {"accuracy": 0.18183333333333335, "hallucinationRate": 0.25850478712568753}, "gdpPdfAllPass": 0.074, "gdpval": 1400, "gdpvalNormalized": 0.45, "itBenchSre": null, "tau2": null, "tauBanking": 0.342268041237113, "terminalbenchHard": null, "terminalBench21": 0.719101123595506, "terminalBench40": 0.0151515151515152, "scicode": 0.429398148148148, "lcr": 0.8, "ifbench": null, "hle": 0.319740500463392, "gpqa": 0.872727272727273, "critpt": 0.0457142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.3720802754388014, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "canonicalIntelligenceIndexTokenCount": {"input": 3718189028, "output": 125854902, "answer": 20396527, "reasoning": 105458375}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 35767.52344738368, "answer": 15749.933253652986, "output": 51517.456701036666}, "briefcaseBreakdown": {"overall": {"elo": 1298.34, "lower95ci": 1289.86, "upper95ci": 1306.75}, "rubricPassRate": 0.4164926931106472, "analyticalQuality": {"elo": 1395.34, "lower95ci": 1379.59, "upper95ci": 1411.95}, "presentation": {"elo": 1250.22, "lower95ci": 1238.27, "upper95ci": 1263.7}}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "8b8b84fb-4b24-45be-b9e2-74ed50d00ff7", "slug": "mbzuai", "name": "MBZUAI Institute of Foundation Models", "logo": "/img/logos/mbzuai_small.svg", "color": "#1521a9", "country": "ae", "url": "https://mbzuai.ac.ae/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bbd93ebe-80da-4594-bb19-61e69d0331df", "slug": "gemini-3-1-pro-preview", "name": "Gemini 3.1 Pro Preview", "shortName": "Gemini 3.1 Pro Preview", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-3-1-pro-preview", "name": "Gemini 3.1 Pro Preview"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 30.3596656132261, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 34.45009536941169, "strategyAndOps": 31.163594010409387, "legal": 44.49707785062165, "healthcareAndMedical": 31.301918241296853, "engineering": 33.60054711473266, "economics": 45.17162685356811}, "omniscience": 31.8833333333333, "omniscienceBreakdown": {"accuracy": 0.5485, "hallucinationRate": 0.5086747877445552}, "mlcrOverall": 0.155555555555556, "harveyLab": 0.588507743522941, "gdpPdfAllPass": 0.178, "gdpval": 903.94, "gdpvalNormalized": 0.20197000000000004, "itBenchSre": 0.303309120258273, "tau2": 0.956140350877193, "tauBanking": 0.214432989690722, "terminalbenchHard": 0.537878787878788, "terminalBench21": 0.737827715355805, "terminalBench40": 0.0404040404040404, "scicode": 0.586805555555556, "lcr": 0.82, "ifbench": 0.771428571428571, "hle": 0.470342910101946, "gpqa": 0.941414141414141, "critpt": 0.177142857142857, "apexAgents": 0.320058997050148, "mmmuPro": 0.824277456647399, "livecodebench": null, "aime25": null, "analystAgent": 0.4125, "automationBenchPartialScore": 0.3542771839809836, "enterpriseOpsGym": 0.42166517457475383, "price1mInputTokens": 2, "price1mOutputTokens": 12, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4.5, "price1mBlended7To2To1": 1.7399999999999998, "price1mBlended0To1To1": 7, "price1mBlended100To1To1": 0.3333333333333333, "price1mBlended0To100To1": 2.099009900990099, "intelligenceIndexTimePerTask": 145.055992849, "intelligenceIndexCost": {"total": 1310.2131291948317, "input": 505.3092771948318, "nonCacheInput": 41.119544, "cacheRead": 212.9216794227965, "cacheWrite": 251.2680537720353, "output": 804.903852, "reasoning": 691.820568, "answer": 113.083284}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.6747317275695374, "input": 0.45738411814947544, "nonCacheInput": 0.028289428701770453, "cacheRead": 0.21247096111146266, "cacheWrite": 0.21662372833624222, "output": 0.21734760942006193, "reasoning": 0.14987632226130493, "answer": 0.06747128715875697}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.09852027546878105}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.02726872759262273}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.02160319197913037}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.4149032829811538}, {"slug": "scicode", "weightedCostPerTask": 0.00829645902777778}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.01967545996292864}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.02378597}, {"slug": "critpt", "weightedCostPerTask": 0.047391682857142854}, {"slug": "omniscience", "weightedCostPerTask": 0.0026507136999999997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.010635964}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1210802196, "output": 67075321, "answer": 9423607, "reasoning": 57651714}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 12489.693521775413, "answer": 5622.60726322975, "output": 18112.30078500516}, "briefcaseBreakdown": {"overall": {"elo": 458.83, "lower95ci": 450.45, "upper95ci": 466.66}, "rubricPassRate": 0.12424242424242424, "analyticalQuality": {"elo": 294.5, "lower95ci": 278.71, "upper95ci": 309.39}, "presentation": {"elo": 358.87, "lower95ci": 341.9, "upper95ci": 373.78}}, "briefcaseTotalCost": 59.76896711772717, "timescaleData": {"medianOutputSpeed": 122.38124218976, "medianTimeToFirstChunk": 30.5797116904999}, "outputSpeedVariance": {"p05": 101.530055005049, "q25": 107.445496887504, "median": 122.38124218976, "q75": 131.949764303265, "p95": 151.012957415477}, "timeToFirstChunkVariance": {"p05": 16.1761347289999, "q25": 23.32236710675, "median": 30.5797116904999, "q75": 43.87923588825, "p95": 146.02968169175}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 128.624584249127, "medianTimeToFirstChunk": 23.881777618, "medianTimeToFirstAnswerToken": 23.881777618, "medianEndToEndResponseTime": 27.769059376140213}, "long": {"medianOutputSpeed": 122.38124218976, "medianTimeToFirstChunk": 30.5797116904999, "medianTimeToFirstAnswerToken": 30.5797116904999, "medianEndToEndResponseTime": 34.66530512829748}, "hundredK": {"medianOutputSpeed": 141.861114166218, "medianTimeToFirstChunk": 88.6684532575, "medianTimeToFirstAnswerToken": 88.6684532575, "medianEndToEndResponseTime": 92.19302729555636}, "mediumParallel": {"medianOutputSpeed": 128.982717299435, "medianTimeToFirstChunk": 15.732902043, "medianTimeToFirstAnswerToken": 15.732902043, "medianEndToEndResponseTime": 19.60939038553696}}, "endToEndResponseTime": {"input": 30.5797116904999, "reasoning": 0, "answer": 4.0855934377975816, "total": 34.66530512829748}, "timeToFirstAnswerToken": {"input": 30.5797116904999, "reasoning": 0, "total": 30.5797116904999}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 3, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bbe6d782-e630-48d5-b11c-3ce37f373f1e", "slug": "qwen3-235b-a22b-instruct-reasoning", "name": "Qwen3 235B A22B (Reasoning)", "shortName": "Qwen3 235B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-235b-a22b-instruct", "name": "Qwen3 235B A22B"}, "deprecated": true, "deprecatedTo": "qwen3-235b-a22b-instruct-2507-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 235, "inferenceParametersActiveBillions": 22, "sizeClass": "large", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-235B-A22B", "microevalsEnabled": false, "intelligenceIndex": 9.49970850374162, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -44.7, "omniscienceBreakdown": {"accuracy": 0.18533333333333332, "hallucinationRate": 0.7761865793780688}, "gdpval": null, "itBenchSre": null, "tau2": 0.239766081871345, "tauBanking": null, "terminalbenchHard": 0.0606060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.387074829931973, "hle": 0.1098, "gpqa": 0.7, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.622222222222222, "aime25": 0.82, "analystAgent": null, "price1mInputTokens": 0.7, "price1mOutputTokens": 8.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2.625, "price1mBlended7To2To1": 1.47, "price1mBlended0To1To1": 4.55, "price1mBlended100To1To1": 0.7754901960784315, "price1mBlended0To100To1": 0.7762376237623763, "timescaleData": {"medianOutputSpeed": 61.0414946384447, "medianTimeToFirstChunk": 2.69788916900001}, "outputSpeedVariance": {"p05": 50.8560988723959, "q25": 56.4823528173128, "median": 61.0414946384447, "q75": 65.6523652026925, "p95": 70.5873666502467}, "timeToFirstChunkVariance": {"p05": 2.63376273799999, "q25": 2.66484892999995, "median": 2.69788916900001, "q75": 2.78599779550006, "p95": 3.16142206840007}, "performanceByPromptType": {"long": {"medianOutputSpeed": 61.0414946384447, "medianTimeToFirstChunk": 2.69788916900001, "medianTimeToFirstAnswerToken": 35.46248662596291, "medianEndToEndResponseTime": 43.65363599020363}}, "endToEndResponseTime": {"input": 2.69788916900001, "reasoning": 32.7645974569629, "answer": 8.191149364240726, "total": 43.65363599020363}, "timeToFirstAnswerToken": {"input": 2.69788916900001, "reasoning": 32.7645974569629, "total": 35.46248662596291}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bc26bfdb-4923-4442-a6ca-e77392923581", "slug": "gpt-5-mini-minimal", "name": "GPT-5 mini (minimal)", "shortName": "GPT-5 mini (minimal)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-05-30", "isReasoning": false, "reasoningTokens": 0, "effort": {"slug": "minimal", "label": "minimal", "level": 10}, "release": {"slug": "gpt-5-mini", "name": "GPT-5 mini"}, "deprecated": true, "deprecatedTo": "gpt-5-4-mini-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 9.90615279545732, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -53.05, "omniscienceBreakdown": {"accuracy": 0.19166666666666668, "hallucinationRate": 0.8934020618556701}, "gdpval": null, "itBenchSre": null, "tau2": 0.318713450292398, "tauBanking": null, "terminalbenchHard": 0.143939393939394, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.393333333333333, "ifbench": 0.45578231292517, "hle": 0.0505097312326228, "gpqa": 0.686868686868687, "critpt": 0, "apexAgents": null, "mmmuPro": 0.583815028901734, "livecodebench": 0.544973544973545, "aime25": 0.466666666666667, "analystAgent": null, "price1mInputTokens": 0.25, "price1mOutputTokens": 2, "cacheHitPrice": 0.025, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.41, "price1mBlended0To3To1": 0.6875, "price1mBlended7To2To1": 0.26749999999999996, "price1mBlended0To1To1": 1.125, "price1mBlended100To1To1": 0.04656862745098039, "price1mBlended0To100To1": 0.26732673267326734, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 66.6462433070236, "medianTimeToFirstChunk": 1.14893859649998}, "outputSpeedVariance": {"p05": 42.7758519821865, "q25": 60.3970062014928, "median": 66.6462433070236, "q75": 82.3002167479695, "p95": 90.5587189599596}, "timeToFirstChunkVariance": {"p05": 0.891960922000033, "q25": 0.940102167500029, "median": 1.14893859649998, "q75": 1.55877467975001, "p95": 3.24483301399995}, "performanceByPromptType": {"long": {"medianOutputSpeed": 66.6462433070236, "medianTimeToFirstChunk": 1.14893859649998, "medianTimeToFirstAnswerToken": 1.14893859649998, "medianEndToEndResponseTime": 8.651236928554757}}, "endToEndResponseTime": {"input": 1.14893859649998, "reasoning": 0, "answer": 7.502298332054777, "total": 8.651236928554757}, "timeToFirstAnswerToken": {"input": 1.14893859649998, "reasoning": 0, "total": 1.14893859649998}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 3, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bc4579d2-9c46-46c3-ace0-454039bf21bb", "slug": "deepseek-v2-5", "name": "DeepSeek-V2.5 (Dec '24)", "shortName": "DeepSeek-V2.5 (Dec)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-10", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v2-5", "name": "DeepSeek-V2.5 (Dec '24)"}, "deprecated": true, "deprecatedTo": "deepseek-v3-0324", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 236, "inferenceParametersActiveBillions": 21, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "DEEPSEEK LICENSE AGREEMENT", "licenseUrl": "https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V2.5-1210", "microevalsEnabled": false, "intelligenceIndex": 6.61726180583266, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": 0.423232323232323, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bcca0e70-7e80-4c07-b1fa-b33bcfb19e51", "slug": "gemini-2-0-flash", "name": "Gemini 2.0 Flash (Feb '25)", "shortName": "Gemini 2.0 Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-05", "knowledgeCutoffDate": "2024-06-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-2-0-flash", "name": "Gemini 2.0 Flash (Feb '25)"}, "deprecated": true, "deprecatedTo": "gemini-2-5-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.94143668759525, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -42.5333333333333, "omniscienceBreakdown": {"accuracy": 0.23466666666666666, "hallucinationRate": 0.8623693379790941}, "gdpval": null, "itBenchSre": null, "tau2": 0.295321637426901, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.313333333333333, "ifbench": 0.402040816326531, "hle": 0.0426, "gpqa": 0.623232323232323, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.334391534391534, "aime25": 0.216666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": true, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bcf8db0a-3bb6-4d82-9516-0f57370c85a6", "slug": "gpt-5-6-terra", "name": "GPT-5.6 Terra (max)", "shortName": "GPT-5.6 Terra (max)", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "gpt-5-6-terra", "name": "GPT-5.6 Terra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 42.2514998239494, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 41.636133424167866, "strategyAndOps": 47.81371992892074, "legal": 41.70574730388043, "healthcareAndMedical": 40.53153668318086, "engineering": 43.24684559496729, "economics": 45.17953568118627}, "omniscience": 0.05, "omniscienceBreakdown": {"accuracy": 0.468, "hallucinationRate": 0.8787593984962406}, "mlcrOverall": 0.316666666666667, "harveyLab": 0.851787523520046, "gdpPdfAllPass": 0.24, "gdpval": 1476.96, "gdpvalNormalized": 0.48848, "itBenchSre": 0.510357815442561, "tau2": 0.862573099415205, "tauBanking": 0.402061855670103, "terminalbenchHard": 0.575757575757576, "terminalBench21": 0.880149812734082, "terminalBench40": 0.353535353535354, "scicode": 0.549768518518518, "lcr": 0.83, "ifbench": 0.712244897959184, "hle": 0.429101019462465, "gpqa": 0.925252525252525, "critpt": 0.3, "apexAgents": 0.389380530973451, "mmmuPro": 0.806936416184971, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5964995802534495, "enterpriseOpsGym": 0.38495971351835273, "price1mInputTokens": 2, "price1mOutputTokens": 12, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4.5, "price1mBlended7To2To1": 1.7399999999999998, "price1mBlended0To1To1": 7, "price1mBlended100To1To1": 0.3333333333333333, "price1mBlended0To100To1": 2.099009900990099, "intelligenceIndexTimePerTask": 434.0907023751559, "intelligenceIndexCost": {"total": 2500.715709911936, "input": 1038.719841911936, "nonCacheInput": 57.770922, "cacheRead": 648.4629313120057, "cacheWrite": 332.48598859993035, "output": 1461.995868, "reasoning": 1251.192432, "answer": 210.80343600000003}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.3987235612691513, "input": 0.9319539940852251, "nonCacheInput": 0.04539704709061227, "cacheRead": 0.6595491203855293, "cacheWrite": 0.22700782660908353, "output": 0.4667695671839262, "reasoning": 0.3125270600792794, "answer": 0.15424250710464688}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.4241689750816913}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.12416013690202822}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.03648857799851444}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.638743408501164}, {"slug": "scicode", "weightedCostPerTask": 0.011439322222222223}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.022773022613531046}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.058910491999999995}, {"slug": "critpt", "weightedCostPerTask": 0.06084076}, {"slug": "omniscience", "weightedCostPerTask": 0.010550521949999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.010648344}]}, "canonicalIntelligenceIndexTokenCount": {"input": 3404194513, "output": 121832989, "answer": 17566953, "reasoning": 104266036}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 26043.92167327328, "answer": 12853.54225872057, "output": 38897.46393199385}, "briefcaseBreakdown": {"overall": {"elo": 1330, "lower95ci": 1322.99, "upper95ci": 1337.13}, "rubricPassRate": 0.3414141414141414, "analyticalQuality": {"elo": 1341.06, "lower95ci": 1325.63, "upper95ci": 1354.86}, "presentation": {"elo": 1520.25, "lower95ci": 1507.79, "upper95ci": 1533.03}}, "briefcaseTotalCost": 257.32917821622607, "timescaleData": {"medianOutputSpeed": 90.7576880098005, "medianTimeToFirstChunk": 139.756118515}, "outputSpeedVariance": {"p05": 71.4898351037674, "q25": 80.8275633666493, "median": 90.7576880098005, "q75": 100.504574291085, "p95": 131.673551350747}, "timeToFirstChunkVariance": {"p05": 50.7168033368, "q25": 93.0493134055, "median": 139.756118515, "q75": 233.6571611945, "p95": 374.386848036}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 101.969898160774, "medianTimeToFirstChunk": 140.034146216, "medianTimeToFirstAnswerToken": 140.034146216, "medianEndToEndResponseTime": 144.93755407477477}, "long": {"medianOutputSpeed": 90.7576880098005, "medianTimeToFirstChunk": 139.756118515, "medianTimeToFirstAnswerToken": 139.756118515, "medianEndToEndResponseTime": 145.26529367100449}, "hundredK": {"medianOutputSpeed": 135.726510649745, "medianTimeToFirstChunk": 42.56422566, "medianTimeToFirstAnswerToken": 42.56422566, "medianEndToEndResponseTime": 46.24810434815324}, "mediumParallel": {"medianOutputSpeed": 108.602126192908, "medianTimeToFirstChunk": 258.629825381, "medianTimeToFirstAnswerToken": 258.629825381, "medianEndToEndResponseTime": 263.2337868090834}}, "endToEndResponseTime": {"input": 139.756118515, "reasoning": 0, "answer": 5.5091751560044955, "total": 145.26529367100449}, "timeToFirstAnswerToken": {"input": 139.756118515, "reasoning": 0, "total": 139.756118515}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 6, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bd2c3517-00d8-4ba5-a989-1f1e52f3ffab", "slug": "gemma-3n-e4b-preview-0520", "name": "Gemma 3n E4B Instruct Preview (May '25)", "shortName": "Gemma 3n E4B (May)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-20", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-3n-e4b-preview-0520", "name": "Gemma 3n E4B Instruct Preview (May '25)"}, "deprecated": true, "deprecatedTo": "gemma-3n-e4b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8.39, "inferenceParametersActiveBillions": 4, "sizeClass": "small", "contextWindowTokens": 32000, "licenseName": "Gemma license", "licenseUrl": "https://ai.google.dev/gemma/terms", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-3n-E4B-it-litert-preview", "microevalsEnabled": false, "intelligenceIndex": 5.81096980860449, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0481927710843374, "gpqa": 0.277777777777778, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.137566137566138, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bddebfd3-0a8d-47f5-b722-bc4c2ca5a5dc", "slug": "kimi-k2-thinking", "name": "Kimi K2 Thinking", "shortName": "Kimi K2 Thinking", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-06", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "kimi-k2-thinking", "name": "Kimi K2 Thinking"}, "deprecated": true, "deprecatedTo": "kimi-k2-5", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 1000, "inferenceParametersActiveBillions": 32, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Modified MIT License", "licenseUrl": "https://huggingface.co/moonshotai/Kimi-K2-Thinking/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-K2-Thinking", "microevalsEnabled": false, "intelligenceIndex": 22.0200270318461, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -21.4166666666667, "omniscienceBreakdown": {"accuracy": 0.30866666666666664, "hallucinationRate": 0.756268081002893}, "gdpval": null, "itBenchSre": null, "tau2": 0.929824561403509, "tauBanking": null, "terminalbenchHard": 0.310606060606061, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.72, "ifbench": 0.680952380952381, "hle": 0.238183503243744, "gpqa": 0.838383838383838, "critpt": 0.0257142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.852910052910053, "aime25": 0.946666666666667, "analystAgent": null, "price1mInputTokens": 0.6, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.075, "price1mBlended7To2To1": 0.79, "price1mBlended0To1To1": 1.55, "price1mBlended100To1To1": 0.6186274509803922, "price1mBlended0To100To1": 0.6188118811881188, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 118.519971393493, "medianTimeToFirstChunk": 1.367697037}, "outputSpeedVariance": {"p05": 39.1353406697354, "q25": 66.3170416991142, "median": 118.519971393493, "q75": 158.719292494363, "p95": 275.385518358243}, "timeToFirstChunkVariance": {"p05": 0.726960011799974, "q25": 1.0958410989997, "median": 1.367697037, "q75": 2.05672185200001, "p95": 8.1068154942}, "performanceByPromptType": {"long": {"medianOutputSpeed": 118.519971393493, "medianTimeToFirstChunk": 1.367697037, "medianTimeToFirstAnswerToken": 18.242490175110767, "medianEndToEndResponseTime": 22.461188459638457}}, "endToEndResponseTime": {"input": 1.367697037, "reasoning": 16.874793138110768, "answer": 4.218698284527692, "total": 22.461188459638457}, "timeToFirstAnswerToken": {"input": 1.367697037, "reasoning": 16.874793138110768, "total": 18.242490175110767}, "performanceDataSource": {"type": "median"}, "hostModelCount": 4, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "be185709-ddb4-4268-9597-856464359b25", "slug": "mimo-v2-flash-reasoning", "name": "MiMo-V2-Flash (Reasoning)", "shortName": "MiMo-V2-Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "mimo-v2-flash", "name": "MiMo-V2-Flash"}, "deprecated": true, "deprecatedTo": "mimo-v2-0206", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 309, "inferenceParametersActiveBillions": 15, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "MIT", "licenseUrl": "https://choosealicense.com/licenses/mit/", "modelWeightsSourceUrl": "https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash", "microevalsEnabled": false, "intelligenceIndex": 20.8177287591331, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -45.35, "omniscienceBreakdown": {"accuracy": 0.24833333333333332, "hallucinationRate": 0.9337028824833703}, "gdpval": null, "itBenchSre": null, "tau2": 0.950292397660819, "tauBanking": null, "terminalbenchHard": 0.28030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.706666666666667, "ifbench": 0.642176870748299, "hle": 0.228452270620945, "gpqa": 0.846464646464647, "critpt": 0.0428571428571429, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.867724867724868, "aime25": 0.963333333333333, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15000000000000002, "price1mBlended7To2To1": 0.12000000000000002, "price1mBlended0To1To1": 0.2, "price1mBlended100To1To1": 0.10196078431372549, "price1mBlended0To100To1": 0.10198019801980199, "openness": {"opennessIndex": 52.77777777777778, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Xiaomi"}, "hostModelCount": 1, "creator": {"id": "5147c8b4-61d5-4070-9324-8adf8aa144c2", "slug": "xiaomi", "name": "Xiaomi", "logo": "/img/logos/xiaomi_small.svg", "color": "#ff6900", "country": "cn", "url": "https://huggingface.co/XiaomiMiMo"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bf220674-68bd-43cc-a1b8-ce5ed4d2f18d", "slug": "deepseek-v4-pro-0424", "name": "DeepSeek V4 Pro 0424 (Reasoning, Max Effort)", "shortName": "DeepSeek V4 Pro (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 4375, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "deepseek-v4-pro-0424", "name": "DeepSeek V4 Pro 0424"}, "deprecated": true, "deprecatedTo": "deepseek-v4-pro", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1600, "inferenceParametersActiveBillions": 49, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro", "microevalsEnabled": true, "intelligenceIndex": 30.8650601315524, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 35.110658672190475, "strategyAndOps": 39.970125151528464, "legal": 34.17941329045252, "healthcareAndMedical": 33.491492283098474, "engineering": 31.959797465413384, "economics": 37.85255987411184}, "omniscience": -10.7333333333333, "omniscienceBreakdown": {"accuracy": 0.4295, "hallucinationRate": 0.9409874379199532}, "mlcrOverall": 0.211111111111111, "harveyLab": 0.843971631205674, "gdpPdfAllPass": 0.134, "gdpval": 1223.37, "gdpvalNormalized": 0.3616849999999999, "itBenchSre": 0.383239171374765, "tau2": 0.961988304093567, "tauBanking": 0.301030927835052, "terminalbenchHard": 0.462121212121212, "terminalBench21": 0.640449438202247, "terminalBench40": 0.146464646464646, "scicode": 0.508101851851852, "lcr": 0.746666666666667, "ifbench": 0.764625850340136, "hle": 0.375347544022243, "gpqa": 0.887878787878788, "critpt": 0.128571428571429, "apexAgents": 0.242625368731563, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.1875, "automationBenchPartialScore": 0.5628968557434271, "enterpriseOpsGym": 0.40435690838555655, "price1mInputTokens": 0.435, "price1mOutputTokens": 0.87, "cacheHitPrice": 0.0036, "cacheHitDiscountPercent": 0.9917241379310345, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.54375, "price1mBlended7To2To1": 0.17652, "price1mBlended0To1To1": 0.6525, "price1mBlended100To1To1": 0.016323529411764705, "price1mBlended0To100To1": 0.4393069306930693, "intelligenceIndexTimePerTask": 432.1132104590177, "intelligenceIndexCost": {"total": 277.3048434620626, "input": 92.84495091206261, "nonCacheInput": 6.8940975, "cacheRead": 15.995607714808935, "cacheWrite": 69.95524569725367, "output": 184.45989254999998, "reasoning": 163.92131274, "answer": 20.538579809999998}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.12152059767597723, "input": 0.07898078838232103, "nonCacheInput": 0.0038584543743672827, "cacheRead": 0.019109338247994517, "cacheWrite": 0.05601299575995922, "output": 0.042539809293656215, "reasoning": 0.028476501430317425, "answer": 0.014063307863338786}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.013879831303687069}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.005716918994109132}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.004183499352645825}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.07661310060659526}, {"slug": "scicode", "weightedCostPerTask": 0.00113605234375}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.004635136392261353}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0029112200999999996}, {"slug": "critpt", "weightedCostPerTask": 0.009288799221428574}, {"slug": "omniscience", "weightedCostPerTask": 0.0008354692214999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0023205701400000004}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4619889522, "output": 212022865, "answer": 23607563, "reasoning": 188415302}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 32731.610839445308, "answer": 16164.721681998606, "output": 48896.33252144391}, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 924.56, "lower95ci": 918.85, "upper95ci": 930.86}, "rubricPassRate": 0.23938679245283018, "analyticalQuality": {"elo": 885.9, "lower95ci": 875.2, "upper95ci": 897.43}, "presentation": {"elo": 935.69, "lower95ci": 924, "upper95ci": 946.89}}, "briefcaseTotalCost": 8.420430990903489, "timescaleData": {"medianOutputSpeed": 85.52229651013, "medianTimeToFirstChunk": 1.63759955649997}, "outputSpeedVariance": {"p05": 46.5037178435696, "q25": 69.5293229713191, "median": 85.52229651013, "q75": 117.17178248443, "p95": 145.717861916691}, "timeToFirstChunkVariance": {"p05": 0.975360288900015, "q25": 1.53040445399995, "median": 1.63759955649997, "q75": 1.91770629275001, "p95": 3.55981127014999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 83.5517305108438, "medianTimeToFirstChunk": 1.18387286399997, "medianTimeToFirstAnswerToken": 53.54664229140506, "medianEndToEndResponseTime": 59.530958797394206}, "long": {"medianOutputSpeed": 85.52229651013, "medianTimeToFirstChunk": 1.63759955649997, "medianTimeToFirstAnswerToken": 52.793849780461, "medianEndToEndResponseTime": 58.640278377485124}, "hundredK": {"medianOutputSpeed": 98.6503466362919, "medianTimeToFirstChunk": 6.04248080100001, "medianTimeToFirstAnswerToken": 50.39103252104543, "medianEndToEndResponseTime": 55.45943843190776}, "mediumParallel": {"medianOutputSpeed": 53.0804942460448, "medianTimeToFirstChunk": 1.17243711399999, "medianTimeToFirstAnswerToken": 83.5944277556187, "medianEndToEndResponseTime": 93.01408382894654}}, "endToEndResponseTime": {"input": 1.63759955649997, "reasoning": 51.15625022396103, "answer": 5.8464285970241185, "total": 58.640278377485124}, "timeToFirstAnswerToken": {"input": 1.63759955649997, "reasoning": 51.15625022396103, "total": 52.793849780461}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 11, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "bf60740e-6aa5-422f-ba49-ef6e9d171205", "slug": "qwen3-32b-instruct", "name": "Qwen3 32B (Non-reasoning)", "shortName": "Qwen3 32B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-32b-instruct", "name": "Qwen3 32B"}, "deprecated": true, "deprecatedTo": "qwen3-30b-a3b-2507", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32.8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-32B", "microevalsEnabled": false, "intelligenceIndex": 7.3442784206229, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.314965986394558, "hle": 0.0413, "gpqa": 0.535353535353535, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.287830687830688, "aime25": 0.196666666666667, "analystAgent": null, "price1mInputTokens": 0.16, "price1mOutputTokens": 0.64, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.28, "price1mBlended7To2To1": 0.20800000000000002, "price1mBlended0To1To1": 0.4, "price1mBlended100To1To1": 0.16470588235294117, "price1mBlended0To100To1": 0.16475247524752476, "timescaleData": {"medianOutputSpeed": 105.205082699026, "medianTimeToFirstChunk": 2.50416632199997}, "outputSpeedVariance": {"p05": 78.9136143556935, "q25": 100.208109646378, "median": 105.205082699026, "q75": 107.033037797739, "p95": 109.42897076705}, "timeToFirstChunkVariance": {"p05": 2.38140645629997, "q25": 2.42217905850004, "median": 2.50416632199997, "q75": 2.64461023574995, "p95": 2.87424043275001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 105.205082699026, "medianTimeToFirstChunk": 2.50416632199997, "medianTimeToFirstAnswerToken": 2.50416632199997, "medianEndToEndResponseTime": 7.256788411851044}}, "endToEndResponseTime": {"input": 2.50416632199997, "reasoning": 0, "answer": 4.752622089851074, "total": 7.256788411851044}, "timeToFirstAnswerToken": {"input": 2.50416632199997, "reasoning": 0, "total": 2.50416632199997}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 4, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c07e65e6-32fc-451e-938d-7477a1c3ffcc", "slug": "grok-4-6-low", "name": "Grok 4.6 (low)", "shortName": "Grok 4.6 (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "grok-4-6", "name": "Grok 4.6"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 500000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 35.4148453482174, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 38.8776958268697, "strategyAndOps": 44.056012484082665, "legal": 44.1529763748085, "engineering": 35.244063056822704, "economics": 45.752378571980245}, "omniscience": 25.9, "omniscienceBreakdown": {"accuracy": 0.43283333333333335, "hallucinationRate": 0.30649426976197475}, "gdpPdfAllPass": 0.158, "gdpval": 1461.3, "gdpvalNormalized": 0.48064999999999997, "itBenchSre": null, "tau2": null, "tauBanking": 0.381443298969072, "terminalbenchHard": null, "terminalBench21": 0.752808988764045, "terminalBench40": 0.0303030303030303, "scicode": 0.494212962962963, "lcr": 0.806666666666667, "ifbench": null, "hle": 0.276181649675626, "gpqa": 0.878787878787879, "critpt": 0.0571428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.53445400590317, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.35, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 0.5686274509803921, "price1mBlended0To100To1": 2.0396039603960396, "intelligenceIndexTimePerTask": 185.00645380958625, "intelligenceIndexCost": {"total": 760.748774423948, "input": 636.019400423948, "nonCacheInput": 49.030226, "cacheRead": 223.73648119201732, "cacheWrite": 363.2526932319307, "output": 124.72937399999999, "reasoning": 55.155816, "answer": 69.57355799999999}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.47528534374531, "input": 0.4137012603073541, "nonCacheInput": 0.03293105428765539, "cacheRead": 0.15161614673011053, "cacheWrite": 0.2291540592895882, "output": 0.061584083437955996, "reasoning": 0.01476484635002166, "answer": 0.04681923708793434}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.12644011678689002}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.03793102280583559}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.026360951029517868}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.24495469021090666}, {"slug": "scicode", "weightedCostPerTask": 0.0009795159722222222}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00132053484708063}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.023192446000000002}, {"slug": "critpt", "weightedCostPerTask": 0.003905457142857143}, {"slug": "omniscience", "weightedCostPerTask": 0.00039197094999999995}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.009808638}]}, "canonicalIntelligenceIndexTokenCount": {"input": 653614422, "output": 20788229, "answer": 11595593, "reasoning": 9192636}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 2460.8077250036104, "answer": 7803.206181322389, "output": 10264.013906326}, "briefcaseBreakdown": {"overall": {"elo": 1293.13, "lower95ci": 1286.46, "upper95ci": 1299.77}, "rubricPassRate": 0.402020202020202, "analyticalQuality": {"elo": 1386.73, "lower95ci": 1373.32, "upper95ci": 1399.54}, "presentation": {"elo": 1261.2, "lower95ci": 1249.5, "upper95ci": 1273.69}}, "briefcaseTotalCost": 76.70700418404661, "timescaleData": {"medianOutputSpeed": 55.9601537743113, "medianTimeToFirstChunk": 5.96980440549999}, "outputSpeedVariance": {"p05": 25.6429867372192, "q25": 49.8746623508509, "median": 55.9601537743113, "q75": 66.222158756409, "p95": 74.6242895806295}, "timeToFirstChunkVariance": {"p05": 4.2083316081, "q25": 4.98736647924992, "median": 5.96980440549999, "q75": 8.70246156400001, "p95": 12.4060617366999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 53.2982207602825, "medianTimeToFirstChunk": 3.9972518875, "medianTimeToFirstAnswerToken": 3.9972518875, "medianEndToEndResponseTime": 13.378428085648004}, "long": {"medianOutputSpeed": 55.9601537743113, "medianTimeToFirstChunk": 5.96980440549999, "medianTimeToFirstAnswerToken": 5.96980440549999, "medianEndToEndResponseTime": 14.904733391158473}, "hundredK": {"medianOutputSpeed": 67.7555420362135, "medianTimeToFirstChunk": 80.484463008, "medianTimeToFirstAnswerToken": 80.484463008, "medianEndToEndResponseTime": 87.86393315868914}, "mediumParallel": {"medianOutputSpeed": 52.5102997224747, "medianTimeToFirstChunk": 4.48256141700005, "medianTimeToFirstAnswerToken": 4.48256141700005, "medianEndToEndResponseTime": 14.004502876915147}}, "endToEndResponseTime": {"input": 5.96980440549999, "reasoning": 0, "answer": 8.934928985658482, "total": 14.904733391158473}, "timeToFirstAnswerToken": {"input": 5.96980440549999, "reasoning": 0, "total": 5.96980440549999}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 1, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c1045dc0-4fd3-4adb-9548-18763e0d051f", "slug": "gpt-4o", "name": "GPT-4o (Nov '24)", "shortName": "GPT-4o (Nov)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-11-20", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4o", "name": "GPT-4o (Nov '24)"}, "deprecated": true, "deprecatedTo": "gpt-4o-chatgpt-03-25", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.4416392330287, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -10.5166666666667, "omniscienceBreakdown": {"accuracy": 0.19866666666666666, "hallucinationRate": 0.37915973377703827}, "gdpval": null, "itBenchSre": null, "tau2": 0.251461988304094, "tauBanking": null, "terminalbenchHard": 0.0833333333333333, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.493333333333333, "ifbench": 0.342857142857143, "hle": 0.0242, "gpqa": 0.543434343434343, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.308994708994709, "aime25": 0.06, "analystAgent": null, "price1mInputTokens": 2.5, "price1mOutputTokens": 10, "cacheHitPrice": 1.5, "cacheHitDiscountPercent": 0.4, "cacheWritePrice": null, "pricePer1k1mpImages": 1.9125, "price1mBlended0To3To1": 4.375, "price1mBlended7To2To1": 2.55, "price1mBlended0To1To1": 6.25, "price1mBlended100To1To1": 1.5931372549019607, "price1mBlended0To100To1": 2.5742574257425743, "timescaleData": {"medianOutputSpeed": 123.283049638527, "medianTimeToFirstChunk": 1.03646241249996}, "outputSpeedVariance": {"p05": 79.8998808994976, "q25": 107.170364728048, "median": 123.283049638527, "q75": 171.439522208089, "p95": 192.917484194638}, "timeToFirstChunkVariance": {"p05": 0.768854582199976, "q25": 0.914180991750012, "median": 1.03646241249996, "q75": 1.35701285625, "p95": 1.90263664284989}, "performanceByPromptType": {"long": {"medianOutputSpeed": 123.283049638527, "medianTimeToFirstChunk": 1.03646241249996, "medianTimeToFirstAnswerToken": 1.03646241249996, "medianEndToEndResponseTime": 5.092170001386094}}, "endToEndResponseTime": {"input": 1.03646241249996, "reasoning": 0, "answer": 4.0557075888861345, "total": 5.092170001386094}, "timeToFirstAnswerToken": {"input": 1.03646241249996, "reasoning": 0, "total": 1.03646241249996}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c1c5db7c-968f-445a-a274-7b5689348bf8", "slug": "g9v3-39a5b", "name": "G9v3-39A5B", "shortName": "G9v3-39A5B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "g9v3-39a5b", "name": "G9v3-39A5B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 39, "inferenceParametersActiveBillions": 5, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ai9stars/G9v3-39A5B", "microevalsEnabled": false, "intelligenceIndex": 21.8316172646825, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 3.76666666666667, "omniscienceBreakdown": {"accuracy": 0.14866666666666667, "hallucinationRate": 0.13038371182458888}, "gdpval": 1188.86, "gdpvalNormalized": 0.34442999999999996, "itBenchSre": null, "tau2": null, "tauBanking": 0.220618556701031, "terminalbenchHard": null, "terminalBench21": 0.325842696629214, "terminalBench40": null, "scicode": 0.368055555555556, "lcr": 0.653333333333333, "ifbench": null, "hle": 0.174698795180723, "gpqa": 0.805050505050505, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "9f712f4a-7885-4632-974d-30b4d93c3f7c", "slug": "ai9star", "name": "AI9Stars", "logo": "/img/logos/ai9stars.svg", "color": "#795BCF", "country": "cn", "url": "https://github.com/AI9Stars"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c298d1a8-606c-4971-8613-ccdaaf941043", "slug": "gpt-5-4-nano-non-reasoning", "name": "GPT-5.4 nano (Non-Reasoning)", "shortName": "GPT-5.4 nano (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-17", "knowledgeCutoffDate": "2025-08-31", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-5-4-nano", "name": "GPT-5.4 nano"}, "deprecated": true, "deprecatedTo": "gpt-5-6-luna-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.6892323777027, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -37.4833333333333, "omniscienceBreakdown": {"accuracy": 0.14883333333333335, "hallucinationRate": 0.6152339925592324}, "gdpval": 680.74, "gdpvalNormalized": 0.09037, "itBenchSre": 0.12909604519774, "tau2": 0.347953216374269, "tauBanking": null, "terminalbenchHard": 0.242424242424242, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.296666666666667, "ifbench": 0.327210884353741, "hle": 0.0407784986098239, "gpqa": 0.557575757575758, "critpt": 0, "apexAgents": null, "mmmuPro": 0.43757225433526, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 1.25, "cacheHitPrice": 0.02, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.5, "price1mBlended0To3To1": 0.4625, "price1mBlended7To2To1": 0.179, "price1mBlended0To1To1": 0.725, "price1mBlended100To1To1": 0.03382352941176471, "price1mBlended0To100To1": 0.2103960396039604, "timescaleData": {"medianOutputSpeed": 147.53612287409, "medianTimeToFirstChunk": 0.85163302849999}, "outputSpeedVariance": {"p05": 98.6656508298856, "q25": 123.477915272853, "median": 147.53612287409, "q75": 164.497743743003, "p95": 180.80974096641}, "timeToFirstChunkVariance": {"p05": 0.595323742849996, "q25": 0.662588341999935, "median": 0.85163302849999, "q75": 1.00952666249999, "p95": 2.03676238014999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 147.53612287409, "medianTimeToFirstChunk": 0.85163302849999, "medianTimeToFirstAnswerToken": 0.85163302849999, "medianEndToEndResponseTime": 4.240633567891344}}, "endToEndResponseTime": {"input": 0.85163302849999, "reasoning": 0, "answer": 3.389000539391353, "total": 4.240633567891344}, "timeToFirstAnswerToken": {"input": 0.85163302849999, "reasoning": 0, "total": 0.85163302849999}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c2b1e769-7aee-4669-8076-73918bdebf6c", "slug": "claude-4-5-haiku", "name": "Claude 4.5 Haiku (Non-reasoning)", "shortName": "Claude 4.5 Haiku (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-15", "knowledgeCutoffDate": "2025-07-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-4-5-haiku", "name": "Claude 4.5 Haiku"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 15.410949885381, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -7.56666666666667, "omniscienceBreakdown": {"accuracy": 0.14433333333333334, "hallucinationRate": 0.2571094663030775}, "mlcrOverall": 0.0444444444444444, "gdpval": null, "itBenchSre": null, "tau2": 0.324561403508772, "tauBanking": null, "terminalbenchHard": 0.272727272727273, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.496666666666667, "ifbench": 0.420408163265306, "hle": 0.0421686746987952, "gpqa": 0.646464646464646, "critpt": 0, "apexAgents": null, "mmmuPro": 0.551445086705202, "livecodebench": 0.511111111111111, "aime25": 0.39, "analystAgent": null, "price1mInputTokens": 1, "price1mOutputTokens": 5, "cacheHitPrice": 0.1, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 1.25, "pricePer1k1mpImages": 1.334, "price1mBlended0To3To1": 2, "price1mBlended7To2To1": 0.77, "price1mBlended0To1To1": 3, "price1mBlended100To1To1": 0.1568627450980392, "price1mBlended0To100To1": 1.0396039603960396, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 88.091801870162, "medianTimeToFirstChunk": 0.67424242650003}, "outputSpeedVariance": {"p05": 57.9317526107776, "q25": 73.4960571733361, "median": 88.091801870162, "q75": 111.583127207515, "p95": 129.295278344629}, "timeToFirstChunkVariance": {"p05": 0.534535581050001, "q25": 0.61141598725003, "median": 0.67424242650003, "q75": 0.837756133749973, "p95": 1.50653166060003}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 99.1535859877656, "medianTimeToFirstChunk": 0.526257938000015, "medianTimeToFirstAnswerToken": 0.526257938000015, "medianEndToEndResponseTime": 5.568939904759081}, "long": {"medianOutputSpeed": 88.091801870162, "medianTimeToFirstChunk": 0.67424242650003, "medianTimeToFirstAnswerToken": 0.67424242650003, "medianEndToEndResponseTime": 6.350139495071145}, "hundredK": {"medianOutputSpeed": 78.4989355706641, "medianTimeToFirstChunk": 2.65564414299999, "medianTimeToFirstAnswerToken": 2.65564414299999, "medianEndToEndResponseTime": 9.025157262702155}, "mediumParallel": {"medianOutputSpeed": 91.8044536255639, "medianTimeToFirstChunk": 0.588118561000101, "medianTimeToFirstAnswerToken": 0.588118561000101, "medianEndToEndResponseTime": 6.034477427633232}}, "endToEndResponseTime": {"input": 0.67424242650003, "reasoning": 0, "answer": 5.675897068571115, "total": 6.350139495071145}, "timeToFirstAnswerToken": {"input": 0.67424242650003, "reasoning": 0, "total": 0.67424242650003}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c3274a19-6d3c-4d01-ab9b-5055a0a40429", "slug": "gpt-5-mini-medium", "name": "GPT-5 mini (medium)", "shortName": "GPT-5 mini (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-05-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-5-mini", "name": "GPT-5 mini"}, "deprecated": true, "deprecatedTo": "gpt-5-4-mini-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 20.5991778305353, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -11.0333333333333, "omniscienceBreakdown": {"accuracy": 0.23066666666666666, "hallucinationRate": 0.44324090121317156}, "gdpval": null, "itBenchSre": null, "tau2": 0.710526315789474, "tauBanking": null, "terminalbenchHard": 0.287878787878788, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.723333333333333, "ifbench": 0.71156462585034, "hle": 0.159406858202039, "gpqa": 0.803030303030303, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": 0.688439306358381, "livecodebench": 0.692063492063492, "aime25": 0.85, "analystAgent": null, "price1mInputTokens": 0.25, "price1mOutputTokens": 2, "cacheHitPrice": 0.025, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.41, "price1mBlended0To3To1": 0.6875, "price1mBlended7To2To1": 0.26749999999999996, "price1mBlended0To1To1": 1.125, "price1mBlended100To1To1": 0.04656862745098039, "price1mBlended0To100To1": 0.26732673267326734, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 66.5066385940983, "medianTimeToFirstChunk": 18.562648987}, "outputSpeedVariance": {"p05": 49.8409904707258, "q25": 62.4875291517177, "median": 66.5066385940983, "q75": 74.1507064898267, "p95": 86.6312290912455}, "timeToFirstChunkVariance": {"p05": 8.31984541899996, "q25": 13.3543562745, "median": 18.562648987, "q75": 30.448773765, "p95": 57.8941200085499}, "performanceByPromptType": {"long": {"medianOutputSpeed": 66.5066385940983, "medianTimeToFirstChunk": 18.562648987, "medianTimeToFirstAnswerToken": 18.562648987, "medianEndToEndResponseTime": 26.080695464308647}}, "endToEndResponseTime": {"input": 18.562648987, "reasoning": 0, "answer": 7.518046477308646, "total": 26.080695464308647}, "timeToFirstAnswerToken": {"input": 18.562648987, "reasoning": 0, "total": 18.562648987}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c3738fb0-3408-4430-a699-760ae4b70c93", "slug": "gpt-5-minimal", "name": "GPT-5 (minimal)", "shortName": "GPT-5 (minimal)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-09-30", "isReasoning": false, "reasoningTokens": 0, "effort": {"slug": "minimal", "label": "minimal", "level": 10}, "release": {"slug": "gpt-5", "name": "GPT-5"}, "deprecated": true, "deprecatedTo": "gpt-5-1-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.4481891190946, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -33.8, "omniscienceBreakdown": {"accuracy": 0.29633333333333334, "hallucinationRate": 0.901468498342018}, "gdpval": null, "itBenchSre": null, "tau2": 0.669590643274854, "tauBanking": null, "terminalbenchHard": 0.181818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.45578231292517, "hle": 0.0602409638554217, "gpqa": 0.672727272727273, "critpt": 0, "apexAgents": null, "mmmuPro": 0.620809248554913, "livecodebench": 0.557671957671958, "aime25": 0.316666666666667, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.788, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 1.3375, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.3366336633663367, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 87.1090071276905, "medianTimeToFirstChunk": 1.29668084200001}, "outputSpeedVariance": {"p05": 30.8563431410058, "q25": 53.4217062108089, "median": 87.1090071276905, "q75": 112.535215704382, "p95": 133.294423656628}, "timeToFirstChunkVariance": {"p05": 1.07215590130005, "q25": 1.1663253685, "median": 1.29668084200001, "q75": 1.6569026415, "p95": 2.39732809805}, "performanceByPromptType": {"long": {"medianOutputSpeed": 87.1090071276905, "medianTimeToFirstChunk": 1.29668084200001, "medianTimeToFirstAnswerToken": 1.29668084200001, "medianEndToEndResponseTime": 7.036615396265619}}, "endToEndResponseTime": {"input": 1.29668084200001, "reasoning": 0, "answer": 5.739934554265609, "total": 7.036615396265619}, "timeToFirstAnswerToken": {"input": 1.29668084200001, "reasoning": 0, "total": 1.29668084200001}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 3, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c3f12f61-9d57-4e2c-9106-5a82bb1cfee2", "slug": "diffusiongemma-26b-a4b", "name": "DiffusionGemma 26B A4B", "shortName": "DiffusionGemma 26B A4B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "diffusiongemma-26b-a4b", "name": "DiffusionGemma 26B A4B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 25.2, "inferenceParametersActiveBillions": 3.8, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/diffusiongemma-26B-A4B-it", "microevalsEnabled": false, "intelligenceIndex": 9.51014305662543, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -59.2333333333333, "omniscienceBreakdown": {"accuracy": 0.16583333333333333, "hallucinationRate": 0.9088911088911089}, "gdpval": 501.29, "gdpvalNormalized": 0.0006450000000000103, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": 0.123595505617978, "terminalBench40": null, "scicode": null, "lcr": 0.196666666666667, "ifbench": 0.594557823129252, "hle": 0.108433734939759, "gpqa": 0.668686868686869, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.665317919075144, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c4169d75-9d24-4794-a9c3-69e1fe364de5", "slug": "gpt-5-5-instant-06-26", "name": "GPT-5.5 Instant (June 2026)", "shortName": "GPT-5.5 Instant (June 2026)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-25", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "gpt-5-5-instant-06-26", "name": "GPT-5.5 Instant (June 2026)"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 26.8042923401368, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 26.00084880175881, "strategyAndOps": 30.667248672972594, "legal": 30.479870196018748, "engineering": 25.45326798522763, "economics": 31.343987546339214}, "omniscience": 3.7, "omniscienceBreakdown": {"accuracy": 0.44416666666666665, "hallucinationRate": 0.7325337331334333}, "gdpPdfAllPass": 0.202, "gdpval": 661.83, "gdpvalNormalized": 0.08091500000000001, "itBenchSre": null, "tau2": null, "tauBanking": 0.117525773195876, "terminalbenchHard": null, "terminalBench21": 0.348314606741573, "terminalBench40": 0.126262626262626, "scicode": 0.525462962962963, "lcr": 0.7, "ifbench": null, "hle": 0.199258572752549, "gpqa": 0.823232323232323, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.36436554387118747, "price1mInputTokens": 5, "price1mOutputTokens": 30, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 11.25, "price1mBlended7To2To1": 4.35, "price1mBlended0To1To1": 17.5, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 5.247524752475248, "intelligenceIndexTimePerTask": 35.14119819320257, "intelligenceIndexCost": {"total": 1184.3361300335328, "input": 866.4088800335328, "nonCacheInput": 109.28457, "cacheRead": 258.6267805518297, "cacheWrite": 498.4975294817031, "output": 317.92725, "reasoning": 80.12367, "answer": 237.80358}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.6914853678439488, "input": 0.5402707715752649, "nonCacheInput": 0.07715252050752461, "cacheRead": 0.16050451883738082, "cacheWrite": 0.3026137322303595, "output": 0.15121459626868378, "reasoning": 0.03624949248225594, "answer": 0.1149651037864279}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.16657027541909386}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.007350633517896044}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.04813005313748918}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.37979287017167185}, {"slug": "scicode", "weightedCostPerTask": 0.0025474895833333335}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0023911499073215937}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.05426168000000001}, {"slug": "critpt", "weightedCostPerTask": 0.005949092857142857}, {"slug": "omniscience", "weightedCostPerTask": 0.00046504824999999995}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.024027075000000005}]}, "canonicalIntelligenceIndexTokenCount": {"input": 638809981, "output": 10597575, "answer": 7926786, "reasoning": 2670789}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 1208.3164160751978, "answer": 3832.170126214263, "output": 5040.486542289461}, "briefcaseBreakdown": {"overall": {"elo": 1081.76, "lower95ci": 1073.16, "upper95ci": 1091.29}, "rubricPassRate": 0.2696969696969697, "analyticalQuality": {"elo": 1049, "lower95ci": 1031.48, "upper95ci": 1067.15}, "presentation": {"elo": 1192.64, "lower95ci": 1176.14, "upper95ci": 1211.07}}, "briefcaseTotalCost": 101.05263375425028, "timescaleData": {"medianOutputSpeed": 144.336859142526, "medianTimeToFirstChunk": 0.983725568999944}, "outputSpeedVariance": {"p05": 92.4707629731026, "q25": 115.994910817412, "median": 144.336859142526, "q75": 160.455854427305, "p95": 185.630212383228}, "timeToFirstChunkVariance": {"p05": 0.843036583400033, "q25": 0.937224187249996, "median": 0.983725568999944, "q75": 1.23430999050001, "p95": 3.81633330334988}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 142.366045774864, "medianTimeToFirstChunk": 1.01192071949998, "medianTimeToFirstAnswerToken": 15.060214251251058, "medianEndToEndResponseTime": 18.57228763418883}, "long": {"medianOutputSpeed": 144.336859142526, "medianTimeToFirstChunk": 0.983725568999944, "medianTimeToFirstAnswerToken": 14.840200012753025, "medianEndToEndResponseTime": 18.304318623691294}, "hundredK": {"medianOutputSpeed": 174.776354474378, "medianTimeToFirstChunk": 2.62608969, "medianTimeToFirstAnswerToken": 14.069285229893229, "medianEndToEndResponseTime": 16.930084114866535}, "mediumParallel": {"medianOutputSpeed": 117.827260107025, "medianTimeToFirstChunk": 0.934795645000009, "medianTimeToFirstAnswerToken": 17.908796382888315, "medianEndToEndResponseTime": 22.152296567360395}}, "endToEndResponseTime": {"input": 0.983725568999944, "reasoning": 13.856474443753081, "answer": 3.4641186109382702, "total": 18.304318623691294}, "timeToFirstAnswerToken": {"input": 0.983725568999944, "reasoning": 13.856474443753081, "total": 14.840200012753025}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c43aa1f9-31bd-4a99-be70-84c5e6bd2e75", "slug": "qwen-chat-14b", "name": "Qwen Chat 14B", "shortName": "Qwen Chat 14B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-09-25", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen-chat-14b", "name": "Qwen Chat 14B"}, "deprecated": true, "deprecatedTo": "qwen3-14b-instruct", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 14, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 8192, "licenseName": "Tongyi Qianwen LICENSE AGREEMENT", "licenseUrl": "https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen-14B-Chat", "microevalsEnabled": false, "intelligenceIndex": 5.03498213171439, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c4c3b42f-e0f0-48ca-b6f9-b296e7697806", "slug": "llama-3-3-nemotron-super-49b", "name": "Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)", "shortName": "Llama 3.3 Nemotron Super 49B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-18", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-3-3-nemotron-super-49b", "name": "Llama 3.3 Nemotron Super 49B v1"}, "deprecated": true, "deprecatedTo": "llama-nemotron-super-49b-v1-5", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 49, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "NVIDIA Open Model License Agreement", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1", "microevalsEnabled": false, "intelligenceIndex": 7.27513732255953, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -50.3, "omniscienceBreakdown": {"accuracy": 0.13466666666666666, "hallucinationRate": 0.7369029275808937}, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.12, "ifbench": 0.394557823129252, "hle": 0.0381, "gpqa": 0.517171717171717, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.28042328042328, "aime25": 0.0766666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 52.77777777777778, "modelAvailability": 4, "transparencyMethodology": 4, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c6a47d8a-7517-46e2-8383-329fe7241725", "slug": "gemini-2-0-pro-experimental-02-05", "name": "Gemini 2.0 Pro Experimental (Feb '25)", "shortName": "Gemini 2.0 Pro Experimental", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-05", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-2-0-pro-experimental-02-05", "name": "Gemini 2.0 Pro Experimental (Feb '25)"}, "deprecated": true, "deprecatedTo": "gemini-2-5-pro-03-25", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.7462081604643, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0619, "gpqa": 0.622222222222222, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.347089947089947, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c72cb85a-18a4-4235-b455-77dff2f16c50", "slug": "grok-4-20", "name": "Grok 4.20 0309 v2 (Reasoning)", "shortName": "Grok 4.20 0309 v2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-07", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "grok-4-20", "name": "Grok 4.20 0309 v2"}, "deprecated": true, "deprecatedTo": "grok-4-3", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 25.6550155187053, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 14.8333333333333, "omniscienceBreakdown": {"accuracy": 0.2748333333333333, "hallucinationRate": 0.17444265686049185}, "gdpval": null, "itBenchSre": null, "tau2": 0.929824561403509, "tauBanking": null, "terminalbenchHard": 0.378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.69, "ifbench": 0.812244897959184, "hle": 0.345227062094532, "gpqa": 0.911111111111111, "critpt": 0.0657142857142857, "apexAgents": null, "mmmuPro": 0.745664739884393, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 2.5, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.84, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5625, "price1mBlended7To2To1": 0.64, "price1mBlended0To1To1": 1.875, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.2623762376237624, "timescaleData": {"medianOutputSpeed": 113.476976135112, "medianTimeToFirstChunk": 20.3011707265}, "outputSpeedVariance": {"p05": 60.8949762467678, "q25": 92.2366704348019, "median": 113.476976135112, "q75": 137.22348875856, "p95": 171.390910404208}, "timeToFirstChunkVariance": {"p05": 9.21128034450001, "q25": 13.59145759075, "median": 20.3011707265, "q75": 36.2885697437499, "p95": 82.2632475377997}, "performanceByPromptType": {"long": {"medianOutputSpeed": 113.476976135112, "medianTimeToFirstChunk": 20.3011707265, "medianTimeToFirstAnswerToken": 20.3011707265, "medianEndToEndResponseTime": 24.70735087889208}}, "endToEndResponseTime": {"input": 20.3011707265, "reasoning": 0, "answer": 4.4061801523920785, "total": 24.70735087889208}, "timeToFirstAnswerToken": {"input": 20.3011707265, "reasoning": 0, "total": 20.3011707265}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 2, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c7327e6e-b27f-4b1b-859d-159a34e0ba1c", "slug": "deepseek-coder-v2-lite", "name": "DeepSeek Coder V2 Lite Instruct", "shortName": "DeepSeek Coder V2 Lite", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-06-17", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-coder-v2-lite", "name": "DeepSeek Coder V2 Lite Instruct"}, "deprecated": true, "deprecatedTo": "deepseek-v2-5-sep-2024", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 16, "inferenceParametersActiveBillions": 2.4, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "DEEPSEEK LICENSE AGREEMENT", "licenseUrl": "https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/LICENSE-MODEL", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", "microevalsEnabled": false, "intelligenceIndex": 5.33591177993782, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0536, "gpqa": 0.319191919191919, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.157671957671958, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c7667559-d9b6-43f1-8cd8-8bdbc78d190b", "slug": "gemini-2-5-flash-preview-09-2025-reasoning", "name": "Gemini 2.5 Flash Preview (Sep '25) (Reasoning)", "shortName": "Gemini 2.5 Flash (Sep)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-25", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-flash-preview-09-2025", "name": "Gemini 2.5 Flash Preview (Sep '25)"}, "deprecated": true, "deprecatedTo": "gemini-3-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 15.4671894654212, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -36.1, "omniscienceBreakdown": {"accuracy": 0.2833333333333333, "hallucinationRate": 0.8990697674418605}, "gdpval": null, "itBenchSre": null, "tau2": 0.456140350877193, "tauBanking": null, "terminalbenchHard": 0.166666666666667, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.71, "ifbench": 0.52312925170068, "hle": 0.138090824837813, "gpqa": 0.792929292929293, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.73121387283237, "livecodebench": 0.713227513227513, "aime25": 0.783333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c76e0ae8-0fd2-45c0-a39d-d398fce9b128", "slug": "falcon-h1r-7b", "name": "Falcon-H1R-7B", "shortName": "Falcon-H1R-7B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-04", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "falcon-h1r-7b", "name": "Falcon-H1R-7B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Falcon Mamba 7B TII License Version 1.0", "licenseUrl": "https://falconllm.tii.ae/falcon-terms-and-conditions.html", "modelWeightsSourceUrl": "https://huggingface.co/tiiuae/Falcon-H1R-7B", "microevalsEnabled": false, "intelligenceIndex": 7.82776928077145, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -61.3, "omniscienceBreakdown": {"accuracy": 0.1455, "hallucinationRate": 0.88765359859567}, "gdpval": null, "itBenchSre": null, "tau2": 0.277777777777778, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.11, "ifbench": 0.54421768707483, "hle": 0.10982391102873, "gpqa": 0.660606060606061, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.723809523809524, "aime25": 0.8, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 4, "transparencyMethodology": 3, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d676bc61-3394-4046-ac6a-85eea9aedaba", "slug": "tii-uae", "name": "TII UAE", "logo": "/img/logos/tii_small.svg", "color": "#6502FF", "country": "ae", "url": "https://falconllm.tii.ae/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c77cfe51-f4a0-4692-9dee-5061ef667f23", "slug": "gpt-5-5-low", "name": "GPT-5.5 (low)", "shortName": "GPT-5.5 (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-23", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gpt-5-5", "name": "GPT-5.5"}, "deprecated": true, "deprecatedTo": "gpt-5-6-sol-low", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 922000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 30.709518471208, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 15.1, "omniscienceBreakdown": {"accuracy": 0.5485, "hallucinationRate": 0.8803986710963455}, "mlcrOverall": 0.111111111111111, "gdpval": 1112.71, "gdpvalNormalized": 0.30635500000000004, "itBenchSre": null, "tau2": 0.839181286549708, "tauBanking": 0.249484536082474, "terminalbenchHard": 0.522727272727273, "terminalBench21": 0.655430711610487, "terminalBench40": null, "scicode": null, "lcr": 0.81, "ifbench": 0.643537414965986, "hle": 0.326691380908248, "gpqa": 0.91010101010101, "critpt": 0.08, "apexAgents": null, "mmmuPro": 0.790173410404624, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 5, "price1mOutputTokens": 30, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 3.83, "price1mBlended0To3To1": 11.25, "price1mBlended7To2To1": 4.35, "price1mBlended0To1To1": 17.5, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 5.247524752475248, "timescaleData": {"medianOutputSpeed": 98.5989634744458, "medianTimeToFirstChunk": 1.7250934125}, "outputSpeedVariance": {"p05": 56.0169952508517, "q25": 63.9614969956888, "median": 98.5989634744458, "q75": 103.120406805224, "p95": 119.47060508797}, "timeToFirstChunkVariance": {"p05": 1.36392612294997, "q25": 1.51377116125004, "median": 1.7250934125, "q75": 2.08942211650006, "p95": 5.20495654434998}, "performanceByPromptType": {"long": {"medianOutputSpeed": 98.5989634744458, "medianTimeToFirstChunk": 1.7250934125, "medianTimeToFirstAnswerToken": 1.7250934125, "medianEndToEndResponseTime": 6.796140636334017}}, "endToEndResponseTime": {"input": 1.7250934125, "reasoning": 0, "answer": 5.071047223834017, "total": 6.796140636334017}, "timeToFirstAnswerToken": {"input": 1.7250934125, "reasoning": 0, "total": 1.7250934125}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c8158c23-6fff-4c31-911d-954c32d80c28", "slug": "step-3-5-flash-0202", "name": "Step 3.5 Flash", "shortName": "Step 3.5 Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "step-3-5-flash-0202", "name": "Step 3.5 Flash"}, "deprecated": true, "deprecatedTo": "step-3-5-flash", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 196, "inferenceParametersActiveBillions": 11, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/stepfun-ai/Step-3.5-Flash", "microevalsEnabled": false, "intelligenceIndex": 16.6169431254306, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -41.8166666666667, "omniscienceBreakdown": {"accuracy": 0.23616666666666666, "hallucinationRate": 0.8566441195723326}, "gdpval": null, "itBenchSre": null, "tau2": 0.944444444444444, "tauBanking": null, "terminalbenchHard": 0.272727272727273, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.5, "ifbench": 0.645578231292517, "hle": 0.211306765523633, "gpqa": 0.831313131313131, "critpt": 0.0246938775510204, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15000000000000002, "price1mBlended7To2To1": 0.12000000000000002, "price1mBlended0To1To1": 0.2, "price1mBlended100To1To1": 0.10196078431372549, "price1mBlended0To100To1": 0.10198019801980199, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 122.094002899082, "medianTimeToFirstChunk": 3.38069470999994}, "outputSpeedVariance": {"p05": 86.5102858342741, "q25": 107.757390679247, "median": 122.094002899082, "q75": 162.013676313303, "p95": 181.625785508993}, "timeToFirstChunkVariance": {"p05": 3.00960075739995, "q25": 3.297509867, "median": 3.38069470999994, "q75": 3.4681455875, "p95": 3.7011141748}, "performanceByPromptType": {"long": {"medianOutputSpeed": 122.094002899082, "medianTimeToFirstChunk": 3.38069470999994, "medianTimeToFirstAnswerToken": 19.76151565542442, "medianEndToEndResponseTime": 23.856720891780544}}, "endToEndResponseTime": {"input": 3.38069470999994, "reasoning": 16.38082094542448, "answer": 4.09520523635612, "total": 23.856720891780544}, "timeToFirstAnswerToken": {"input": 3.38069470999994, "reasoning": 16.38082094542448, "total": 19.76151565542442}, "performanceDataSource": {"type": "firstParty", "providerName": "StepFun"}, "hostModelCount": 2, "creator": {"id": "ce2e2e8b-7a22-4020-98ec-8ef71000dd42", "slug": "stepfun", "name": "StepFun", "logo": "/img/logos/stepfun_small.svg", "color": "#017AFF", "country": "cn", "url": "https://www.stepfun.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c8673741-5e1a-46a1-9e4f-710a5c920982", "slug": "glm-4-7-flash-non-reasoning", "name": "GLM-4.7-Flash (Non-reasoning)", "shortName": "GLM-4.7-Flash (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-01-19", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "glm-4-7-flash", "name": "GLM-4.7-Flash"}, "deprecated": true, "deprecatedTo": "glm-5-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 31.2, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 200000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-4.7-Flash", "microevalsEnabled": false, "intelligenceIndex": 10.555698892906, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -68.9333333333333, "omniscienceBreakdown": {"accuracy": 0.1305, "hallucinationRate": 0.942879049262028}, "gdpval": null, "itBenchSre": null, "tau2": 0.91812865497076, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.203333333333333, "ifbench": 0.462585034013605, "hle": 0.0495829471733086, "gpqa": 0.451515151515151, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.07, "price1mOutputTokens": 0.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15250000000000002, "price1mBlended7To2To1": 0.10300000000000002, "price1mBlended0To1To1": 0.23500000000000001, "price1mBlended100To1To1": 0.07323529411764708, "price1mBlended0To100To1": 0.07326732673267328, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 105.892125511233, "medianTimeToFirstChunk": 1.65102251849996}, "outputSpeedVariance": {"p05": 45.2912082193372, "q25": 72.2599892453869, "median": 105.892125511233, "q75": 203.766582613733, "p95": 231.127816831456}, "timeToFirstChunkVariance": {"p05": 0.890633863500028, "q25": 0.984885461750011, "median": 1.65102251849996, "q75": 3.86480909024998, "p95": 73.3947839967499}, "performanceByPromptType": {"long": {"medianOutputSpeed": 105.892125511233, "medianTimeToFirstChunk": 1.65102251849996, "medianTimeToFirstAnswerToken": 1.65102251849996, "medianEndToEndResponseTime": 6.372808936385775}}, "endToEndResponseTime": {"input": 1.65102251849996, "reasoning": 0, "answer": 4.721786417885815, "total": 6.372808936385775}, "timeToFirstAnswerToken": {"input": 1.65102251849996, "reasoning": 0, "total": 1.65102251849996}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c8a3fa87-735e-49a9-afb1-270c5e9f53f7", "slug": "olmo-3-32b-think", "name": "Olmo 3 32B Think", "shortName": "Olmo 3 32B Think", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-20", "knowledgeCutoffDate": "2024-12-01", "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "olmo-3-32b-think", "name": "Olmo 3 32B Think"}, "deprecated": true, "deprecatedTo": "olmo-3-1-32b-think", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32.2, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 65536, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/allenai/Olmo-3-1125-32B", "microevalsEnabled": false, "intelligenceIndex": 6.47275394213019, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -58.0666666666667, "omniscienceBreakdown": {"accuracy": 0.14866666666666667, "hallucinationRate": 0.8566953797963978}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.491156462585034, "hle": 0.0644114921223355, "gpqa": 0.61010101010101, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.671957671957672, "aime25": 0.736666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "ab6c5270-d7b9-4c09-92fe-62662618c631", "slug": "ai2", "name": "Allen Institute for AI", "logo": "/img/logos/ai2_small.svg", "color": "#F0529C", "country": "us", "url": "https://allenai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c8a79180-7d16-4474-8701-9a77c0baa56a", "slug": "qwen3-next-80b-a3b-reasoning", "name": "Qwen3 Next 80B A3B (Reasoning)", "shortName": "Qwen3 Next 80B A3B (Reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-next-80b-a3b", "name": "Qwen3 Next 80B A3B (Reasoning)"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 80, "inferenceParametersActiveBillions": 3, "sizeClass": "medium", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Thinking", "microevalsEnabled": true, "intelligenceIndex": 11.1973684395653, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -51.4166666666667, "omniscienceBreakdown": {"accuracy": 0.19033333333333333, "hallucinationRate": 0.8701111568546727}, "gdpval": 324.88, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.415204678362573, "tauBanking": 0.0618556701030928, "terminalbenchHard": 0.0984848484848485, "terminalBench21": 0.0674157303370786, "terminalBench40": null, "scicode": null, "lcr": 0.636666666666667, "ifbench": 0.606802721088435, "hle": 0.125579240037071, "gpqa": 0.758585858585858, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.784126984126984, "aime25": 0.843333333333333, "analystAgent": null, "price1mInputTokens": 0.15, "price1mOutputTokens": 1.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.4125, "price1mBlended7To2To1": 0.255, "price1mBlended0To1To1": 0.6749999999999999, "price1mBlended100To1To1": 0.16029411764705884, "price1mBlended0To100To1": 0.1603960396039604, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 201.896059187458, "medianTimeToFirstChunk": 2.402351436}, "outputSpeedVariance": {"p05": 179.453999120768, "q25": 187.906302158967, "median": 201.896059187458, "q75": 211.267855582598, "p95": 224.678445037599}, "timeToFirstChunkVariance": {"p05": 2.17907757224999, "q25": 2.2149885042499, "median": 2.402351436, "q75": 2.64677057875011, "p95": 3.52908780119998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 206.578194023776, "medianTimeToFirstChunk": 1.163190278, "medianTimeToFirstAnswerToken": 10.844754246798232, "medianEndToEndResponseTime": 13.265145238997789}, "long": {"medianOutputSpeed": 201.896059187458, "medianTimeToFirstChunk": 2.402351436, "medianTimeToFirstAnswerToken": 12.308438796244236, "medianEndToEndResponseTime": 14.784960636305296}, "hundredK": {"medianOutputSpeed": 162.794044253873, "medianTimeToFirstChunk": 21.5671728825, "medianTimeToFirstAnswerToken": 33.85263460910379, "medianEndToEndResponseTime": 36.924000040754734}, "mediumParallel": {"medianOutputSpeed": 194.282097922116, "medianTimeToFirstChunk": 1.23715131950008, "medianTimeToFirstAnswerToken": 11.531460581086096, "medianEndToEndResponseTime": 14.1050378964826}}, "endToEndResponseTime": {"input": 2.402351436, "reasoning": 9.906087360244236, "answer": 2.476521840061059, "total": 14.784960636305296}, "timeToFirstAnswerToken": {"input": 2.402351436, "reasoning": 9.906087360244236, "total": 12.308438796244236}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 4, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c8adc5cf-fd5a-407b-af51-dc3bede3e49c", "slug": "grok-4-6", "name": "Grok 4.6 (high)", "shortName": "Grok 4.6 (high)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-08-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "grok-4-6", "name": "Grok 4.6"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 500000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 44.4050073012592, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 49.468290142773675, "strategyAndOps": 52.71318144504561, "legal": 52.083156975280694, "healthcareAndMedical": 45.38923116306219, "engineering": 45.09021204518372, "economics": 54.04451484785294}, "omniscience": 30.4833333333333, "omniscienceBreakdown": {"accuracy": 0.48233333333333334, "hallucinationRate": 0.3428847392144237}, "mlcrOverall": 0.122222222222222, "gdpPdfAllPass": 0.17, "gdpval": 1642.96, "gdpvalNormalized": 0.57148, "itBenchSre": null, "tau2": null, "tauBanking": 0.507216494845361, "terminalbenchHard": null, "terminalBench21": 0.883895131086142, "terminalBench40": 0.212121212121212, "scicode": 0.564814814814815, "lcr": 0.803333333333333, "ifbench": null, "hle": 0.429101019462465, "gpqa": 0.94949494949495, "critpt": 0.171428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.4125, "automationBenchPartialScore": 0.6667849638121398, "enterpriseOpsGym": 0.4834377797672337, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.35, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 0.5686274509803921, "price1mBlended0To100To1": 2.0396039603960396, "intelligenceIndexTimePerTask": 548.2774338272527, "intelligenceIndexCost": {"total": 2351.8314013235918, "input": 1786.7117293235917, "nonCacheInput": 46.041936, "cacheRead": 803.5460035588027, "cacheWrite": 937.1237897647891, "output": 565.119672, "reasoning": 435.636876, "answer": 129.482796}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.8589423352127492, "input": 1.643935276118273, "nonCacheInput": 0.032751100914639515, "cacheRead": 0.7729047787054619, "cacheWrite": 0.8382793964981715, "output": 0.21500705909447615, "reasoning": 0.11268937380954741, "answer": 0.10231768528492875}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.7514204227735786}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.23552031288742276}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.037613054150823624}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.7509448610305077}, {"slug": "scicode", "weightedCostPerTask": 0.002717834027777778}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.012054022335495828}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.025640956000000003}, {"slug": "critpt", "weightedCostPerTask": 0.03160332285714286}, {"slug": "omniscience", "weightedCostPerTask": 0.0012998501499999998}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.010127699}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2098674870, "output": 94186612, "answer": 21580466, "reasoning": 72606146}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 18781.562301591235, "answer": 17052.94754748812, "output": 35834.50984907935}, "briefcaseBreakdown": {"overall": {"elo": 1534.13, "lower95ci": 1527.89, "upper95ci": 1540.96}, "rubricPassRate": 0.5282828282828282, "analyticalQuality": {"elo": 1668.79, "lower95ci": 1656.92, "upper95ci": 1681.28}, "presentation": {"elo": 1501.89, "lower95ci": 1490.25, "upper95ci": 1514.15}}, "briefcaseTotalCost": 455.86172314930434, "timescaleData": {"medianOutputSpeed": 64.4561261702102, "medianTimeToFirstChunk": 40.558767104}, "outputSpeedVariance": {"p05": 41.2558721254051, "q25": 50.8878061309025, "median": 64.4561261702102, "q75": 76.6842461613775, "p95": 83.4616353609667}, "timeToFirstChunkVariance": {"p05": 10.1066142697, "q25": 17.44758498225, "median": 40.558767104, "q75": 55.83894221125, "p95": 65.6955357674499}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 59.4875341151687, "medianTimeToFirstChunk": 35.282276372, "medianTimeToFirstAnswerToken": 35.282276372, "medianEndToEndResponseTime": 43.6873986793391}, "long": {"medianOutputSpeed": 64.4561261702102, "medianTimeToFirstChunk": 40.558767104, "medianTimeToFirstAnswerToken": 40.558767104, "medianEndToEndResponseTime": 48.31598165765845}, "hundredK": {"medianOutputSpeed": 66.6404901646692, "medianTimeToFirstChunk": 39.6582756735, "medianTimeToFirstAnswerToken": 39.6582756735, "medianEndToEndResponseTime": 47.16122168671953}, "mediumParallel": {"medianOutputSpeed": 64.1891943605939, "medianTimeToFirstChunk": 41.1705452809999, "medianTimeToFirstAnswerToken": 41.1705452809999, "medianEndToEndResponseTime": 48.960018337651206}}, "endToEndResponseTime": {"input": 40.558767104, "reasoning": 0, "answer": 7.757214553658453, "total": 48.31598165765845}, "timeToFirstAnswerToken": {"input": 40.558767104, "reasoning": 0, "total": 40.558767104}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 4, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "c99f3bde-7c08-4de8-bd5c-8ee9123ebffa", "slug": "gpt-oss-120b-low", "name": "gpt-oss-120b (low)", "shortName": "gpt-oss-120b (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-05", "knowledgeCutoffDate": "2025-05-31", "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gpt-oss-120b", "name": "gpt-oss-120b"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 117, "inferenceParametersActiveBillions": 5.1, "sizeClass": "medium", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/openai/gpt-oss-120b", "microevalsEnabled": false, "intelligenceIndex": 10.2105650347196, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -53.5, "omniscienceBreakdown": {"accuracy": 0.198, "hallucinationRate": 0.9139650872817955}, "gdpval": 364.46, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.450292397660819, "tauBanking": 0.0288659793814433, "terminalbenchHard": 0.053030303030303, "terminalBench21": 0.138576779026217, "terminalBench40": null, "scicode": null, "lcr": 0.46, "ifbench": 0.582993197278912, "hle": 0.0588507877664504, "gpqa": 0.671717171717172, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.706878306878307, "aime25": 0.666666666666667, "analystAgent": null, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.5449999999999999, "cacheHitPrice": 0.15, "cacheHitDiscountPercent": 0.45000000000000007, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.24874999999999997, "price1mBlended7To2To1": 0.1895, "price1mBlended0To1To1": 0.3475, "price1mBlended100To1To1": 0.15387254901960784, "price1mBlended0To100To1": 0.1539108910891089, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 173.370718648091, "medianTimeToFirstChunk": 0.870137830999994}, "outputSpeedVariance": {"p05": 35.0903350909178, "q25": 78.0538871032537, "median": 173.370718648091, "q75": 344.627127527874, "p95": 1378.56265206158}, "timeToFirstChunkVariance": {"p05": 0.257485318899978, "q25": 0.558594679000066, "median": 0.870137830999994, "q75": 1.23391071499998, "p95": 7.4493832192}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 170.431145786548, "medianTimeToFirstChunk": 0.566875815499998, "medianTimeToFirstAnswerToken": 12.30182009912787, "medianEndToEndResponseTime": 15.235556170034839}, "long": {"medianOutputSpeed": 173.370718648091, "medianTimeToFirstChunk": 0.870137830999994, "medianTimeToFirstAnswerToken": 12.406111238710281, "medianEndToEndResponseTime": 15.290104590637853}, "hundredK": {"medianOutputSpeed": 198.923865054508, "medianTimeToFirstChunk": 3.93902309500004, "medianTimeToFirstAnswerToken": 13.993120925101879, "medianEndToEndResponseTime": 16.506645382627337}, "mediumParallel": {"medianOutputSpeed": 197.744775396834, "medianTimeToFirstChunk": 0.514670719999913, "medianTimeToFirstAnswerToken": 10.628717960875948, "medianEndToEndResponseTime": 13.157229771094956}}, "endToEndResponseTime": {"input": 0.870137830999994, "reasoning": 11.535973407710287, "answer": 2.883993351927572, "total": 15.290104590637853}, "timeToFirstAnswerToken": {"input": 0.870137830999994, "reasoning": 11.535973407710287, "total": 12.406111238710281}, "performanceDataSource": {"type": "median"}, "hostModelCount": 18, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ca04852c-eaae-4881-a208-f9b2ca3b7cd6", "slug": "o3-pro", "name": "o3-pro", "shortName": "o3-pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-10", "knowledgeCutoffDate": "2024-06-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "o3-pro", "name": "o3-pro"}, "deprecated": true, "deprecatedTo": "gpt-5", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 21.869975912052, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": 0.845454545454545, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 20, "price1mOutputTokens": 80, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 35, "price1mBlended7To2To1": 26, "price1mBlended0To1To1": 50, "price1mBlended100To1To1": 20.58823529411765, "price1mBlended0To100To1": 20.594059405940595, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ca6c1412-f3c1-4391-9231-f83a702aa7af", "slug": "mistral-8x22b-instruct", "name": "Mixtral 8x22B Instruct", "shortName": "Mixtral 8x22B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-04-17", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-8x22b-instruct", "name": "Mixtral 8x22B Instruct"}, "deprecated": true, "deprecatedTo": "mistral-small-3-2", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 141, "inferenceParametersActiveBillions": 39, "sizeClass": "medium", "contextWindowTokens": 65384, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1", "microevalsEnabled": false, "intelligenceIndex": 5.74434049511794, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0401, "gpqa": 0.332323232323232, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.148148148148148, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "cbac8c35-e069-4c73-823e-0953e6ed0e85", "slug": "qwen3-max-thinking-preview", "name": "Qwen3 Max Thinking (Preview)", "shortName": "Qwen3 Max Thinking (Preview)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-03", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-max-thinking-preview", "name": "Qwen3 Max Thinking (Preview)"}, "deprecated": true, "deprecatedTo": "qwen3-max-thinking", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 16.290984641221, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -39.1166666666667, "omniscienceBreakdown": {"accuracy": 0.2735, "hallucinationRate": 0.9148887359486121}, "gdpval": null, "itBenchSre": null, "tau2": 0.83625730994152, "tauBanking": null, "terminalbenchHard": 0.174242424242424, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.62, "ifbench": 0.538095238095238, "hle": 0.126506024096386, "gpqa": 0.775757575757576, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.535449735449735, "aime25": 0.823333333333333, "analystAgent": null, "price1mInputTokens": 1.2, "price1mOutputTokens": 6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 1.231, "price1mBlended0To3To1": 2.4, "price1mBlended7To2To1": 1.6800000000000002, "price1mBlended0To1To1": 3.6, "price1mBlended100To1To1": 1.2470588235294118, "price1mBlended0To100To1": 1.2475247524752475, "openness": {"opennessIndex": 16.666666666666668, "modelAvailability": 2, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 58.3666038406177, "medianTimeToFirstChunk": 4.07561777250001}, "outputSpeedVariance": {"p05": 43.8520594102977, "q25": 53.3375808294955, "median": 58.3666038406177, "q75": 64.4458960192655, "p95": 70.6207799151901}, "timeToFirstChunkVariance": {"p05": 3.92097262765004, "q25": 3.9589108, "median": 4.07561777250001, "q75": 4.53187035475, "p95": 6.02549235604998}, "performanceByPromptType": {"long": {"medianOutputSpeed": 58.3666038406177, "medianTimeToFirstChunk": 4.07561777250001, "medianTimeToFirstAnswerToken": 38.34178829462635, "medianEndToEndResponseTime": 46.90833092515793}}, "endToEndResponseTime": {"input": 4.07561777250001, "reasoning": 34.26617052212634, "answer": 8.566542630531584, "total": 46.90833092515793}, "timeToFirstAnswerToken": {"input": 4.07561777250001, "reasoning": 34.26617052212634, "total": 38.34178829462635}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "cc1fa238-1a76-486d-a997-22309275eadd", "slug": "devstral-small-2505", "name": "Devstral Small (May '25)", "shortName": "Devstral Small (May)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-21", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "devstral-small-2505", "name": "Devstral Small (May '25)"}, "deprecated": true, "deprecatedTo": "devstral-small", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 23.6, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Devstral-Small-2505", "microevalsEnabled": false, "intelligenceIndex": 8.73503199772396, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -56.7833333333333, "omniscienceBreakdown": {"accuracy": 0.15866666666666668, "hallucinationRate": 0.8635103011093502}, "gdpval": null, "itBenchSre": null, "tau2": 0.380116959064327, "tauBanking": null, "terminalbenchHard": 0.0606060606060606, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.32, "ifbench": 0.316326530612245, "hle": 0.0403151065801668, "gpqa": 0.434343434343434, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.258201058201058, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "cc4a20cd-09fe-4962-a430-119c815e85fa", "slug": "gpt-5-6-terra-low", "name": "GPT-5.6 Terra (low)", "shortName": "GPT-5.6 Terra (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gpt-5-6-terra", "name": "GPT-5.6 Terra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 27.916528401716, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 30.16279973310341, "strategyAndOps": 32.04062735173325, "legal": 31.160255520444064, "healthcareAndMedical": 28.00916410442121, "engineering": 27.925513121817946, "economics": 34.93996092060551}, "omniscience": -6.83333333333333, "omniscienceBreakdown": {"accuracy": 0.43733333333333335, "hallucinationRate": 0.898696682464455}, "mlcrOverall": 0.0888888888888889, "gdpPdfAllPass": 0.176, "gdpval": 1177.99, "gdpvalNormalized": 0.338995, "itBenchSre": null, "tau2": 0.605263157894737, "tauBanking": 0.187628865979381, "terminalbenchHard": 0.439393939393939, "terminalBench21": 0.625468164794007, "terminalBench40": 0.0151515151515152, "scicode": 0.498842592592593, "lcr": 0.713333333333333, "ifbench": 0.596598639455782, "hle": 0.291936978683967, "gpqa": 0.843434343434343, "critpt": 0.0942857142857143, "apexAgents": null, "mmmuPro": 0.761271676300578, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.29106376138008166, "price1mInputTokens": 2, "price1mOutputTokens": 12, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4.5, "price1mBlended7To2To1": 1.7399999999999998, "price1mBlended0To1To1": 7, "price1mBlended100To1To1": 0.3333333333333333, "price1mBlended0To100To1": 2.099009900990099, "intelligenceIndexTimePerTask": 43.920619618398774, "intelligenceIndexCost": {"total": 350.36029690867963, "input": 214.79332090867965, "nonCacheInput": 55.91648, "cacheRead": 67.41816774707135, "cacheWrite": 91.45867316160829, "output": 135.566976, "reasoning": 58.738368, "answer": 76.828608}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.1444617614290821, "input": 0.09800621112672665, "nonCacheInput": 0.0430322275727599, "cacheRead": 0.022938415626610687, "cacheWrite": 0.03203556792735608, "output": 0.0464555503023554, "reasoning": 0.012283158092665612, "answer": 0.0341723922096898}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.04497051121380352}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.010206699980324368}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.013452772870137866}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.024329289851485338}, {"slug": "scicode", "weightedCostPerTask": 0.0011905694444444444}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0014177235403151065}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.034589184}, {"slug": "critpt", "weightedCostPerTask": 0.004342631428571429}, {"slug": "omniscience", "weightedCostPerTask": 0.0004268311}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.009535548000000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 401632548, "output": 11297248, "answer": 6402384, "reasoning": 4894864}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 1023.5965077221342, "answer": 2847.6993508074834, "output": 3871.2958585296174}, "briefcaseBreakdown": {"overall": {"elo": 1014.49, "lower95ci": 1005.22, "upper95ci": 1022.5}, "rubricPassRate": 0.23333333333333334, "analyticalQuality": {"elo": 921.48, "lower95ci": 905.02, "upper95ci": 937}, "presentation": {"elo": 1184.91, "lower95ci": 1169.41, "upper95ci": 1199.06}}, "briefcaseTotalCost": 27.282110136374136, "timescaleData": {"medianOutputSpeed": 88.8146745835079, "medianTimeToFirstChunk": 1.77793348999999}, "outputSpeedVariance": {"p05": 60.3109951156576, "q25": 69.3848854272192, "median": 88.8146745835079, "q75": 99.9467660633414, "p95": 119.315104145713}, "timeToFirstChunkVariance": {"p05": 1.23380146395002, "q25": 1.49766441350005, "median": 1.77793348999999, "q75": 2.12094162024994, "p95": 3.94104267545}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 80.9473007717321, "medianTimeToFirstChunk": 1.814760284, "medianTimeToFirstAnswerToken": 1.814760284, "medianEndToEndResponseTime": 7.991618502039641}, "long": {"medianOutputSpeed": 88.8146745835079, "medianTimeToFirstChunk": 1.77793348999999, "medianTimeToFirstAnswerToken": 1.77793348999999, "medianEndToEndResponseTime": 7.407633788342868}, "hundredK": {"medianOutputSpeed": 126.577405252599, "medianTimeToFirstChunk": 1.8285947915, "medianTimeToFirstAnswerToken": 1.8285947915, "medianEndToEndResponseTime": 5.778746866447307}, "mediumParallel": {"medianOutputSpeed": 75.6610072885538, "medianTimeToFirstChunk": 4.48006155599997, "medianTimeToFirstAnswerToken": 4.48006155599997, "medianEndToEndResponseTime": 11.088485338849095}}, "endToEndResponseTime": {"input": 1.77793348999999, "reasoning": 0, "answer": 5.629700298342878, "total": 7.407633788342868}, "timeToFirstAnswerToken": {"input": 1.77793348999999, "reasoning": 0, "total": 1.77793348999999}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ccbfa8c3-a762-480b-aade-34fb9697f98c", "slug": "claude-4-1-opus-thinking", "name": "Claude 4.1 Opus (Reasoning)", "shortName": "Claude 4.1 Opus", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-05", "knowledgeCutoffDate": "2025-03-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "claude-4-1-opus", "name": "Claude 4.1 Opus"}, "deprecated": true, "deprecatedTo": "claude-opus-4-5-thinking", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 22.8471944399332, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.713660933660934, "tauBanking": null, "terminalbenchHard": 0.343352330715909, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.76, "ifbench": 0.554421768707483, "hle": 0.124652455977757, "gpqa": 0.809, "critpt": 0, "apexAgents": null, "mmmuPro": 0.679190751445087, "livecodebench": 0.6535448276, "aime25": 0.803333333333333, "analystAgent": null, "price1mInputTokens": 15, "price1mOutputTokens": 75, "cacheHitPrice": 1.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 18.75, "pricePer1k1mpImages": 20.01, "price1mBlended0To3To1": 30, "price1mBlended7To2To1": 11.55, "price1mBlended0To1To1": 45, "price1mBlended100To1To1": 2.3529411764705883, "price1mBlended0To100To1": 15.594059405940595, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "cd26a386-4873-46ff-b853-d239050025a2", "slug": "gemma-4-31b", "name": "Gemma 4 31B (Reasoning)", "shortName": "Gemma 4 31B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 1736, "release": {"slug": "gemma-4-31b", "name": "Gemma 4 31B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30.7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-4-31B-it", "microevalsEnabled": true, "intelligenceIndex": 15.4156500745828, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 14.688526119716055, "strategyAndOps": 10.630033453175963, "legal": 14.870916327683801, "engineering": 17.496484741162458, "economics": 21.523943562712393}, "omniscience": -47.9333333333333, "omniscienceBreakdown": {"accuracy": 0.20033333333333334, "hallucinationRate": 0.8499374739474781}, "harveyLab": 0.47228253003329, "gdpPdfAllPass": 0.06, "gdpval": 755.45, "gdpvalNormalized": 0.12772500000000003, "itBenchSre": 0.372881355932203, "tau2": 0.599415204678363, "tauBanking": 0.148453608247423, "terminalbenchHard": 0.363636363636364, "terminalBench21": 0.434456928838951, "terminalBench40": 0, "scicode": 0.454861111111111, "lcr": 0.696666666666667, "ifbench": 0.75578231292517, "hle": 0.236329935125116, "gpqa": 0.856565656565657, "critpt": 0.0142857142857143, "apexAgents": null, "mmmuPro": 0.734104046242775, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.049330634486812325, "enterpriseOpsGym": 0.28349746344374815, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "intelligenceIndexTimePerTask": 344.3397954286963, "intelligenceIndexCost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "intelligenceIndexCostPerTask": {"cost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0}, {"slug": "gdpval-aa", "weightedCostPerTask": 0}, {"slug": "automationbench-aa", "weightedCostPerTask": 0}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0}, {"slug": "scicode", "weightedCostPerTask": 0}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0}, {"slug": "gdp-pdf", "weightedCostPerTask": 0}, {"slug": "critpt", "weightedCostPerTask": 0}, {"slug": "omniscience", "weightedCostPerTask": 0}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0}]}, "canonicalIntelligenceIndexTokenCount": {"input": 894212004, "output": 48539135, "answer": 9618907, "reasoning": 38920228}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 7833.237082636707, "answer": 4679.969333946847, "output": 12513.206416583555}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 376.57, "lower95ci": 368.26, "upper95ci": 384.46}, "rubricPassRate": 0.07777777777777778, "analyticalQuality": {"elo": 146.95, "lower95ci": 131.22, "upper95ci": 164.37}, "presentation": {"elo": 342.02, "lower95ci": 325.21, "upper95ci": 357.63}}, "briefcaseTotalCost": 0, "timescaleData": {"medianOutputSpeed": 35.1137800690964, "medianTimeToFirstChunk": 1.00272738400008}, "outputSpeedVariance": {"p05": 32.1368381406587, "q25": 34.2306876427066, "median": 35.1137800690964, "q75": 36.133349397173, "p95": 36.8814489275484}, "timeToFirstChunkVariance": {"p05": 0.919560775600053, "q25": 0.978535482500035, "median": 1.00272738400008, "q75": 1.13427968999994, "p95": 1.3779817864}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 35.1908299120849, "medianTimeToFirstChunk": 0.948349027999967, "medianTimeToFirstAnswerToken": 50.279382264128316, "medianEndToEndResponseTime": 64.48762916393487}, "long": {"medianOutputSpeed": 35.1137800690964, "medianTimeToFirstChunk": 1.00272738400008, "medianTimeToFirstAnswerToken": 50.44200725030681, "medianEndToEndResponseTime": 64.68143117493432}, "mediumParallel": {"medianOutputSpeed": 34.0897724835863, "medianTimeToFirstChunk": 1.010803041, "medianTimeToFirstAnswerToken": 51.935167550497894, "medianEndToEndResponseTime": 66.60232322719659}}, "endToEndResponseTime": {"input": 1.00272738400008, "reasoning": 49.43927986630673, "answer": 14.239423924627513, "total": 64.68143117493432}, "timeToFirstAnswerToken": {"input": 1.00272738400008, "reasoning": 49.43927986630673, "total": 50.44200725030681}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 15, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "cd55210d-358e-4df1-ba9c-9acb5f186cc9", "slug": "claude-fable-5", "name": "Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)", "shortName": "Claude Fable 5 (with fallback)", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-06-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "claude-fable-5", "name": "Claude Fable 5"}, "deprecated": true, "deprecatedTo": "claude-fable-5-1", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 49.6994452733378, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 53.94528081168623, "strategyAndOps": 55.6487900320478, "legal": 58.10012372330013, "healthcareAndMedical": 53.9605447218599, "engineering": 53.15509496289321, "economics": 60.57472574915045}, "omniscience": 43.3, "omniscienceBreakdown": {"accuracy": 0.6535, "hallucinationRate": 0.6363636363636364}, "mlcrOverall": 0.644444444444444, "harveyLab": 0.935591257779708, "gdpPdfAllPass": 0.24, "gdpval": 1631.46, "gdpvalNormalized": 0.5657300000000001, "itBenchSre": null, "tau2": 0.985380116959064, "tauBanking": 0.381443298969072, "terminalbenchHard": 0.628787878787879, "terminalBench21": 0.846441947565543, "terminalBench40": 0.424242424242424, "scicode": 0.609953703703704, "lcr": 0.823333333333333, "ifbench": 0.63469387755102, "hle": 0.554680259499537, "gpqa": 0.926262626262626, "critpt": 0.2857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.4875, "automationBenchPartialScore": 0.5407130114065382, "enterpriseOpsGym": 0.5111906893464637, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 1, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 12.5, "pricePer1k1mpImages": 13.72, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.7, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 1.5686274509803921, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 612.7663655473026, "intelligenceIndexCost": {"total": 11160.864676562578, "input": 5103.334720587579, "nonCacheInput": 343.840672935, "cacheRead": 3126.3542941769497, "cacheWrite": 1633.1397534756295, "output": 6057.529955975, "reasoning": 4610.49913035, "answer": 1447.0308256250003}, "intelligenceIndexCostPerTask": {"cost": {"total": 8.745961651687406, "input": 5.436116413654773, "nonCacheInput": 0.2529111606186462, "cacheRead": 3.8607340421583887, "cacheWrite": 1.322471210877739, "output": 3.3098452380326338, "reasoning": 2.226132425198911, "answer": 1.0837128128337221}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 3.3455005020745747}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.7745990148318164}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.13981003234077705}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 3.490556477700918}, {"slug": "scicode", "weightedCostPerTask": 0.026770639390625003}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.09339926033063022}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.224473679500565}, {"slug": "critpt", "weightedCostPerTask": 0.5620819316}, {"slug": "omniscience", "weightedCostPerTask": 0.010473518917499997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.078296595}]}, "canonicalIntelligenceIndexTokenCount": {"input": 3360275183, "output": 125970391, "answer": 30068173, "reasoning": 95902218}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 45041.401509187875, "answer": 21806.974804706657, "output": 66848.37631389454}, "briefcaseBreakdown": {"overall": {"elo": 1529.62, "lower95ci": 1523.91, "upper95ci": 1535.94}, "rubricPassRate": 0.5595959595959596, "analyticalQuality": {"elo": 1669.7, "lower95ci": 1658.1, "upper95ci": 1682.36}, "presentation": {"elo": 1452.29, "lower95ci": 1441.52, "upper95ci": 1463.2}}, "briefcaseTotalCost": 2029.603637925242, "timescaleData": {"medianOutputSpeed": 68.2334534069976, "medianTimeToFirstChunk": 129.83805002}, "outputSpeedVariance": {"p05": 46.2955780017564, "q25": 55.8235594335803, "median": 68.2334534069976, "q75": 73.2926935313806, "p95": 83.3155976767518}, "timeToFirstChunkVariance": {"p05": 16.0409088942, "q25": 64.4790512545, "median": 129.83805002, "q75": 226.0021056155, "p95": 336.1084058702}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 68.6442184984329, "medianTimeToFirstChunk": 52.666651708, "medianTimeToFirstAnswerToken": 52.666651708, "medianEndToEndResponseTime": 59.95058633406636}, "long": {"medianOutputSpeed": 68.2334534069976, "medianTimeToFirstChunk": 129.83805002, "medianTimeToFirstAnswerToken": 129.83805002, "medianEndToEndResponseTime": 137.16583390069573}, "hundredK": {"medianOutputSpeed": 57.8801038757818, "medianTimeToFirstChunk": 159.1182455545, "medianTimeToFirstAnswerToken": 159.1182455545, "medianEndToEndResponseTime": 167.75679259430947}, "mediumParallel": {"medianOutputSpeed": 64.7273807592238, "medianTimeToFirstChunk": 83.5463864069999, "medianTimeToFirstAnswerToken": 83.5463864069999, "medianEndToEndResponseTime": 91.27109261533428}}, "endToEndResponseTime": {"input": 129.83805002, "reasoning": 0, "answer": 7.327783880695728, "total": 137.16583390069573}, "timeToFirstAnswerToken": {"input": 129.83805002, "reasoning": 0, "total": 129.83805002}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 7, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "cd684ea4-b475-4269-b001-d469d06d8a7a", "slug": "glm-5-3", "name": "GLM-5.3 (max)", "shortName": "GLM-5.3 (max)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-08-18", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "glm-5-3", "name": "GLM-5.3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 753, "inferenceParametersActiveBillions": 40, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "GLM-5.3 License", "licenseUrl": "https://huggingface.co/zai-org/GLM-5.3/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-5.3", "microevalsEnabled": true, "intelligenceIndex": 44.855717385614, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 44.52239652422968, "strategyAndOps": 47.35892773045149, "legal": 41.88204903610222, "healthcareAndMedical": 46.516437561171216, "engineering": 47.02161032501635, "economics": 51.07368191998765}, "omniscience": 14.3, "omniscienceBreakdown": {"accuracy": 0.3385, "hallucinationRate": 0.29554043839758126}, "mlcrOverall": 0.483333333333333, "gdpPdfAllPass": 0.112, "gdpval": 1641.18, "gdpvalNormalized": 0.57059, "itBenchSre": null, "tau2": null, "tauBanking": 0.503092783505155, "terminalbenchHard": null, "terminalBench21": 0.838951310861423, "terminalBench40": 0.419191919191919, "scicode": 0.590277777777778, "lcr": 0.796666666666667, "ifbench": null, "hle": 0.422613531047266, "gpqa": 0.917171717171717, "critpt": 0.191428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.622028649962642, "enterpriseOpsGym": 0.36436884512085943, "price1mInputTokens": 1.4, "price1mOutputTokens": 4.4, "cacheHitPrice": 0.26, "cacheHitDiscountPercent": 0.8142857142857143, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2.15, "price1mBlended7To2To1": 0.9019999999999999, "price1mBlended0To1To1": 2.9000000000000004, "price1mBlended100To1To1": 0.3117647058823529, "price1mBlended0To100To1": 1.4297029702970299, "intelligenceIndexTimePerTask": 823.4913648617828, "intelligenceIndexCost": {"total": 2503.478685148468, "input": 1585.445203948468, "nonCacheInput": 22.7931298, "cacheRead": 1364.5232082257878, "cacheWrite": 198.1288659226801, "output": 918.0334812000001, "reasoning": 789.8118888, "answer": 128.22159240000002}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.0056375150449584, "input": 1.6926760150367, "nonCacheInput": 0.013454088251824734, "cacheRead": 1.5218481062416964, "cacheWrite": 0.1573738205431785, "output": 0.3129615000082585, "reasoning": 0.21440989106607802, "answer": 0.09855160894218057}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.8473184620626165}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.22569955738459915}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.023022340810111726}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.8064202070800424}, {"slug": "scicode", "weightedCostPerTask": 0.008202589583333333}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.023284347052826695}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.017337381000000002}, {"slug": "critpt", "weightedCostPerTask": 0.04521809657142857}, {"slug": "omniscience", "weightedCostPerTask": 0.001705003}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0074295305}]}, "canonicalIntelligenceIndexTokenCount": {"input": 5405967611, "output": 208643973, "answer": 29141271, "reasoning": 179502702}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 48729.52069683591, "answer": 22398.092941404666, "output": 71127.61363824058}, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 5, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1505.44, "lower95ci": 1497.58, "upper95ci": 1513.39}, "rubricPassRate": 0.5134854771784232, "analyticalQuality": {"elo": 1766.32, "lower95ci": 1752.11, "upper95ci": 1781.73}, "presentation": {"elo": 1347.89, "lower95ci": 1334.18, "upper95ci": 1361.56}}, "briefcaseTotalCost": 514.039866984654, "timescaleData": {"medianOutputSpeed": 67.0082715819019, "medianTimeToFirstChunk": 3.10987266900003}, "outputSpeedVariance": {"p05": 38.9151888189929, "q25": 53.5342402895599, "median": 67.0082715819019, "q75": 81.8229558736336, "p95": 100.295301438681}, "timeToFirstChunkVariance": {"p05": 2.469905272, "q25": 2.79550635925, "median": 3.10987266900003, "q75": 4.55183235849994, "p95": 5.79339742895}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 58.5211395076748, "medianTimeToFirstChunk": 2.90550006099997, "medianTimeToFirstAnswerToken": 37.081184554254044, "medianEndToEndResponseTime": 45.62510567756756}, "long": {"medianOutputSpeed": 67.0082715819019, "medianTimeToFirstChunk": 3.10987266900003, "medianTimeToFirstAnswerToken": 32.95693412551692, "medianEndToEndResponseTime": 40.418699489646144}, "hundredK": {"medianOutputSpeed": 78.0279705323514, "medianTimeToFirstChunk": 7.64773363400001, "medianTimeToFirstAnswerToken": 33.279567787251175, "medianEndToEndResponseTime": 39.687526325563965}, "mediumParallel": {"medianOutputSpeed": 49.9420033477106, "medianTimeToFirstChunk": 3.28143275100001, "medianTimeToFirstAnswerToken": 43.32788395311588, "medianEndToEndResponseTime": 53.339496753644845}}, "endToEndResponseTime": {"input": 3.10987266900003, "reasoning": 29.84706145651689, "answer": 7.4617653641292225, "total": 40.418699489646144}, "timeToFirstAnswerToken": {"input": 3.10987266900003, "reasoning": 29.84706145651689, "total": 32.95693412551692}, "performanceDataSource": {"type": "firstParty", "providerName": "Z AI"}, "hostModelCount": 22, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ce3d286e-093d-413d-a81a-0270309f039e", "slug": "qwen3-vl-30b-a3b-reasoning", "name": "Qwen3 VL 30B A3B (Reasoning)", "shortName": "Qwen3 VL 30B A3B (Reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-03", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-vl-30b-a3b", "name": "Qwen3 VL 30B A3B (Reasoning)"}, "deprecated": true, "deprecatedTo": "qwen3-5-35b-a3b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Thinking", "microevalsEnabled": false, "intelligenceIndex": 9.45305611694923, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -57.6333333333333, "omniscienceBreakdown": {"accuracy": 0.16933333333333334, "hallucinationRate": 0.8976725521669342}, "gdpval": null, "itBenchSre": null, "tau2": 0.198830409356725, "tauBanking": null, "terminalbenchHard": 0.053030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.451020408163265, "hle": 0.0894346617238184, "gpqa": 0.72020202020202, "critpt": 0, "apexAgents": null, "mmmuPro": 0.61849710982659, "livecodebench": 0.697354497354497, "aime25": 0.823333333333333, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 2.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.204, "price1mBlended0To3To1": 0.75, "price1mBlended7To2To1": 0.42000000000000004, "price1mBlended0To1To1": 1.3, "price1mBlended100To1To1": 0.22156862745098038, "price1mBlended0To100To1": 0.22178217821782176, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 110.44879004194, "medianTimeToFirstChunk": 2.1814968555}, "outputSpeedVariance": {"p05": 96.7983929514126, "q25": 108.598779690753, "median": 110.44879004194, "q75": 112.924838005777, "p95": 116.228194692855}, "timeToFirstChunkVariance": {"p05": 2.06468827130001, "q25": 2.12688627549999, "median": 2.1814968555, "q75": 2.37188392325001, "p95": 2.58563301540001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 110.44879004194, "medianTimeToFirstChunk": 2.1814968555, "medianTimeToFirstAnswerToken": 20.28943628372328, "medianEndToEndResponseTime": 24.8164211407791}}, "endToEndResponseTime": {"input": 2.1814968555, "reasoning": 18.10793942822328, "answer": 4.52698485705582, "total": 24.8164211407791}, "timeToFirstAnswerToken": {"input": 2.1814968555, "reasoning": 18.10793942822328, "total": 20.28943628372328}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ce819310-af7c-49d3-9a02-6845111e1788", "slug": "devstral-small-2", "name": "Devstral Small 2", "shortName": "Devstral Small 2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-09", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "devstral-small-2", "name": "Devstral Small 2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 24, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512", "microevalsEnabled": false, "intelligenceIndex": 8.3575858990318, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 7.282457040373469, "strategyAndOps": 6.772578130205696, "legal": 8.878981262015797, "engineering": 9.995716033364227, "economics": 10.548154077849858}, "omniscience": -57.7, "omniscienceBreakdown": {"accuracy": 0.158, "hallucinationRate": 0.8729216152019003}, "gdpPdfAllPass": 0.01, "gdpval": 679.88, "gdpvalNormalized": 0.08993999999999999, "itBenchSre": null, "tau2": 0.233918128654971, "tauBanking": 0.107216494845361, "terminalbenchHard": 0.166666666666667, "terminalBench21": 0.295880149812734, "terminalBench40": 0, "scicode": 0.324074074074074, "lcr": 0.28, "ifbench": 0.31156462585034, "hle": 0.0347544022242817, "gpqa": 0.532323232323232, "critpt": 0, "apexAgents": null, "mmmuPro": 0.446242774566474, "livecodebench": 0.348148148148148, "aime25": 0.343333333333333, "analystAgent": null, "automationBenchPartialScore": 0.030901842411547694, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "intelligenceIndexTimePerTask": 93.45515174600754, "intelligenceIndexCost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "intelligenceIndexCostPerTask": {"cost": {"total": 0, "input": 0, "nonCacheInput": 0, "cacheRead": 0, "cacheWrite": 0, "output": 0, "reasoning": 0, "answer": 0}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0}, {"slug": "gdpval-aa", "weightedCostPerTask": 0}, {"slug": "automationbench-aa", "weightedCostPerTask": 0}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0}, {"slug": "scicode", "weightedCostPerTask": 0}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0}, {"slug": "gdp-pdf", "weightedCostPerTask": 0}, {"slug": "critpt", "weightedCostPerTask": 0}, {"slug": "omniscience", "weightedCostPerTask": 0}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0}]}, "canonicalIntelligenceIndexTokenCount": {"input": 940300567, "output": 17895639, "answer": 17895639, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 13060.27418852321, "output": 13060.27418852321}, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 5, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 495.98, "lower95ci": 485.58, "upper95ci": 505.35}, "rubricPassRate": 0.10202020202020202, "analyticalQuality": {"elo": 302.93, "lower95ci": 284.51, "upper95ci": 321.99}, "presentation": {"elo": 486.8, "lower95ci": 466.13, "upper95ci": 505.45}}, "briefcaseTotalCost": 0, "timescaleData": {"medianOutputSpeed": 131.137846653751, "medianTimeToFirstChunk": 2.2937167880001}, "outputSpeedVariance": {"p05": 74.6034470308119, "q25": 100.455053803105, "median": 131.137846653751, "q75": 152.939161829861, "p95": 174.145120243687}, "timeToFirstChunkVariance": {"p05": 2.1242177748, "q25": 2.21495197000004, "median": 2.2937167880001, "q75": 2.6970985905, "p95": 5.78060197049999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 135.903523981603, "medianTimeToFirstChunk": 0.662816010000029, "medianTimeToFirstAnswerToken": 0.662816010000029, "medianEndToEndResponseTime": 4.341896473488849}, "long": {"medianOutputSpeed": 131.137846653751, "medianTimeToFirstChunk": 2.2937167880001, "medianTimeToFirstAnswerToken": 2.2937167880001, "medianEndToEndResponseTime": 6.106498626031739}, "hundredK": {"medianOutputSpeed": 126.86484267916, "medianTimeToFirstChunk": 34.928678604, "medianTimeToFirstAnswerToken": 34.928678604, "medianEndToEndResponseTime": 38.86988082709734}, "mediumParallel": {"medianOutputSpeed": 138.553289476241, "medianTimeToFirstChunk": 0.714200712499974, "medianTimeToFirstAnswerToken": 0.714200712499974, "medianEndToEndResponseTime": 4.322920519081972}}, "endToEndResponseTime": {"input": 2.2937167880001, "reasoning": 0, "answer": 3.812781838031639, "total": 6.106498626031739}, "timeToFirstAnswerToken": {"input": 2.2937167880001, "reasoning": 0, "total": 2.2937167880001}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 1, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ceb4d610-d0a4-48c1-bea0-80ed76f1e5ca", "slug": "qwq-32b", "name": "QwQ 32B", "shortName": "QwQ-32B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-05", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2491, "release": {"slug": "qwq-32b", "name": "QwQ 32B"}, "deprecated": true, "deprecatedTo": "qwen3-32b-instruct-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32.8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/QwQ-32B", "microevalsEnabled": false, "intelligenceIndex": 9.47210556751002, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.266666666666667, "ifbench": 0.387755102040816, "hle": 0.0735, "gpqa": 0.592929292929293, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.630687830687831, "aime25": 0.29, "analystAgent": null, "price1mInputTokens": 0.66, "price1mOutputTokens": 1, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.745, "price1mBlended7To2To1": 0.6940000000000001, "price1mBlended0To1To1": 0.8300000000000001, "price1mBlended100To1To1": 0.6633333333333333, "price1mBlended0To100To1": 0.6633663366336634, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "cf095603-72b6-47f8-8ee1-09a42890f92a", "slug": "llama-3-1-nemotron-ultra-253b-v1-reasoning", "name": "Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)", "shortName": "Llama Nemotron Ultra", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-07", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "llama-3-1-nemotron-ultra-253b-v1", "name": "Llama 3.1 Nemotron Ultra 253B v1"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 253, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "NVIDIA Open Model License Agreement", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1", "microevalsEnabled": false, "intelligenceIndex": 7.52746905624501, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -44.8666666666667, "omniscienceBreakdown": {"accuracy": 0.20066666666666666, "hallucinationRate": 0.8123436196830692}, "gdpval": null, "itBenchSre": null, "tau2": 0.114035087719298, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.381632653061225, "hle": 0.0738, "gpqa": 0.728282828282828, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.641269841269841, "aime25": 0.636666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 52.77777777777778, "modelAvailability": 4, "transparencyMethodology": 4, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d034dafe-463d-4c50-956f-84fca657b26f", "slug": "claude-4-sonnet", "name": "Claude 4 Sonnet (Non-reasoning)", "shortName": "Claude 4 Sonnet (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-05-22", "knowledgeCutoffDate": "2025-03-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-4-sonnet", "name": "Claude 4 Sonnet"}, "deprecated": true, "deprecatedTo": "claude-4-5-sonnet", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 16.6124406514554, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -9.01666666666667, "omniscienceBreakdown": {"accuracy": 0.22666666666666666, "hallucinationRate": 0.409698275862069}, "gdpval": null, "itBenchSre": null, "tau2": 0.523391812865497, "tauBanking": null, "terminalbenchHard": 0.272727272727273, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.44, "ifbench": 0.453741496598639, "hle": 0.0426320667284523, "gpqa": 0.682828282828283, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": 0.623699421965318, "livecodebench": 0.448677248677249, "aime25": 0.38, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d0aa27aa-4705-4184-9a1d-483b78c9331c", "slug": "gemma-4-31b-non-reasoning", "name": "Gemma 4 31B (Non-reasoning)", "shortName": "Gemma 4 31B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-02", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-4-31b", "name": "Gemma 4 31B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30.7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-4-31B", "microevalsEnabled": false, "intelligenceIndex": 13.9198819005287, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -51.6833333333333, "omniscienceBreakdown": {"accuracy": 0.16633333333333333, "hallucinationRate": 0.8194722111155538}, "gdpval": 691.46, "gdpvalNormalized": 0.09573000000000002, "itBenchSre": null, "tau2": 0.654970760233918, "tauBanking": 0.088659793814433, "terminalbenchHard": 0.303030303030303, "terminalBench21": 0.292134831460674, "terminalBench40": null, "scicode": null, "lcr": 0.466666666666667, "ifbench": 0.53469387755102, "hle": 0.118164967562558, "gpqa": 0.762626262626263, "critpt": 0, "apexAgents": null, "mmmuPro": 0.703468208092486, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.14, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.14, "cacheHitDiscountPercent": 0.6, "cacheWritePrice": null, "pricePer1k1mpImages": 0.0269, "price1mBlended0To3To1": 0.20500000000000002, "price1mBlended7To2To1": 0.166, "price1mBlended0To1To1": 0.27, "price1mBlended100To1To1": 0.14254901960784316, "price1mBlended0To100To1": 0.1425742574257426, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 43.9818036187747, "medianTimeToFirstChunk": 1.95986389900011}, "outputSpeedVariance": {"p05": 7.3623850931848, "q25": 20.7602539558621, "median": 43.9818036187747, "q75": 112.607306151498, "p95": 222.358985579926}, "timeToFirstChunkVariance": {"p05": 0.397327610349782, "q25": 1.22830466750003, "median": 1.95986389900011, "q75": 3.38750520925001, "p95": 17.2974069004999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 47.7324193963305, "medianTimeToFirstChunk": 0.92004732099997, "medianTimeToFirstAnswerToken": 0.92004732099997, "medianEndToEndResponseTime": 11.395108219305039}, "long": {"medianOutputSpeed": 43.9818036187747, "medianTimeToFirstChunk": 1.95986389900011, "medianTimeToFirstAnswerToken": 1.95986389900011, "medianEndToEndResponseTime": 13.328201685551521}, "hundredK": {"medianOutputSpeed": 31.4020879035068, "medianTimeToFirstChunk": 19.788655907, "medianTimeToFirstAnswerToken": 19.788655907, "medianEndToEndResponseTime": 35.711164038829125}, "mediumParallel": {"medianOutputSpeed": 37.9921557392659, "medianTimeToFirstChunk": 0.833144218000143, "medianTimeToFirstAnswerToken": 0.833144218000143, "medianEndToEndResponseTime": 13.993755672412476}}, "endToEndResponseTime": {"input": 1.95986389900011, "reasoning": 0, "answer": 11.368337786551411, "total": 13.328201685551521}, "timeToFirstAnswerToken": {"input": 1.95986389900011, "reasoning": 0, "total": 1.95986389900011}, "performanceDataSource": {"type": "median"}, "hostModelCount": 11, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d0b3d47e-aec6-425e-9de7-168dcc6d1e28", "slug": "gpt-5-1-non-reasoning", "name": "GPT-5.1 (Non-reasoning)", "shortName": "GPT-5.1 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-13", "knowledgeCutoffDate": "2024-09-30", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-5-1", "name": "GPT-5.1"}, "deprecated": true, "deprecatedTo": "gpt-5-2-non-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 13.3137294472025, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -34.45, "omniscienceBreakdown": {"accuracy": 0.2946666666666667, "hallucinationRate": 0.9061909262759924}, "gdpval": null, "itBenchSre": null, "tau2": 0.464912280701754, "tauBanking": null, "terminalbenchHard": 0.227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.45, "ifbench": 0.431972789115646, "hle": 0.0528266913809083, "gpqa": 0.643434343434343, "critpt": 0, "apexAgents": null, "mmmuPro": 0.623699421965318, "livecodebench": 0.494179894179894, "aime25": 0.38, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.788, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 1.3375, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.3366336633663367, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 96.4345493364362, "medianTimeToFirstChunk": 1.06049445299999}, "outputSpeedVariance": {"p05": 55.3790756656995, "q25": 85.8279523968102, "median": 96.4345493364362, "q75": 124.535041290809, "p95": 155.891870673204}, "timeToFirstChunkVariance": {"p05": 0.887985112550012, "q25": 0.955895704999676, "median": 1.06049445299999, "q75": 1.31826250674998, "p95": 1.65751549110007}, "performanceByPromptType": {"long": {"medianOutputSpeed": 96.4345493364362, "medianTimeToFirstChunk": 1.06049445299999, "medianTimeToFirstAnswerToken": 1.06049445299999, "medianEndToEndResponseTime": 6.245358212311231}}, "endToEndResponseTime": {"input": 1.06049445299999, "reasoning": 0, "answer": 5.184863759311241, "total": 6.245358212311231}, "timeToFirstAnswerToken": {"input": 1.06049445299999, "reasoning": 0, "total": 1.06049445299999}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d1122eff-ee85-4fdc-8a9f-23bee6590667", "slug": "gemini-3-pro", "name": "Gemini 3 Pro Preview (high)", "shortName": "Gemini 3 Pro Preview (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-18", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gemini-3-pro-preview", "name": "Gemini 3 Pro Preview"}, "deprecated": true, "deprecatedTo": "gemini-3-1-pro-preview", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 27.9579716203661, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 15.2833333333333, "omniscienceBreakdown": {"accuracy": 0.5575, "hallucinationRate": 0.9145009416195857}, "gdpval": null, "itBenchSre": null, "tau2": 0.871345029239766, "tauBanking": null, "terminalbenchHard": 0.416666666666667, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.76, "ifbench": 0.704081632653061, "hle": 0.397126969416126, "gpqa": 0.908080808080808, "critpt": 0.0914285714285714, "apexAgents": null, "mmmuPro": 0.801734104046243, "livecodebench": 0.917460317460317, "aime25": 0.956666666666667, "analystAgent": null, "price1mInputTokens": 2, "price1mOutputTokens": 12, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 1.12, "price1mBlended0To3To1": 4.5, "price1mBlended7To2To1": 1.7399999999999998, "price1mBlended0To1To1": 7, "price1mBlended100To1To1": 0.3333333333333333, "price1mBlended0To100To1": 2.099009900990099, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d1720545-d0a8-4c15-a53e-ef5ca99ac7ea", "slug": "gemma-3-1b", "name": "Gemma 3 1B Instruct", "shortName": "Gemma 3 1B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-13", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemma-3-1b-instruct", "name": "Gemma 3 1B Instruct"}, "deprecated": true, "deprecatedTo": "gemma-4-e2b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "Gemma license", "licenseUrl": "https://ai.google.dev/gemma/terms", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-3-1b-it", "microevalsEnabled": false, "intelligenceIndex": 4.83423948, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -75.45, "omniscienceBreakdown": {"accuracy": 0.0375, "hallucinationRate": 0.8228571428571428}, "gdpval": null, "itBenchSre": null, "tau2": 0.105263157894737, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.199319727891156, "hle": 0.0532900834105653, "gpqa": 0.237373737373737, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0169312169312169, "aime25": 0.0333333333333333, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d1768b3a-0a21-4e08-b3f6-56a9ab6cfbf3", "slug": "qwen1.5-110b-chat", "name": "Qwen1.5 Chat 110B", "shortName": "Qwen1.5 Chat 110B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-04-25", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen1.5-110b-chat", "name": "Qwen1.5 Chat 110B"}, "deprecated": true, "deprecatedTo": "qwen2-5-72b-instruct", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 110, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 32000, "licenseName": "Tongyi Qianwen LICENSE AGREEMENT", "licenseUrl": "https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen1.5-110B-Chat", "microevalsEnabled": false, "intelligenceIndex": 5.65355605607575, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": 0.288888888888889, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d2d7dd95-770f-4cb0-9bbc-d275ac19c265", "slug": "glm-4-6v-reasoning", "name": "GLM-4.6V (Reasoning)", "shortName": "GLM-4.6V", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-08", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "glm-4-6v", "name": "GLM-4.6V"}, "deprecated": true, "deprecatedTo": "glm-5v-turbo", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 108, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-4.6V", "microevalsEnabled": false, "intelligenceIndex": 11.2162066974921, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -26.95, "omniscienceBreakdown": {"accuracy": 0.16183333333333333, "hallucinationRate": 0.5146152316563929}, "gdpval": null, "itBenchSre": null, "tau2": 0.315789473684211, "tauBanking": null, "terminalbenchHard": 0.143939393939394, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.486666666666667, "ifbench": 0.300680272108844, "hle": 0.0963855421686747, "gpqa": 0.719191919191919, "critpt": 0, "apexAgents": null, "mmmuPro": 0.485549132947977, "livecodebench": 0.15978835978836, "aime25": 0.853333333333333, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 0.9, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.44999999999999996, "price1mBlended7To2To1": 0.36, "price1mBlended0To1To1": 0.6, "price1mBlended100To1To1": 0.30588235294117644, "price1mBlended0To100To1": 0.30594059405940593, "timescaleData": {"medianOutputSpeed": 70.6309973074749, "medianTimeToFirstChunk": 3.652262498}, "outputSpeedVariance": {"p05": 41.6966266808508, "q25": 52.2674291530189, "median": 70.6309973074749, "q75": 81.2078045099254, "p95": 107.242510026636}, "timeToFirstChunkVariance": {"p05": 1.9278636308, "q25": 2.31070698850001, "median": 3.652262498, "q75": 4.24297492500003, "p95": 14.8608119507}, "performanceByPromptType": {"long": {"medianOutputSpeed": 70.6309973074749, "medianTimeToFirstChunk": 3.652262498, "medianTimeToFirstAnswerToken": 31.968442025997962, "medianEndToEndResponseTime": 39.04748690799745}}, "endToEndResponseTime": {"input": 3.652262498, "reasoning": 28.316179527997964, "answer": 7.079044881999491, "total": 39.04748690799745}, "timeToFirstAnswerToken": {"input": 3.652262498, "reasoning": 28.316179527997964, "total": 31.968442025997962}, "performanceDataSource": {"type": "median"}, "hostModelCount": 2, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d306cccd-0085-4b2f-8aa0-ffcdbb434695", "slug": "minicpm5-1b-non-reasoning", "name": "MiniCPM5-1B (Non-reasoning)", "shortName": "MiniCPM5-1B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-25", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "minicpm5-1b", "name": "MiniCPM5-1B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "apache-2.0", "licenseUrl": "https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md", "modelWeightsSourceUrl": "https://huggingface.co/openbmb/MiniCPM5-1B", "microevalsEnabled": false, "intelligenceIndex": 8.69473818567247, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -0.8, "omniscienceBreakdown": {"accuracy": 0.001, "hallucinationRate": 0.009009009009009009}, "gdpval": null, "itBenchSre": null, "tau2": 0.824561403508772, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.05, "ifbench": 0.351700680272109, "hle": 0.0454124189063948, "gpqa": 0.268686868686869, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 83.33333333333333, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 3, "transparencyPreTrainingData": 3}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "7399e4ac-f64d-4be6-b649-2fc20756839f", "slug": "openbmb", "name": "OpenBMB", "logo": "/img/logos/openbmb_small.svg", "color": "#3B62EC", "country": "cn", "url": "https://www.openbmb.cn/en/home"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d370fcbf-c4a1-41a2-abc4-d204fcc3fcbf", "slug": "qwen3-vl-32b-reasoning", "name": "Qwen3 VL 32B (Reasoning)", "shortName": "Qwen3 VL 32B (Reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-21", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-vl-32b", "name": "Qwen3 VL 32B (Reasoning)"}, "deprecated": true, "deprecatedTo": "qwen3-5-27b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 33.4, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-VL-32B-Thinking", "microevalsEnabled": false, "intelligenceIndex": 11.8701729641937, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -52.5166666666667, "omniscienceBreakdown": {"accuracy": 0.16966666666666666, "hallucinationRate": 0.8368125250903252}, "gdpval": null, "itBenchSre": null, "tau2": 0.456140350877193, "tauBanking": null, "terminalbenchHard": 0.0757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.553333333333333, "ifbench": 0.593877551020408, "hle": 0.101482854494903, "gpqa": 0.733333333333333, "critpt": 0, "apexAgents": null, "mmmuPro": 0.634104046242775, "livecodebench": 0.737566137566138, "aime25": 0.846666666666667, "analystAgent": null, "price1mInputTokens": 0.16, "price1mOutputTokens": 0.64, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.716, "price1mBlended0To3To1": 0.28, "price1mBlended7To2To1": 0.20800000000000002, "price1mBlended0To1To1": 0.4, "price1mBlended100To1To1": 0.16470588235294117, "price1mBlended0To100To1": 0.16475247524752476, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 88.8547811108001, "medianTimeToFirstChunk": 2.66809725600001}, "outputSpeedVariance": {"p05": 76.5492707859112, "q25": 83.7614657458906, "median": 88.8547811108001, "q75": 90.9695282263913, "p95": 91.9972669109323}, "timeToFirstChunkVariance": {"p05": 2.45706550199999, "q25": 2.51979287274997, "median": 2.66809725600001, "q75": 2.87699098374999, "p95": 3.35091318579998}, "performanceByPromptType": {"long": {"medianOutputSpeed": 88.8547811108001, "medianTimeToFirstChunk": 2.66809725600001, "medianTimeToFirstAnswerToken": 25.176734101394302, "medianEndToEndResponseTime": 30.803893312742876}}, "endToEndResponseTime": {"input": 2.66809725600001, "reasoning": 22.508636845394292, "answer": 5.627159211348573, "total": 30.803893312742876}, "timeToFirstAnswerToken": {"input": 2.66809725600001, "reasoning": 22.508636845394292, "total": 25.176734101394302}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d3968fd3-97d8-4693-8d26-19cefc6f5d5f", "slug": "hermes-4-llama-3-1-405b", "name": "Hermes 4 - Llama-3.1 405B (Non-reasoning)", "shortName": "Hermes 4 405B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-27", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "hermes-4-llama-3-1-405b", "name": "Hermes 4 - Llama-3.1 405B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 406, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "META LLAMA 3 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://llama.meta.com/llama3/license/", "modelWeightsSourceUrl": "https://huggingface.co/NousResearch/Hermes-4-405B", "microevalsEnabled": false, "intelligenceIndex": 7.41221110231024, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -33.2833333333333, "omniscienceBreakdown": {"accuracy": 0.2605, "hallucinationRate": 0.8023439260761775}, "gdpval": null, "itBenchSre": null, "tau2": 0.266081871345029, "tauBanking": null, "terminalbenchHard": 0.0984848484848485, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.22, "ifbench": 0.347619047619048, "hle": 0.0421686746987952, "gpqa": 0.536363636363636, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.546031746031746, "aime25": 0.153333333333333, "analystAgent": null, "price1mInputTokens": 1, "price1mOutputTokens": 3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5, "price1mBlended7To2To1": 1.2, "price1mBlended0To1To1": 2, "price1mBlended100To1To1": 1.0196078431372548, "price1mBlended0To100To1": 1.0198019801980198, "openness": {"opennessIndex": 47.22222222222222, "modelAvailability": 4, "transparencyMethodology": 3, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 44.174978632777, "medianTimeToFirstChunk": 2.33769267150001}, "outputSpeedVariance": {"p05": 34.582196523658, "q25": 42.250751968616, "median": 44.174978632777, "q75": 45.7548346856893, "p95": 46.4941952659348}, "timeToFirstChunkVariance": {"p05": 2.26161508489998, "q25": 2.29448205125004, "median": 2.33769267150001, "q75": 2.44242678250001, "p95": 4.12860280569997}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 43.5379669539592, "medianTimeToFirstChunk": 0.758632069000001, "medianTimeToFirstAnswerToken": 0.758632069000001, "medianEndToEndResponseTime": 12.242861466499042}, "long": {"medianOutputSpeed": 44.174978632777, "medianTimeToFirstChunk": 2.33769267150001, "medianTimeToFirstAnswerToken": 2.33769267150001, "medianEndToEndResponseTime": 13.656317274727536}, "hundredK": {"medianOutputSpeed": 37.3482955851089, "medianTimeToFirstChunk": 27.8306555774999, "medianTimeToFirstAnswerToken": 27.8306555774999, "medianEndToEndResponseTime": 41.218147353680294}, "mediumParallel": {"medianOutputSpeed": 36.0465965003294, "medianTimeToFirstChunk": 1.78867409599997, "medianTimeToFirstAnswerToken": 1.78867409599997, "medianEndToEndResponseTime": 15.659609178468322}}, "endToEndResponseTime": {"input": 2.33769267150001, "reasoning": 0, "answer": 11.318624603227526, "total": 13.656317274727536}, "timeToFirstAnswerToken": {"input": 2.33769267150001, "reasoning": 0, "total": 2.33769267150001}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0a2f41cc-2cbc-4949-be54-9fef1319d4a9", "slug": "nous-research", "name": "Nous Research", "logo": "/img/logos/nousresearch_small.jpg", "color": "#006fa8", "country": "us", "url": "https://nousresearch.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d4be6393-8915-436c-a3a8-4e59bd5c89a9", "slug": "granite-4-1-30b", "name": "Granite 4.1 30B", "shortName": "Granite 4.1 30B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-29", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "granite-4-1-30b", "name": "Granite 4.1 30B"}, "deprecated": true, "deprecatedTo": "granite-4-2-30b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.1-30b", "microevalsEnabled": false, "intelligenceIndex": 7.43693799607016, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -67.7833333333333, "omniscienceBreakdown": {"accuracy": 0.1395, "hallucinationRate": 0.9498353670346698}, "gdpval": 378.65, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.421052631578947, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": 0.0262172284644195, "terminalBench40": null, "scicode": null, "lcr": 0.236666666666667, "ifbench": 0.443537414965986, "hle": 0.041241890639481, "gpqa": 0.480808080808081, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 61.111111111111114, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d4fc3f33-f2b0-4da1-88ee-f1f82bd4de31", "slug": "gpt-5-4-nano", "name": "GPT-5.4 nano (xhigh)", "shortName": "GPT-5.4 nano (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-17", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-4-nano", "name": "GPT-5.4 nano"}, "deprecated": true, "deprecatedTo": "gpt-5-6-luna-xhigh", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 21.2442352504557, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 21.521351049672926, "strategyAndOps": 16.728408881295923, "legal": 22.78588258617129, "healthcareAndMedical": 17.424150818735555, "engineering": 23.176253830793424, "economics": 30.920790954299996}, "omniscience": -29.4666666666667, "omniscienceBreakdown": {"accuracy": 0.25666666666666665, "hallucinationRate": 0.7417040358744394}, "mlcrOverall": 0.05, "harveyLab": 0.522362136343899, "gdpPdfAllPass": 0.078, "gdpval": 1035.42, "gdpvalNormalized": 0.26771000000000006, "itBenchSre": 0.243879472693032, "tau2": 0.760233918128655, "tauBanking": 0.274226804123711, "terminalbenchHard": 0.424242424242424, "terminalBench21": 0.606741573033708, "terminalBench40": 0.00505050505050505, "scicode": 0.472222222222222, "lcr": 0.766666666666667, "ifbench": 0.759183673469388, "hle": 0.282669138090825, "gpqa": 0.817171717171717, "critpt": 0.0925306122448979, "apexAgents": 0.249262536873156, "mmmuPro": 0.653757225433526, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.05960613074868808, "enterpriseOpsGym": 0.3148313936138466, "price1mInputTokens": 0.2, "price1mOutputTokens": 1.25, "cacheHitPrice": 0.02, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.5, "price1mBlended0To3To1": 0.4625, "price1mBlended7To2To1": 0.179, "price1mBlended0To1To1": 0.725, "price1mBlended100To1To1": 0.03382352941176471, "price1mBlended0To100To1": 0.2103960396039604, "intelligenceIndexTimePerTask": 418.9724659392721, "intelligenceIndexCost": {"total": 331.2403616636226, "input": 98.39009916362261, "nonCacheInput": 4.3930142, "cacheRead": 38.93528571515304, "cacheWrite": 55.06179924846956, "output": 232.8502625, "reasoning": 217.76634125, "answer": 15.083921250000001}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.1830802502922872, "input": 0.09991766310144838, "nonCacheInput": 0.003088938282176325, "cacheRead": 0.04129412327324764, "cacheWrite": 0.055534601546024416, "output": 0.0831625871908388, "reasoning": 0.07118380592087782, "answer": 0.01197878126996098}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.08820817433685044}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0240642575473984}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0016385050957639937}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.04001411902017877}, {"slug": "scicode", "weightedCostPerTask": 0.002267486614583334}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.00429115314179796}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.005695963150000001}, {"slug": "critpt", "weightedCostPerTask": 0.014225881285714283}, {"slug": "omniscience", "weightedCostPerTask": 0.0014923635249999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.001182346575}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2244038353, "output": 186280210, "answer": 12067137, "reasoning": 174213073}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 56947.044736702264, "answer": 9583.025015968784, "output": 66530.06975267104}, "briefcaseBreakdown": {"overall": {"elo": 669.58, "lower95ci": 659.54, "upper95ci": 679.09}, "rubricPassRate": 0.14621676891615543, "analyticalQuality": {"elo": 639.85, "lower95ci": 621.87, "upper95ci": 659.23}, "presentation": {"elo": 586.01, "lower95ci": 567.46, "upper95ci": 604.64}}, "briefcaseTotalCost": 53.51295909768926, "timescaleData": {"medianOutputSpeed": 158.562050947907, "medianTimeToFirstChunk": 62.3139017244998}, "outputSpeedVariance": {"p05": 120.214653504664, "q25": 151.497333638599, "median": 158.562050947907, "q75": 171.871748084025, "p95": 226.737843362096}, "timeToFirstChunkVariance": {"p05": 44.80244202345, "q25": 54.0589607585, "median": 62.3139017244998, "q75": 142.05901573725, "p95": 161.4232032692}, "performanceByPromptType": {"long": {"medianOutputSpeed": 158.562050947907, "medianTimeToFirstChunk": 62.3139017244998, "medianTimeToFirstAnswerToken": 62.3139017244998, "medianEndToEndResponseTime": 65.4672413603769}}, "endToEndResponseTime": {"input": 62.3139017244998, "reasoning": 0, "answer": 3.1533396358771046, "total": 65.4672413603769}, "timeToFirstAnswerToken": {"input": 62.3139017244998, "reasoning": 0, "total": 62.3139017244998}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d5170215-69be-4129-849b-26d8d8825bfc", "slug": "muse-spark-1-3-xhigh", "name": "Muse Spark 1.3 (xhigh)", "shortName": "Muse Spark 1.3 (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "muse-spark-1-3", "name": "Muse Spark 1.3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 45.1612216922226, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 47.962441542820116, "strategyAndOps": 49.26616568719428, "legal": 48.98343999138821, "engineering": 45.735501575532915, "economics": 55.010220342910095}, "omniscience": 23.1166666666667, "omniscienceBreakdown": {"accuracy": 0.4151666666666667, "hallucinationRate": 0.3146195497292676}, "harveyLab": 0.954841511072514, "gdpPdfAllPass": 0.242, "gdpval": 1662.34, "gdpvalNormalized": 0.58117, "itBenchSre": null, "tau2": null, "tauBanking": 0.472164948453608, "terminalbenchHard": null, "terminalBench21": 0.853932584269663, "terminalBench40": 0.166666666666667, "scicode": 0.597222222222222, "lcr": 0.83, "ifbench": null, "hle": 0.47451343836886, "gpqa": 0.941414141414141, "critpt": 0.26, "apexAgents": null, "mmmuPro": 0.820231213872832, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5683609003249621, "price1mInputTokens": 1.25, "price1mOutputTokens": 4.25, "cacheHitPrice": 0.15, "cacheHitDiscountPercent": 0.88, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2, "price1mBlended7To2To1": 0.78, "price1mBlended0To1To1": 2.75, "price1mBlended100To1To1": 0.20098039215686275, "price1mBlended0To100To1": 1.2797029702970297, "intelligenceIndexTimePerTask": 232.5118081349218, "intelligenceIndexCost": {"total": 1655.2659660850002, "input": 1072.6752010850003, "nonCacheInput": 30.463553750000003, "cacheRead": 631.8350943974999, "cacheWrite": 410.3765529375004, "output": 582.5907649999999, "reasoning": 456.4705615, "answer": 126.1202035}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.3677936514692752, "input": 1.1361136556121443, "nonCacheInput": 0.022424631305992284, "cacheRead": 0.7053631760294088, "cacheWrite": 0.40832584827674323, "output": 0.23167999585713062, "reasoning": 0.13826752296182798, "answer": 0.09341247289530265}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.5130901957170333}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.1395897439386364}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.018436831469939116}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.6231928608636365}, {"slug": "scicode", "weightedCostPerTask": 0.0037165736979166667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.010410691682113067}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.019641599500000002}, {"slug": "critpt", "weightedCostPerTask": 0.0308008575}, {"slug": "omniscience", "weightedCostPerTask": 0.0023402448499999996}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.006574052250000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4564906048, "output": 137080180, "answer": 29675342, "reasoning": 107404838}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 32533.534814547762, "answer": 21979.40538713003, "output": 54512.94020167779}, "briefcaseBreakdown": {"overall": {"elo": 1483.22, "lower95ci": 1473.51, "upper95ci": 1493.73}, "rubricPassRate": 0.5161616161616162, "analyticalQuality": {"elo": 1580.73, "lower95ci": 1563.74, "upper95ci": 1597.86}, "presentation": {"elo": 1468.85, "lower95ci": 1450.73, "upper95ci": 1487.49}}, "briefcaseTotalCost": 311.2747187350002, "timescaleData": {"medianOutputSpeed": 240.976581512463, "medianTimeToFirstChunk": 24.67182423}, "outputSpeedVariance": {"p05": 83.0232063320522, "q25": 158.307817897713, "median": 240.976581512463, "q75": 310.421353331718, "p95": 440.435941169267}, "timeToFirstChunkVariance": {"p05": 13.28593774075, "q25": 18.30433234775, "median": 24.67182423, "q75": 31.8897215602501, "p95": 43.19596593705}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 287.73770580298, "medianTimeToFirstChunk": 22.521511433, "medianTimeToFirstAnswerToken": 29.472286252096673, "medianEndToEndResponseTime": 31.209979956870843}, "long": {"medianOutputSpeed": 240.976581512463, "medianTimeToFirstChunk": 24.67182423, "medianTimeToFirstAnswerToken": 32.9713859029527, "medianEndToEndResponseTime": 35.046276321190874}, "hundredK": {"medianOutputSpeed": 366.505288089804, "medianTimeToFirstChunk": 31.276805818, "medianTimeToFirstAnswerToken": 36.73375300264729, "medianEndToEndResponseTime": 38.09798979880911}, "mediumParallel": {"medianOutputSpeed": 229.341947612614, "medianTimeToFirstChunk": 23.9149602899999, "medianTimeToFirstAnswerToken": 32.63556295697576, "medianEndToEndResponseTime": 34.81571362371973}}, "endToEndResponseTime": {"input": 24.67182423, "reasoning": 8.299561672952699, "answer": 2.0748904182381747, "total": 35.046276321190874}, "timeToFirstAnswerToken": {"input": 24.67182423, "reasoning": 8.299561672952699, "total": 32.9713859029527}, "performanceDataSource": {"type": "firstParty", "providerName": "Meta"}, "hostModelCount": 5, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d58b9ada-fd9d-4fff-a086-242034657963", "slug": "claude-sonnet-5-non-reasoning", "name": "Claude Sonnet 5 (Non-reasoning, High Effort)", "shortName": "Claude Sonnet 5 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "claude-sonnet-5", "name": "Claude Sonnet 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 28.9377045284576, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -0.65, "omniscienceBreakdown": {"accuracy": 0.338, "hallucinationRate": 0.520392749244713}, "gdpval": 1283.47, "gdpvalNormalized": 0.391735, "itBenchSre": null, "tau2": null, "tauBanking": 0.156701030927835, "terminalbenchHard": null, "terminalBench21": 0.752808988764045, "terminalBench40": null, "scicode": null, "lcr": 0.7, "ifbench": null, "hle": 0.190454124189064, "gpqa": 0.8, "critpt": 0.0114285714285714, "apexAgents": null, "mmmuPro": 0.71907514450867, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 2, "price1mOutputTokens": 10, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 4, "price1mBlended7To2To1": 1.54, "price1mBlended0To1To1": 6, "price1mBlended100To1To1": 0.3137254901960784, "price1mBlended0To100To1": 2.0792079207920793, "timescaleData": {"medianOutputSpeed": 67.1190975388743, "medianTimeToFirstChunk": 1.38739828000001}, "outputSpeedVariance": {"p05": 49.6470742870952, "q25": 53.7334321691657, "median": 67.1190975388743, "q75": 80.9459791945222, "p95": 94.4095178467439}, "timeToFirstChunkVariance": {"p05": 0.629161136300026, "q25": 0.888899887250063, "median": 1.38739828000001, "q75": 1.81170383500004, "p95": 2.83272292799999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 66.3486435248189, "medianTimeToFirstChunk": 0.775446488500009, "medianTimeToFirstAnswerToken": 0.775446488500009, "medianEndToEndResponseTime": 8.311395581610949}, "long": {"medianOutputSpeed": 67.1190975388743, "medianTimeToFirstChunk": 1.38739828000001, "medianTimeToFirstAnswerToken": 1.38739828000001, "medianEndToEndResponseTime": 8.836842899102763}, "hundredK": {"medianOutputSpeed": 69.0633806708051, "medianTimeToFirstChunk": 5.88208952350001, "medianTimeToFirstAnswerToken": 5.88208952350001, "medianEndToEndResponseTime": 13.12181620851824}, "mediumParallel": {"medianOutputSpeed": 58.2172164365821, "medianTimeToFirstChunk": 1.05368068050006, "medianTimeToFirstAnswerToken": 1.05368068050006, "medianEndToEndResponseTime": 9.642205357640304}}, "endToEndResponseTime": {"input": 1.38739828000001, "reasoning": 0, "answer": 7.449444619102753, "total": 8.836842899102763}, "timeToFirstAnswerToken": {"input": 1.38739828000001, "reasoning": 0, "total": 1.38739828000001}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 2, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d58cf573-1bd3-4d1f-9182-5482a460f570", "slug": "qwen3-vl-235b-a22b-instruct", "name": "Qwen3 VL 235B A22B Instruct", "shortName": "Qwen3 VL 235B A22B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-23", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-vl-235b-a22b-instruct", "name": "Qwen3 VL 235B A22B Instruct"}, "deprecated": true, "deprecatedTo": "qwen3-5-397b-a17b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 235, "inferenceParametersActiveBillions": 22, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 9.93699415502801, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -52.6666666666667, "omniscienceBreakdown": {"accuracy": 0.203, "hallucinationRate": 0.9155165202843998}, "gdpval": null, "itBenchSre": null, "tau2": 0.350877192982456, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.326666666666667, "ifbench": 0.426530612244898, "hle": 0.0662650602409639, "gpqa": 0.712121212121212, "critpt": 0, "apexAgents": null, "mmmuPro": 0.675722543352601, "livecodebench": 0.593650793650794, "aime25": 0.706666666666667, "analystAgent": null, "price1mInputTokens": 0.4, "price1mOutputTokens": 1.6, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.716, "price1mBlended0To3To1": 0.7000000000000001, "price1mBlended7To2To1": 0.5200000000000001, "price1mBlended0To1To1": 1, "price1mBlended100To1To1": 0.4117647058823529, "price1mBlended0To100To1": 0.4118811881188119, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 49.7872767091561, "medianTimeToFirstChunk": 2.66520994749999}, "outputSpeedVariance": {"p05": 36.4480217308091, "q25": 46.9951448012943, "median": 49.7872767091561, "q75": 53.294135992521, "p95": 60.8107333497598}, "timeToFirstChunkVariance": {"p05": 2.54604920670001, "q25": 2.57017823224996, "median": 2.66520994749999, "q75": 2.99641340750014, "p95": 3.66709815030009}, "performanceByPromptType": {"long": {"medianOutputSpeed": 49.7872767091561, "medianTimeToFirstChunk": 2.66520994749999, "medianTimeToFirstAnswerToken": 2.66520994749999, "medianEndToEndResponseTime": 12.707936383831619}}, "endToEndResponseTime": {"input": 2.66520994749999, "reasoning": 0, "answer": 10.042726436331629, "total": 12.707936383831619}, "timeToFirstAnswerToken": {"input": 2.66520994749999, "reasoning": 0, "total": 2.66520994749999}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 4, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d61493e2-43ff-460c-9054-eaf6ba317360", "slug": "muse-spark-1-1", "name": "Muse Spark 1.1 (xhigh)", "shortName": "Muse Spark 1.1 (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "muse-spark-1-1", "name": "Muse Spark 1.1"}, "deprecated": true, "deprecatedTo": "muse-spark-1-2", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1048576, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 34.2657675919846, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 39.39549344832693, "strategyAndOps": 37.61027709399176, "legal": 43.29340707041142, "engineering": 38.29784151673936, "economics": 48.44408570821749}, "omniscience": 28.0833333333333, "omniscienceBreakdown": {"accuracy": 0.5205, "hallucinationRate": 0.49982620785540494}, "gdpPdfAllPass": 0.144, "gdpval": 1294.15, "gdpvalNormalized": 0.39707500000000007, "itBenchSre": null, "tau2": null, "tauBanking": 0.317525773195876, "terminalbenchHard": null, "terminalBench21": 0.779026217228464, "terminalBench40": 0.0606060606060606, "scicode": 0.587962962962963, "lcr": 0.776666666666667, "ifbench": null, "hle": 0.462001853568119, "gpqa": 0.897979797979798, "critpt": 0.151428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.38848916245422865, "price1mInputTokens": 1.25, "price1mOutputTokens": 4.25, "cacheHitPrice": 0.15, "cacheHitDiscountPercent": 0.88, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2, "price1mBlended7To2To1": 0.78, "price1mBlended0To1To1": 2.75, "price1mBlended100To1To1": 0.20098039215686275, "price1mBlended0To100To1": 1.2797029702970297, "intelligenceIndexCost": {"total": 1737.1834210250004, "input": 1006.0378755250002, "nonCacheInput": 31.14276875, "cacheRead": 603.6671077125, "cacheWrite": 371.2279990625003, "output": 731.1455455, "reasoning": 594.200864, "answer": 136.9446815}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.3802453886670354, "input": 1.1440207014984463, "nonCacheInput": 0.0228423940227223, "cacheRead": 0.7316065823630551, "cacheWrite": 0.38957172511266885, "output": 0.23622468716858927, "reasoning": 0.1269308704109567, "answer": 0.10929381675763261}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.3777722816868133}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.028819144506818183}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.03769455360578387}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.8574393914242424}, {"slug": "scicode", "weightedCostPerTask": 0.00306867578125}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.010746071026413347}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0185094675}, {"slug": "critpt", "weightedCostPerTask": 0.03759185678571429}, {"slug": "omniscience", "weightedCostPerTask": 0.002121404225}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.006482542125}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4346343999, "output": 172034246, "answer": 32222278, "reasoning": 139811968}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 29866.08715551922, "answer": 25716.192178266498, "output": 55582.279333785715}, "briefcaseBreakdown": {"overall": {"elo": 860.36, "lower95ci": 851.99, "upper95ci": 867.89}, "rubricPassRate": 0.34545454545454546, "analyticalQuality": {"elo": 1003.94, "lower95ci": 990.52, "upper95ci": 1017.2}, "presentation": {"elo": 436.74, "lower95ci": 417.95, "upper95ci": 453.65}}, "briefcaseTotalCost": 229.18185089000008, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Meta"}, "hostModelCount": 2, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d621247c-d47e-458c-82cb-a166bc3b37e5", "slug": "deepseek-v3-2-reasoning", "name": "DeepSeek V3.2 (Reasoning)", "shortName": "DeepSeek V3.2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-01", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-v3-2", "name": "DeepSeek V3.2"}, "deprecated": true, "deprecatedTo": "deepseek-v4-pro-0424", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3.2", "microevalsEnabled": false, "intelligenceIndex": 21.4867901704834, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -22.4833333333333, "omniscienceBreakdown": {"accuracy": 0.32966666666666666, "hallucinationRate": 0.8272003978120338}, "gdpval": 810.24, "gdpvalNormalized": 0.15512, "itBenchSre": null, "tau2": 0.906432748538012, "tauBanking": null, "terminalbenchHard": 0.356060606060606, "terminalBench21": 0.468164794007491, "terminalBench40": null, "scicode": null, "lcr": 0.733333333333333, "ifbench": 0.606802721088435, "hle": 0.245597775718258, "gpqa": 0.84040404040404, "critpt": 0.0285714285714286, "apexAgents": 0.145280235988201, "mmmuPro": null, "livecodebench": 0.862433862433862, "aime25": 0.92, "analystAgent": null, "price1mInputTokens": 0.28, "price1mOutputTokens": 0.42, "cacheHitPrice": 0.014, "cacheHitDiscountPercent": 0.95, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.315, "price1mBlended7To2To1": 0.1078, "price1mBlended0To1To1": 0.35, "price1mBlended100To1To1": 0.020588235294117647, "price1mBlended0To100To1": 0.2813861386138614, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 10, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d6f43d0a-e8c4-447c-9ff7-5cf0a9d59aa3", "slug": "grok-4-6-xhigh", "name": "Grok 4.6 (xhigh)", "shortName": "Grok 4.6 (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-12", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "grok-4-6", "name": "Grok 4.6"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 500000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 44.270160436996, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 48.963360347647765, "strategyAndOps": 51.28700437279218, "legal": 51.631940613213764, "engineering": 45.07658773595883, "economics": 54.67762870713625}, "omniscience": 29.3166666666667, "omniscienceBreakdown": {"accuracy": 0.43, "hallucinationRate": 0.24005847953216375}, "gdpPdfAllPass": 0.172, "gdpval": 1663.07, "gdpvalNormalized": 0.5815349999999999, "itBenchSre": null, "tau2": null, "tauBanking": 0.43298969072165, "terminalbenchHard": null, "terminalBench21": 0.880149812734082, "terminalBench40": 0.171717171717172, "scicode": 0.530092592592593, "lcr": 0.81, "ifbench": null, "hle": 0.440685820203893, "gpqa": 0.935353535353535, "critpt": 0.197142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.6699736836183247, "price1mInputTokens": 2, "price1mOutputTokens": 6, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.35, "price1mBlended0To1To1": 4, "price1mBlended100To1To1": 0.5686274509803921, "price1mBlended0To100To1": 2.0396039603960396, "intelligenceIndexTimePerTask": 644.5627375858841, "intelligenceIndexCost": {"total": 2830.0686238377757, "input": 2246.5653058377757, "nonCacheInput": 49.085978, "cacheRead": 896.2496573874081, "cacheWrite": 1301.2296704503674, "output": 583.503318, "reasoning": 447.700146, "answer": 135.80317200000002}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.323692124283027, "input": 2.0980432159519586, "nonCacheInput": 0.032954786631021526, "cacheRead": 0.870674917176649, "cacheWrite": 1.1944135121442876, "output": 0.22564890833106815, "reasoning": 0.11881005510049145, "answer": 0.10683885323057671}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.9796148595942716}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.3202370383693247}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.04134432695468555}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.8983965299295481}, {"slug": "scicode", "weightedCostPerTask": 0.002956769444444445}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.012478578869323447}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.026171466000000004}, {"slug": "critpt", "weightedCostPerTask": 0.031089448571428577}, {"slug": "omniscience", "weightedCostPerTask": 0.0012236255499999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.010179480999999999}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2467657139, "output": 97250553, "answer": 22633862, "reasoning": 74616691}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 19801.67585008191, "answer": 17806.47553842945, "output": 37608.15138851136}, "briefcaseBreakdown": {"overall": {"elo": 1545.11, "lower95ci": 1538.79, "upper95ci": 1551.98}, "rubricPassRate": 0.5383838383838384, "analyticalQuality": {"elo": 1680.03, "lower95ci": 1667.85, "upper95ci": 1693.05}, "presentation": {"elo": 1515.41, "lower95ci": 1503.76, "upper95ci": 1528.11}}, "briefcaseTotalCost": 594.2996814871915, "timescaleData": {"medianOutputSpeed": 59.065318087042, "medianTimeToFirstChunk": 25.400185502}, "outputSpeedVariance": {"p05": 43.5718214215127, "q25": 50.6069615299501, "median": 59.065318087042, "q75": 72.9065549252104, "p95": 83.5162427379854}, "timeToFirstChunkVariance": {"p05": 15.7113245652999, "q25": 20.1188236254998, "median": 25.400185502, "q75": 52.3169129247501, "p95": 74.8189049718001}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 60.640759321923, "medianTimeToFirstChunk": 37.9781055700001, "medianTimeToFirstAnswerToken": 37.9781055700001, "medianEndToEndResponseTime": 46.22338491001719}, "long": {"medianOutputSpeed": 59.065318087042, "medianTimeToFirstChunk": 25.400185502, "medianTimeToFirstAnswerToken": 25.400185502, "medianEndToEndResponseTime": 33.86539006185984}, "hundredK": {"medianOutputSpeed": 68.6638555030875, "medianTimeToFirstChunk": 38.4183787724999, "medianTimeToFirstAnswerToken": 38.4183787724999, "medianEndToEndResponseTime": 45.700230284282796}, "mediumParallel": {"medianOutputSpeed": 64.4355178272083, "medianTimeToFirstChunk": 34.5551664185, "medianTimeToFirstAnswerToken": 34.5551664185, "medianEndToEndResponseTime": 42.314861953822785}}, "endToEndResponseTime": {"input": 25.400185502, "reasoning": 0, "answer": 8.465204559859842, "total": 33.86539006185984}, "timeToFirstAnswerToken": {"input": 25.400185502, "reasoning": 0, "total": 25.400185502}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 1, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d734e2ce-5cf8-467f-8148-586d02671333", "slug": "exaone-4-0-1-2b-reasoning", "name": "Exaone 4.0 1.2B (Reasoning)", "shortName": "Exaone 4.0 1.2B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-15", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "exaone-4-0-1-2b", "name": "Exaone 4.0 1.2B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 1.28, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 64000, "licenseName": "EXAONE AI Model License Agreement 1.2 - NC", "licenseUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-1.2B", "microevalsEnabled": false, "intelligenceIndex": 5.27138994054015, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -79.8166666666667, "omniscienceBreakdown": {"accuracy": 0.06833333333333333, "hallucinationRate": 0.9300536672629696}, "gdpval": null, "itBenchSre": null, "tau2": 0.16374269005848, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.229931972789116, "hle": 0.0597775718257646, "gpqa": 0.515151515151515, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.516402116402116, "aime25": 0.503333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 3, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "45157c16-fcbb-4110-b20f-7bca754b6554", "slug": "lg", "name": "LG AI Research", "logo": "/img/logos/lg_small.png", "color": "#df3b8a", "country": "kr", "url": "https://www.lgresearch.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d80eb0f1-f62e-4d31-99d2-7a925eb126b0", "slug": "gemma-4-e4b", "name": "Gemma 4 E4B (Reasoning)", "shortName": "Gemma 4 E4B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-03", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "gemma-4-e4b", "name": "Gemma 4 E4B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8, "inferenceParametersActiveBillions": 4.5, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-4-E4B-it", "microevalsEnabled": false, "intelligenceIndex": 8.91477392266452, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -19.7, "omniscienceBreakdown": {"accuracy": 0.08583333333333333, "hallucinationRate": 0.30938924339106655}, "gdpval": 176.92, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.207602339181287, "tauBanking": null, "terminalbenchHard": 0.0833333333333333, "terminalBench21": 0.0187265917602996, "terminalBench40": null, "scicode": null, "lcr": 0.32, "ifbench": 0.442176870748299, "hle": 0.0375347544022243, "gpqa": 0.575757575757576, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": 0.513872832369942, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.02, "price1mOutputTokens": 0.1, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.04, "price1mBlended7To2To1": 0.028000000000000004, "price1mBlended0To1To1": 0.060000000000000005, "price1mBlended100To1To1": 0.020784313725490198, "price1mBlended0To100To1": 0.020792079207920793, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 42.7859547992677, "medianTimeToFirstChunk": 0.865107724500007}, "outputSpeedVariance": {"p05": 21.3956060563411, "q25": 36.7632777658511, "median": 42.7859547992677, "q75": 48.1787740085284, "p95": 54.2990523368712}, "timeToFirstChunkVariance": {"p05": 0.734968374499969, "q25": 0.781979438499889, "median": 0.865107724500007, "q75": 0.981834998250065, "p95": 1.20467815474996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 37.873881660068, "medianTimeToFirstChunk": 0.392026868000016, "medianTimeToFirstAnswerToken": 53.198866630312594, "medianEndToEndResponseTime": 66.40057657089073}, "long": {"medianOutputSpeed": 42.7859547992677, "medianTimeToFirstChunk": 0.865107724500007, "medianTimeToFirstAnswerToken": 47.60941924876289, "medianEndToEndResponseTime": 59.29549712982861}, "hundredK": {"medianOutputSpeed": 29.2009365537406, "medianTimeToFirstChunk": 10.58814073, "medianTimeToFirstAnswerToken": 79.07909465263378, "medianEndToEndResponseTime": 96.20183313329224}, "mediumParallel": {"medianOutputSpeed": 68.750012115672, "medianTimeToFirstChunk": 0.487290602999963, "medianTimeToFirstAnswerToken": 29.578194567278498, "medianEndToEndResponseTime": 36.85092055834813}}, "endToEndResponseTime": {"input": 0.865107724500007, "reasoning": 46.74431152426288, "answer": 11.68607788106572, "total": 59.29549712982861}, "timeToFirstAnswerToken": {"input": 0.865107724500007, "reasoning": 46.74431152426288, "total": 47.60941924876289}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d8ddb241-b3e4-4c25-a6a3-72eb1b30c541", "slug": "deepseek-v4-flash-0420", "name": "DeepSeek V4 Flash 0420 (Reasoning, Max Effort)", "shortName": "DeepSeek V4 Flash (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 5613, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "deepseek-v4-flash-0420", "name": "DeepSeek V4 Flash 0420"}, "deprecated": true, "deprecatedTo": "deepseek-v4-flash", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 284, "inferenceParametersActiveBillions": 13, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash", "microevalsEnabled": true, "intelligenceIndex": 24.626713823555, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 27.511660692640604, "strategyAndOps": 27.7884648128209, "legal": 27.591952585732564, "healthcareAndMedical": 26.901179771621557, "engineering": 26.838328544748435, "economics": 32.62258238724128}, "omniscience": -23.9, "omniscienceBreakdown": {"accuracy": 0.36816666666666664, "hallucinationRate": 0.9609601688208916}, "mlcrOverall": 0.15, "harveyLab": 0.813287016934433, "gdpPdfAllPass": 0.108, "gdpval": 1115.64, "gdpvalNormalized": 0.30782000000000004, "itBenchSre": 0.315160075329567, "tau2": 0.950292397660819, "tauBanking": 0.309278350515464, "terminalbenchHard": 0.356060606060606, "terminalBench21": 0.617977528089888, "terminalBench40": 0.0252525252525253, "scicode": 0.452546296296296, "lcr": 0.743333333333333, "ifbench": 0.791836734693877, "hle": 0.348470806302132, "gpqa": 0.893939393939394, "critpt": 0.0714285714285714, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": 0.25, "automationBenchPartialScore": 0.27985986830616555, "enterpriseOpsGym": 0.39570277529095793, "price1mInputTokens": 0.13, "price1mOutputTokens": 0.28, "cacheHitPrice": 0.028, "cacheHitDiscountPercent": 0.7974413646055437, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.1675, "price1mBlended7To2To1": 0.0736, "price1mBlended0To1To1": 0.20500000000000002, "price1mBlended100To1To1": 0.03147058823529412, "price1mBlended0To100To1": 0.1314851485148515, "intelligenceIndexCost": {"total": 190.87882481373208, "input": 120.87545361373209, "nonCacheInput": 2.14274697, "cacheRead": 71.13856126760297, "cacheWrite": 47.59414537612912, "output": 70.0033712, "reasoning": 64.05000056, "answer": 5.953370640000001}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.11794440406341464, "input": 0.10250290159868769, "nonCacheInput": 0.0011565787415497705, "cacheRead": 0.06332581066379589, "cacheWrite": 0.03802051219334202, "output": 0.015441502464726968, "reasoning": 0.011355422382687903, "answer": 0.004086080082039067}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.01079060542275069}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.005087996987125369}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.004015109732356251}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.08804254740266625}, {"slug": "scicode", "weightedCostPerTask": 0.0003921402916666667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0020000853188137167}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0009157781100000002}, {"slug": "critpt", "weightedCostPerTask": 0.005694519114285715}, {"slug": "omniscience", "weightedCostPerTask": 0.00029126098874999995}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.000714360695}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2923254382, "output": 250012040, "answer": 21262038, "reasoning": 228750002}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 40555.079938171075, "answer": 14593.143150139522, "output": 55148.223088310595}, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 833.07, "lower95ci": 826.74, "upper95ci": 839.45}, "rubricPassRate": 0.18680203045685279, "analyticalQuality": {"elo": 755.39, "lower95ci": 742.97, "upper95ci": 767.07}, "presentation": {"elo": 878.69, "lower95ci": 866.29, "upper95ci": 890.37}}, "briefcaseTotalCost": 6.546300623135419, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 5, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d925845d-39ad-4de3-8495-f176b79828c0", "slug": "claude-3-7-sonnet", "name": "Claude 3.7 Sonnet (Non-reasoning)", "shortName": "Claude 3.7 Sonnet (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-24", "knowledgeCutoffDate": "2024-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-3-7-sonnet", "name": "Claude 3.7 Sonnet"}, "deprecated": true, "deprecatedTo": "claude-4-sonnet", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 15.2705782730385, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -9.71666666666667, "omniscienceBreakdown": {"accuracy": 0.282, "hallucinationRate": 0.5280872794800371}, "gdpval": null, "itBenchSre": null, "tau2": 0.5, "tauBanking": null, "terminalbenchHard": 0.212121212121212, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.516666666666667, "ifbench": 0.440136054421769, "hle": 0.0416, "gpqa": 0.655555555555556, "critpt": 0, "apexAgents": null, "mmmuPro": 0.600578034682081, "livecodebench": 0.393650793650794, "aime25": 0.21, "analystAgent": null, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 3.75, "pricePer1k1mpImages": 4, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 2.31, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 0.47058823529411764, "price1mBlended0To100To1": 3.118811881188119, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d93edfe8-bf35-49ad-b56e-b18116142a1c", "slug": "gpt-5-6-sol", "name": "GPT-5.6 Sol (max)", "shortName": "GPT-5.6 Sol (max)", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "gpt-5-6-sol", "name": "GPT-5.6 Sol"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 47.0613568915036, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 49.195616009069006, "strategyAndOps": 54.5136409968153, "legal": 49.9895786557395, "healthcareAndMedical": 45.55304501317306, "engineering": 48.97679594281222, "economics": 53.01603156858202}, "omniscience": 21.9666666666667, "omniscienceBreakdown": {"accuracy": 0.594, "hallucinationRate": 0.9220032840722496}, "mlcrOverall": 0.261111111111111, "harveyLab": 0.871761470545665, "gdpPdfAllPass": 0.272, "gdpval": 1624.11, "gdpvalNormalized": 0.562055, "itBenchSre": 0.562146892655367, "tau2": 0.850877192982456, "tauBanking": 0.443298969072165, "terminalbenchHard": 0.659090909090909, "terminalBench21": 0.880149812734082, "terminalBench40": 0.398989898989899, "scicode": 0.570601851851852, "lcr": 0.84, "ifbench": 0.726530612244898, "hle": 0.494902687673772, "gpqa": 0.941414141414141, "critpt": 0.322857142857143, "apexAgents": null, "mmmuPro": 0.834104046242775, "livecodebench": null, "aime25": null, "analystAgent": 0.475, "automationBenchPartialScore": 0.6008114996276329, "enterpriseOpsGym": 0.42912563413906296, "price1mInputTokens": 4, "price1mOutputTokens": 20, "cacheHitPrice": 0.4, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 8, "price1mBlended7To2To1": 3.08, "price1mBlended0To1To1": 12, "price1mBlended100To1To1": 0.6274509803921569, "price1mBlended0To100To1": 4.158415841584159, "intelligenceIndexTimePerTask": 393.5174805957844, "intelligenceIndexCost": {"total": 3464.843215149396, "input": 1665.2590751493963, "nonCacheInput": 113.0612, "cacheRead": 1039.4640221609222, "cacheWrite": 512.733852988474, "output": 1799.58414, "reasoning": 1452.0295999999998, "answer": 347.55454}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.98845538085375, "input": 1.402267896152844, "nonCacheInput": 0.08606791137271577, "cacheRead": 0.9898341191978236, "cacheWrite": 0.3263658655823049, "output": 0.5861874847009061, "reasoning": 0.34560890027721825, "answer": 0.24057858442368782}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.603039486157021}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.2810069578848972}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.048622738025150714}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.8093173260861856}, {"slug": "scicode", "weightedCostPerTask": 0.007969684722222222}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.026838166821130677}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.092854668}, {"slug": "critpt", "weightedCostPerTask": 0.08591434285714286}, {"slug": "omniscience", "weightedCostPerTask": 0.012811386299999996}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.020080624000000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2729472126, "output": 89979207, "answer": 17377727, "reasoning": 72601480}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 17280.445013860917, "answer": 12028.929221184391, "output": 29309.37423504531}, "briefcaseBreakdown": {"overall": {"elo": 1475, "lower95ci": 1467.79, "upper95ci": 1483.49}, "rubricPassRate": 0.4184839044652129, "analyticalQuality": {"elo": 1536.77, "lower95ci": 1525.14, "upper95ci": 1549.05}, "presentation": {"elo": 1634.77, "lower95ci": 1622.25, "upper95ci": 1647.63}}, "briefcaseTotalCost": 365.8439549352594, "timescaleData": {"medianOutputSpeed": 73.3388606063309, "medianTimeToFirstChunk": 103.504099104}, "outputSpeedVariance": {"p05": 46.5774636415047, "q25": 60.7142210596198, "median": 73.3388606063309, "q75": 84.6762542720845, "p95": 114.349127765956}, "timeToFirstChunkVariance": {"p05": 44.6641173762, "q25": 77.0277246590001, "median": 103.504099104, "q75": 140.01530590275, "p95": 384.1850910099}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 74.4989050409818, "medianTimeToFirstChunk": 71.179518871, "medianTimeToFirstAnswerToken": 71.179518871, "medianEndToEndResponseTime": 77.89102690893627}, "long": {"medianOutputSpeed": 73.3388606063309, "medianTimeToFirstChunk": 103.504099104, "medianTimeToFirstAnswerToken": 103.504099104, "medianEndToEndResponseTime": 110.32176706156353}, "hundredK": {"medianOutputSpeed": 85.7510389985572, "medianTimeToFirstChunk": 49.0562311174999, "medianTimeToFirstAnswerToken": 49.0562311174999, "medianEndToEndResponseTime": 54.887064257707245}, "mediumParallel": {"medianOutputSpeed": 65.2131298967899, "medianTimeToFirstChunk": 279.3848164085, "medianTimeToFirstAnswerToken": 279.3848164085, "medianEndToEndResponseTime": 287.0519840600347}}, "endToEndResponseTime": {"input": 103.504099104, "reasoning": 0, "answer": 6.817667957563525, "total": 110.32176706156353}, "timeToFirstAnswerToken": {"input": 103.504099104, "reasoning": 0, "total": 103.504099104}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 7, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d97713f2-afa6-4f8d-b2f3-ac89a24c4d6c", "slug": "solar-mini", "name": "Solar Mini", "shortName": "Solar Mini", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-01-25", "knowledgeCutoffDate": "2023-11-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "solar-mini", "name": "Solar Mini"}, "deprecated": true, "deprecatedTo": "solar-pro-2-preview", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 10.7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 4096, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/upstage/SOLAR-10.7B-v1.0", "microevalsEnabled": false, "intelligenceIndex": 6.4088294637731, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.201754385964912, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.15, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15, "price1mBlended7To2To1": 0.15, "price1mBlended0To1To1": 0.15, "price1mBlended100To1To1": 0.15, "price1mBlended0To100To1": 0.15, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Upstage"}, "hostModelCount": 1, "creator": {"id": "64ff7f06-c6fb-42ea-ba24-9cd103ab2d61", "slug": "upstage", "name": "Upstage", "logo": "/img/logos/upstage_small.svg", "color": "#7c59f5", "country": "kr", "url": "https://www.upstage.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "d998db47-9b67-4727-a2bb-2e1261020ac0", "slug": "gpt-5-6-sol-xhigh", "name": "GPT-5.6 Sol (xhigh)", "shortName": "GPT-5.6 Sol (xhigh)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-6-sol", "name": "GPT-5.6 Sol"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 44.138026369169, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 47.35517609702749, "strategyAndOps": 52.47850014684089, "legal": 49.12050190210911, "healthcareAndMedical": 42.88139087653333, "engineering": 44.79248443203383, "economics": 51.56823084646278}, "omniscience": 20.9833333333333, "omniscienceBreakdown": {"accuracy": 0.5881666666666666, "hallucinationRate": 0.9186564144071226}, "mlcrOverall": 0.183333333333333, "gdpPdfAllPass": 0.276, "gdpval": 1584.88, "gdpvalNormalized": 0.54244, "itBenchSre": null, "tau2": 0.847953216374269, "tauBanking": 0.381443298969072, "terminalbenchHard": 0.613636363636364, "terminalBench21": 0.895131086142322, "terminalBench40": 0.247474747474747, "scicode": 0.570601851851852, "lcr": 0.823333333333333, "ifbench": 0.710204081632653, "hle": 0.473123262279889, "gpqa": 0.931313131313131, "critpt": 0.285714285714286, "apexAgents": null, "mmmuPro": 0.826589595375723, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5531167269326989, "price1mInputTokens": 4, "price1mOutputTokens": 20, "cacheHitPrice": 0.4, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 8, "price1mBlended7To2To1": 3.08, "price1mBlended0To1To1": 12, "price1mBlended100To1To1": 0.6274509803921569, "price1mBlended0To100To1": 4.158415841584159, "intelligenceIndexTimePerTask": 283.24713642950496, "intelligenceIndexCost": {"total": 2082.284913706361, "input": 1062.3177737063609, "nonCacheInput": 109.447908, "cacheRead": 545.1302329820554, "cacheWrite": 407.7396327243054, "output": 1019.96714, "reasoning": 719.42678, "answer": 300.54036}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.1843629381907275, "input": 0.7928364848325662, "nonCacheInput": 0.08274375790901188, "cacheRead": 0.4548901148928282, "cacheWrite": 0.25520261203072625, "output": 0.3915264533581611, "reasoning": 0.20251853315323862, "answer": 0.1890079202049226}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.4620745541810946}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.17043211598341093}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.04052910420102486}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.3464118966740298}, {"slug": "scicode", "weightedCostPerTask": 0.004489145833333334}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.014209612974976828}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.07820276}, {"slug": "critpt", "weightedCostPerTask": 0.04366673714285714}, {"slug": "omniscience", "weightedCostPerTask": 0.0049681332}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.019378878}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1471735486, "output": 50998357, "answer": 15027018, "reasoning": 35971339}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 10125.92665766193, "answer": 9450.396010246131, "output": 19576.32266790806}, "briefcaseBreakdown": {"overall": {"elo": 1434.68, "lower95ci": 1426.27, "upper95ci": 1443.26}, "rubricPassRate": 0.4131313131313131, "analyticalQuality": {"elo": 1473.38, "lower95ci": 1457.63, "upper95ci": 1489.91}, "presentation": {"elo": 1580.66, "lower95ci": 1563.05, "upper95ci": 1598}}, "briefcaseTotalCost": 280.32522953653074, "timescaleData": {"medianOutputSpeed": 68.3461510920101, "medianTimeToFirstChunk": 29.0436852535001}, "outputSpeedVariance": {"p05": 41.0137684873587, "q25": 51.7743801140751, "median": 68.3461510920101, "q75": 86.6378021539121, "p95": 98.4414998742734}, "timeToFirstChunkVariance": {"p05": 11.8487422547003, "q25": 18.4276935177501, "median": 29.0436852535001, "q75": 56.07144067425, "p95": 198.1908271201}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 68.6220394607843, "medianTimeToFirstChunk": 29.5680381105, "medianTimeToFirstAnswerToken": 29.5680381105, "medianEndToEndResponseTime": 36.854326946111435}, "long": {"medianOutputSpeed": 68.3461510920101, "medianTimeToFirstChunk": 29.0436852535001, "medianTimeToFirstAnswerToken": 29.0436852535001, "medianEndToEndResponseTime": 36.35938616732159}, "hundredK": {"medianOutputSpeed": 85.3352269679388, "medianTimeToFirstChunk": 26.9232137985, "medianTimeToFirstAnswerToken": 26.9232137985, "medianEndToEndResponseTime": 32.78245877581581}, "mediumParallel": {"medianOutputSpeed": 65.9160236968534, "medianTimeToFirstChunk": 100.1528697935, "medianTimeToFirstAnswerToken": 100.1528697935, "medianEndToEndResponseTime": 107.73827880268858}}, "endToEndResponseTime": {"input": 29.0436852535001, "reasoning": 0, "answer": 7.315700913821491, "total": 36.35938616732159}, "timeToFirstAnswerToken": {"input": 29.0436852535001, "reasoning": 0, "total": 29.0436852535001}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "da9fe224-8af3-46d7-a8c4-6220779c3f35", "slug": "qwen3-coder-30b-a3b-instruct", "name": "Qwen3 Coder 30B A3B Instruct", "shortName": "Qwen3 Coder 30B A3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-31", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-coder-30b-a3b-instruct", "name": "Qwen3 Coder 30B A3B Instruct"}, "deprecated": true, "deprecatedTo": "qwen3-coder-next", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30.5, "inferenceParametersActiveBillions": 3.3, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 9.58537639337592, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -50.7333333333333, "omniscienceBreakdown": {"accuracy": 0.164, "hallucinationRate": 0.803030303030303}, "gdpval": null, "itBenchSre": null, "tau2": 0.345029239766082, "tauBanking": null, "terminalbenchHard": 0.151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.326666666666667, "ifbench": 0.326530612244898, "hle": 0.0384615384615385, "gpqa": 0.516161616161616, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.403174603174603, "aime25": 0.29, "analystAgent": null, "price1mInputTokens": 0.45, "price1mOutputTokens": 2.25, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.9, "price1mBlended7To2To1": 0.63, "price1mBlended0To1To1": 1.35, "price1mBlended100To1To1": 0.4676470588235294, "price1mBlended0To100To1": 0.46782178217821785, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 93.1738948233956, "medianTimeToFirstChunk": 2.65246754750007}, "outputSpeedVariance": {"p05": 86.615119283994, "q25": 90.8156546923733, "median": 93.1738948233956, "q75": 97.433728904953, "p95": 103.606872526034}, "timeToFirstChunkVariance": {"p05": 2.33648777395001, "q25": 2.53915899500007, "median": 2.65246754750007, "q75": 2.81185758700009, "p95": 2.96364442619992}, "performanceByPromptType": {"long": {"medianOutputSpeed": 93.1738948233956, "medianTimeToFirstChunk": 2.65246754750007, "medianTimeToFirstAnswerToken": 2.65246754750007, "medianEndToEndResponseTime": 8.018777509616754}}, "endToEndResponseTime": {"input": 2.65246754750007, "reasoning": 0, "answer": 5.366309962116684, "total": 8.018777509616754}, "timeToFirstAnswerToken": {"input": 2.65246754750007, "reasoning": 0, "total": 2.65246754750007}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 4, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "dae31abc-0587-44d0-ba53-f78e96b6e486", "slug": "k2-v2-low", "name": "K2-V2 (low)", "shortName": "K2-V2 (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-05", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "k2-v2", "name": "K2-V2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 512000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/LLM360/K2-V2-Instruct", "microevalsEnabled": false, "intelligenceIndex": 7.31130007284626, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -47.2833333333333, "omniscienceBreakdown": {"accuracy": 0.16333333333333333, "hallucinationRate": 0.7603585657370517}, "gdpval": null, "itBenchSre": null, "tau2": 0.207602339181287, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.203333333333333, "ifbench": 0.40952380952381, "hle": 0.036144578313253, "gpqa": 0.541414141414141, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.392592592592593, "aime25": 0.353333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "8b8b84fb-4b24-45be-b9e2-74ed50d00ff7", "slug": "mbzuai", "name": "MBZUAI Institute of Foundation Models", "logo": "/img/logos/mbzuai_small.svg", "color": "#1521a9", "country": "ae", "url": "https://mbzuai.ac.ae/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "dafbb6d2-4825-43d1-a927-feedcfd2e998", "slug": "granite-4-0-h-nano-1b", "name": "Granite 4.0 H 1B", "shortName": "Granite 4.0 H 1B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "granite-4-0-h-nano-1b", "name": "Granite 4.0 H 1B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1.5, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ibm-granite/granite-4.0-h-1b", "microevalsEnabled": false, "intelligenceIndex": 5.1945517329943, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -72.2666666666667, "omniscienceBreakdown": {"accuracy": 0.052, "hallucinationRate": 0.8171589310829818}, "gdpval": null, "itBenchSre": null, "tau2": 0.195906432748538, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.07, "ifbench": 0.261904761904762, "hle": 0.0500463392029657, "gpqa": 0.262626262626263, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.115343915343915, "aime25": 0.0633333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 55.55555555555556, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "512ef1e4-e02e-4532-a5f2-d11a40962498", "slug": "ibm", "name": "IBM", "logo": "/img/logos/ibm_small.svg", "color": "#0f62fe", "country": "us", "url": "https://www.ibm.com/au-en"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "dbbcf240-a69e-4078-8f16-7c94c7a8c514", "slug": "reka-flash-3", "name": "Reka Flash 3", "shortName": "Reka Flash 3", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "reka-flash-3", "name": "Reka Flash 3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 21, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/RekaAI/reka-flash-3", "modelWeightsSourceUrl": "https://huggingface.co/RekaAI/reka-flash-3", "microevalsEnabled": false, "intelligenceIndex": 5.64602230491152, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -65.1333333333333, "omniscienceBreakdown": {"accuracy": 0.13666666666666666, "hallucinationRate": 0.9127413127413128}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.304081632653061, "hle": 0.0444, "gpqa": 0.529292929292929, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.434920634920635, "aime25": 0.336666666666667, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.35000000000000003, "price1mBlended7To2To1": 0.26000000000000006, "price1mBlended0To1To1": 0.5, "price1mBlended100To1To1": 0.20588235294117646, "price1mBlended0To100To1": 0.20594059405940596, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 86.923890623499, "medianTimeToFirstChunk": 0.91250583499999, "medianTimeToFirstAnswerToken": 23.921140005124446, "medianEndToEndResponseTime": 29.67329854765556}, "mediumParallel": {"medianOutputSpeed": 87.5158088197349, "medianTimeToFirstChunk": 0.935646833000021, "medianTimeToFirstAnswerToken": 23.78866078525179, "medianEndToEndResponseTime": 29.501914273314732}}, "performanceDataSource": {"type": "firstParty", "providerName": "Reka AI"}, "hostModelCount": 1, "creator": {"id": "4571a280-f096-486f-b220-dffc3e522b0f", "slug": "reka-ai", "name": "Reka AI", "logo": "/img/logos/reka_small.svg", "color": "#172136", "country": "us", "url": "http://reka.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "dbe7c625-3100-4463-b479-a228c41f75dd", "slug": "deepseek-v4-1-flash", "name": "DeepSeek V4.1 Flash (Reasoning, Max Effort)", "shortName": "DeepSeek V4.1 Flash (max)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-09-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "deepseek-v4-1-flash", "name": "DeepSeek V4.1 Flash"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 552, "inferenceParametersActiveBillions": 16, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash", "microevalsEnabled": false, "intelligenceIndex": 39.545442472527, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 45.14140759477568, "strategyAndOps": 51.92536333555024, "legal": 41.49090847910638, "engineering": 39.421804394801995, "economics": 44.57588171918442}, "omniscience": -5.3, "omniscienceBreakdown": {"accuracy": 0.464, "hallucinationRate": 0.9645522388059702}, "gdpPdfAllPass": 0.128, "gdpval": 1632.06, "gdpvalNormalized": 0.5660299999999999, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": 0.267676767676768, "scicode": 0.518518518518518, "lcr": 0.84, "ifbench": null, "hle": 0.392493049119555, "gpqa": null, "critpt": 0.142857142857143, "apexAgents": null, "mmmuPro": 0.769942196531792, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.6889097769674057, "price1mInputTokens": 0.3, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.006, "cacheHitDiscountPercent": 0.98, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5249999999999999, "price1mBlended7To2To1": 0.1842, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.020588235294117643, "price1mBlended0To100To1": 0.3089108910891089, "intelligenceIndexTimePerTask": 293.8862434179947, "intelligenceIndexCost": {"total": 476.89044593693893, "input": 173.15417873693895, "nonCacheInput": 5.8523109, "cacheRead": 53.13491481557268, "cacheWrite": 114.16695302136627, "output": 303.7362672, "reasoning": 263.358132, "answer": 40.378135199999996}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.26522527009606844, "input": 0.1589364719024416, "nonCacheInput": 0.003871747133582461, "cacheRead": 0.058423437101084455, "cacheWrite": 0.09664128766777466, "output": 0.10628879819362691, "reasoning": 0.07520347462481308, "answer": 0.0310853235688138}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.08486535889023365}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.030034422856518143}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.008670066648065492}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.11560279303577277}, {"slug": "scicode", "weightedCostPerTask": 0.0012361726041666666}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.004172025430954587}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0040740693}, {"slug": "critpt", "weightedCostPerTask": 0.013483931142857144}, {"slug": "omniscience", "weightedCostPerTask": 0.0014691853874999996}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0016172448}]}, "canonicalIntelligenceIndexTokenCount": {"input": 9255883349, "output": 253113556, "answer": 33648446, "reasoning": 219465110}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 62669.56218734425, "answer": 25904.436307344844, "output": 88573.99849468909}, "briefcaseBreakdown": {"overall": {"elo": 1423.72, "lower95ci": 1414.08, "upper95ci": 1433.7}, "rubricPassRate": 0.45194274028629855, "analyticalQuality": {"elo": 1630.22, "lower95ci": 1614.6, "upper95ci": 1646.26}, "presentation": {"elo": 1335.57, "lower95ci": 1315.86, "upper95ci": 1355.9}}, "briefcaseTotalCost": 51.48498439340842, "timescaleData": {"medianOutputSpeed": 219.798885558096, "medianTimeToFirstChunk": 1.12626271299996}, "outputSpeedVariance": {"p05": 173.634478893567, "q25": 203.566625668807, "median": 219.798885558096, "q75": 240.073495148893, "p95": 254.577540547446}, "timeToFirstChunkVariance": {"p05": 0.914768738400107, "q25": 0.951333296999934, "median": 1.12626271299996, "q75": 1.28853405000004, "p95": 1.77906281650007}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 223.492313054079, "medianTimeToFirstChunk": 0.899526740999988, "medianTimeToFirstAnswerToken": 9.848380384642107, "medianEndToEndResponseTime": 12.085593795552636}, "long": {"medianOutputSpeed": 219.798885558096, "medianTimeToFirstChunk": 1.12626271299996, "medianTimeToFirstAnswerToken": 10.225489922099577, "medianEndToEndResponseTime": 12.500296724374481}, "hundredK": {"medianOutputSpeed": 246.27399831111, "medianTimeToFirstChunk": 2.44936759499997, "medianTimeToFirstAnswerToken": 10.570403570034022, "medianEndToEndResponseTime": 12.600662563792536}, "mediumParallel": {"medianOutputSpeed": 216.09198955487, "medianTimeToFirstChunk": 0.824597834999992, "medianTimeToFirstAnswerToken": 10.07991546208936, "medianEndToEndResponseTime": 12.393744868861702}}, "endToEndResponseTime": {"input": 1.12626271299996, "reasoning": 9.099227209099617, "answer": 2.274806802274904, "total": 12.500296724374481}, "timeToFirstAnswerToken": {"input": 1.12626271299996, "reasoning": 9.099227209099617, "total": 10.225489922099577}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 8, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "dc64f856-3ded-497d-9527-d41d31267ed5", "slug": "gpt-5-6-luna-non-reasoning", "name": "GPT-5.6 Luna (Non-reasoning)", "shortName": "GPT-5.6 Luna (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-09", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-5-6-luna", "name": "GPT-5.6 Luna"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 16.0500252110259, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 16.742052468172048, "strategyAndOps": 15.477031205736665, "legal": 17.55304004802501, "engineering": 18.749759643769888, "economics": 22.114141315261044}, "omniscience": -24.95, "omniscienceBreakdown": {"accuracy": 0.286, "hallucinationRate": 0.75}, "gdpPdfAllPass": 0.06, "gdpval": 987.47, "gdpvalNormalized": 0.243735, "itBenchSre": null, "tau2": null, "tauBanking": 0.0969072164948454, "terminalbenchHard": null, "terminalBench21": 0.389513108614232, "terminalBench40": 0.0101010101010101, "scicode": 0.403935185185185, "lcr": 0.426666666666667, "ifbench": null, "hle": 0.072289156626506, "gpqa": 0.645454545454546, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.603468208092486, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.04970838599882015, "price1mInputTokens": 0.2, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.02, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.25, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.45, "price1mBlended7To2To1": 0.174, "price1mBlended0To1To1": 0.7, "price1mBlended100To1To1": 0.03333333333333334, "price1mBlended0To100To1": 0.2099009900990099, "intelligenceIndexTimePerTask": 19.51996169044787, "intelligenceIndexCost": {"total": 22.965138804039693, "input": 17.148150804039695, "nonCacheInput": 5.5948218, "cacheRead": 5.523543825735678, "cacheWrite": 6.029785178304018, "output": 5.816987999999999, "reasoning": 0, "answer": 5.816987999999999}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.010091821810180262, "input": 0.007658850390116149, "nonCacheInput": 0.004303053286662401, "cacheRead": 0.0013225316336537422, "cacheWrite": 0.0020332654698000056, "output": 0.002432971420064113, "reasoning": 0, "answer": 0.002432971420064113}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.002039561070500442}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0007739248277439582}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0009353886837691701}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.0016423026699583264}, {"slug": "scicode", "weightedCostPerTask": 0.00010406638888888888}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 3.0651093605189994e-05}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0033800128}, {"slug": "critpt", "weightedCostPerTask": 0.00023136628571428572}, {"slug": "omniscience", "weightedCostPerTask": 6.263590000000001e-06}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0009482844000000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 328270441, "output": 4847490, "answer": 4847490, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 2027.4761833867608, "output": 2027.4761833867608}, "briefcaseBreakdown": {"overall": {"elo": 710.24, "lower95ci": 702.19, "upper95ci": 718.57}, "rubricPassRate": 0.12857142857142856, "analyticalQuality": {"elo": 577.37, "lower95ci": 560.91, "upper95ci": 593.5}, "presentation": {"elo": 822.71, "lower95ci": 807.64, "upper95ci": 838.94}}, "briefcaseTotalCost": 1.2373337161036013, "timescaleData": {"medianOutputSpeed": 103.638043996641, "medianTimeToFirstChunk": 0.79298804550001}, "outputSpeedVariance": {"p05": 69.8188090552231, "q25": 91.4926730686841, "median": 103.638043996641, "q75": 125.686842356787, "p95": 135.05859437557}, "timeToFirstChunkVariance": {"p05": 0.673312649900032, "q25": 0.73687053549996, "median": 0.79298804550001, "q75": 0.881510256000098, "p95": 1.55598822594996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 117.722809122008, "medianTimeToFirstChunk": 0.797561362999943, "medianTimeToFirstAnswerToken": 0.797561362999943, "medianEndToEndResponseTime": 5.0448266442913505}, "long": {"medianOutputSpeed": 103.638043996641, "medianTimeToFirstChunk": 0.79298804550001, "medianTimeToFirstAnswerToken": 0.79298804550001, "medianEndToEndResponseTime": 5.617471224825601}, "hundredK": {"medianOutputSpeed": 94.2555458764939, "medianTimeToFirstChunk": 1.46877891149995, "medianTimeToFirstAnswerToken": 1.46877891149995, "medianEndToEndResponseTime": 6.773506557501452}, "mediumParallel": {"medianOutputSpeed": 100.134903951295, "medianTimeToFirstChunk": 0.854458960500097, "medianTimeToFirstAnswerToken": 0.854458960500097, "medianEndToEndResponseTime": 5.847722850214286}}, "endToEndResponseTime": {"input": 0.79298804550001, "reasoning": 0, "answer": 4.824483179325591, "total": 5.617471224825601}, "timeToFirstAnswerToken": {"input": 0.79298804550001, "reasoning": 0, "total": 0.79298804550001}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "dd059b25-d82a-4ead-82a4-4adceaaec48b", "slug": "mistral-medium-3-5", "name": "Mistral Medium 3.5", "shortName": "Mistral Medium 3.5", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-04-29", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "mistral-medium-3-5", "name": "Mistral Medium 3.5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 128, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": "Modified MIT License", "licenseUrl": "https://huggingface.co/mistralai/Mistral-Medium-3.5-128B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-Medium-3.5-128B", "microevalsEnabled": true, "intelligenceIndex": 14.8946727802691, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 15.070822398711472, "strategyAndOps": 13.124537534044611, "legal": 16.915472474491786, "healthcareAndMedical": 14.409866036991213, "engineering": 17.951118634979483, "economics": 21.226593897026646}, "omniscience": -36.8, "omniscienceBreakdown": {"accuracy": 0.24666666666666667, "hallucinationRate": 0.815929203539823}, "mlcrOverall": 0.0166666666666667, "harveyLab": 0.690982776089159, "gdpPdfAllPass": 0.028, "gdpval": 875.14, "gdpvalNormalized": 0.18757, "itBenchSre": null, "tau2": 0.941520467836257, "tauBanking": 0.150515463917526, "terminalbenchHard": 0.333333333333333, "terminalBench21": 0.50561797752809, "terminalBench40": 0, "scicode": 0.40162037037037, "lcr": 0.693333333333333, "ifbench": 0.687755102040816, "hle": 0.137627432808156, "gpqa": 0.748484848484849, "critpt": 0, "apexAgents": null, "mmmuPro": 0.648554913294798, "livecodebench": null, "aime25": null, "analystAgent": 0.125, "automationBenchPartialScore": 0.06299648656993127, "enterpriseOpsGym": 0.3372127723067741, "price1mInputTokens": 1.5, "price1mOutputTokens": 7.5, "cacheHitPrice": 0.15, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 2.11, "price1mBlended0To3To1": 3, "price1mBlended7To2To1": 1.155, "price1mBlended0To1To1": 4.5, "price1mBlended100To1To1": 0.23529411764705882, "price1mBlended0To100To1": 1.5594059405940595, "intelligenceIndexTimePerTask": 167.3748590106601, "intelligenceIndexCost": {"total": 1159.9343362199486, "input": 404.77083371994866, "nonCacheInput": 25.625038500000002, "cacheRead": 200.0654505866724, "cacheWrite": 179.08034463327624, "output": 755.1635024999999, "reasoning": 623.5584524999999, "answer": 131.60504999999998}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.43697278975091847, "input": 0.24133132071112287, "nonCacheInput": 0.01620853681211329, "cacheRead": 0.12533339167458266, "cacheWrite": 0.0997893922244269, "output": 0.19564146903979557, "reasoning": 0.10514817666176263, "answer": 0.09049329237803294}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.10208841992694014}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.035934626523399564}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.022178566465144958}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.17550314332442601}, {"slug": "scicode", "weightedCostPerTask": 0.008166539583333333}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.020226252316960146}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.013852606500000001}, {"slug": "critpt", "weightedCostPerTask": 0.04829877428571429}, {"slug": "omniscience", "weightedCostPerTask": 0.002173011825}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.008550849}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1470239926, "output": 100688467, "answer": 17547340, "reasoning": 83141127}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 14019.756888235019, "answer": 12065.772317071056, "output": 26085.529205306077}, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 5, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 523.63, "lower95ci": 515.55, "upper95ci": 530.83}, "rubricPassRate": 0.12424242424242424, "analyticalQuality": {"elo": 353.89, "lower95ci": 339.11, "upper95ci": 367.53}, "presentation": {"elo": 484.38, "lower95ci": 468.83, "upper95ci": 498.8}}, "briefcaseTotalCost": 61.93364142234368, "timescaleData": {"medianOutputSpeed": 142.153558039118, "medianTimeToFirstChunk": 2.258426305}, "outputSpeedVariance": {"p05": 90.9401695336397, "q25": 111.321504308928, "median": 142.153558039118, "q75": 166.269037312542, "p95": 186.307566193656}, "timeToFirstChunkVariance": {"p05": 2.13921782200001, "q25": 2.1845899407499, "median": 2.258426305, "q75": 2.64788267025003, "p95": 6.10981099180004}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 152.408989074631, "medianTimeToFirstChunk": 0.700305401999998, "medianTimeToFirstAnswerToken": 13.822890966954098, "medianEndToEndResponseTime": 17.103537358192625}, "long": {"medianOutputSpeed": 142.153558039118, "medianTimeToFirstChunk": 2.258426305, "medianTimeToFirstAnswerToken": 16.32771888964032, "medianEndToEndResponseTime": 19.8450420358004}, "hundredK": {"medianOutputSpeed": 145.344655740418, "medianTimeToFirstChunk": 34.5261455495, "medianTimeToFirstAnswerToken": 48.28654141552999, "medianEndToEndResponseTime": 51.72664038203749}, "mediumParallel": {"medianOutputSpeed": 136.043346587074, "medianTimeToFirstChunk": 0.767204402999994, "medianTimeToFirstAnswerToken": 15.46840111841531, "medianEndToEndResponseTime": 19.143700297269138}}, "endToEndResponseTime": {"input": 2.258426305, "reasoning": 14.06929258464032, "answer": 3.51732314616008, "total": 19.8450420358004}, "timeToFirstAnswerToken": {"input": 2.258426305, "reasoning": 14.06929258464032, "total": 16.32771888964032}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 2, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "dd738be7-2b69-4775-91a5-8851d3341c2d", "slug": "k2-v2-medium", "name": "K2-V2 (medium)", "shortName": "K2-V2 (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-05", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "k2-v2", "name": "K2-V2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 70, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 512000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/LLM360/K2-V2-Instruct", "microevalsEnabled": false, "intelligenceIndex": 9.01595166538807, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -49, "omniscienceBreakdown": {"accuracy": 0.17933333333333334, "hallucinationRate": 0.8155970755483347}, "gdpval": null, "itBenchSre": null, "tau2": 0.248538011695906, "tauBanking": null, "terminalbenchHard": 0.0833333333333333, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.28, "ifbench": 0.551020408163265, "hle": 0.0435588507877665, "gpqa": 0.597979797979798, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.540740740740741, "aime25": 0.646666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "8b8b84fb-4b24-45be-b9e2-74ed50d00ff7", "slug": "mbzuai", "name": "MBZUAI Institute of Foundation Models", "logo": "/img/logos/mbzuai_small.svg", "color": "#1521a9", "country": "ae", "url": "https://mbzuai.ac.ae/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ddc748d0-6a9b-466b-8d6c-68417980d56d", "slug": "claude-2", "name": "Claude 2.0", "shortName": "Claude 2.0", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-07-11", "knowledgeCutoffDate": "2023-01-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-2", "name": "Claude 2.0"}, "deprecated": true, "deprecatedTo": "claude-21", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 100000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 5.50606445861584, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": 0.344444444444444, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.171428571428571, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ddfdaf64-3f8e-40a6-a492-608ee83a1351", "slug": "gemini-3-7-flash-low", "name": "Gemini 3.7 Flash (low)", "shortName": "Gemini 3.7 Flash (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-13", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gemini-3-7-flash", "name": "Gemini 3.7 Flash"}, "deprecated": true, "deprecatedTo": "gemini-3-8-flash-low", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 36.9459114891198, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 22.1333333333333, "omniscienceBreakdown": {"accuracy": 0.5356666666666666, "hallucinationRate": 0.6769562096195262}, "gdpval": 1354.06, "gdpvalNormalized": 0.42702999999999997, "itBenchSre": null, "tau2": null, "tauBanking": 0.294845360824742, "terminalbenchHard": null, "terminalBench21": 0.797752808988764, "terminalBench40": null, "scicode": 0.556712962962963, "lcr": 0.786666666666667, "ifbench": null, "hle": 0.351251158480074, "gpqa": 0.901010101010101, "critpt": 0.0571428571428571, "apexAgents": null, "mmmuPro": 0.848554913294798, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.75, "price1mOutputTokens": 3.75, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.75, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5, "price1mBlended7To2To1": 0.5775, "price1mBlended0To1To1": 2.25, "price1mBlended100To1To1": 0.11764705882352941, "price1mBlended0To100To1": 0.7797029702970297, "timescaleData": {"medianOutputSpeed": 297.664071865269, "medianTimeToFirstChunk": 0.843149980000021}, "outputSpeedVariance": {"p05": 214.92137477478, "q25": 254.907365936338, "median": 297.664071865269, "q75": 347.598585103057, "p95": 412.667766422077}, "timeToFirstChunkVariance": {"p05": 0.685055189599985, "q25": 0.727279648499983, "median": 0.843149980000021, "q75": 1.41727111225003, "p95": 4.11837945984999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 306.191736789845, "medianTimeToFirstChunk": 0.758282158999918, "medianTimeToFirstAnswerToken": 0.758282158999918, "medianEndToEndResponseTime": 2.391245887028854}, "long": {"medianOutputSpeed": 297.664071865269, "medianTimeToFirstChunk": 0.843149980000021, "medianTimeToFirstAnswerToken": 0.843149980000021, "medianEndToEndResponseTime": 2.522895865577753}, "hundredK": {"medianOutputSpeed": 270.261196710066, "medianTimeToFirstChunk": 1.394279375, "medianTimeToFirstAnswerToken": 1.394279375, "medianEndToEndResponseTime": 3.244341485604786}, "mediumParallel": {"medianOutputSpeed": 262.838847771741, "medianTimeToFirstChunk": 0.736401271000034, "medianTimeToFirstAnswerToken": 0.736401271000034, "medianEndToEndResponseTime": 2.63870758621497}}, "endToEndResponseTime": {"input": 0.843149980000021, "reasoning": 0, "answer": 1.679745885577732, "total": 2.522895865577753}, "timeToFirstAnswerToken": {"input": 0.843149980000021, "reasoning": 0, "total": 0.843149980000021}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "de0beaf0-c951-487a-8eb4-3dd12e74122c", "slug": "pixtral-large-2411", "name": "Pixtral Large", "shortName": "Pixtral Large", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-11-18", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "pixtral-large-2411", "name": "Pixtral Large"}, "deprecated": true, "deprecatedTo": "mistral-medium-3-1", "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 124, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "Mistral Research License", "licenseUrl": "https://mistral.ai/licenses/MRL-0.1.md", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Pixtral-Large-Instruct-2411", "microevalsEnabled": false, "intelligenceIndex": 7.14734063408637, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.365497076023392, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.344897959183673, "hle": 0.028, "gpqa": 0.505050505050505, "critpt": null, "apexAgents": null, "mmmuPro": 0.505780346820809, "livecodebench": 0.261375661375661, "aime25": 0.0233333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "dec8073c-57e2-41c0-b1aa-7a62960f103f", "slug": "qwen3-vl-8b-reasoning", "name": "Qwen3 VL 8B (Reasoning)", "shortName": "Qwen3 VL 8B (Reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-14", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-vl-8b", "name": "Qwen3 VL 8B (Reasoning)"}, "deprecated": true, "deprecatedTo": "qwen3-5-9b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 8.77, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-VL-8B-Thinking", "microevalsEnabled": false, "intelligenceIndex": 8.17229749994459, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -52.3, "omniscienceBreakdown": {"accuracy": 0.20433333333333334, "hallucinationRate": 0.9141181399245916}, "gdpval": null, "itBenchSre": null, "tau2": 0.225146198830409, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.333333333333333, "ifbench": 0.398639455782313, "hle": 0.0384615384615385, "gpqa": 0.578787878787879, "critpt": 0.00285714285714286, "apexAgents": null, "mmmuPro": 0.566473988439306, "livecodebench": 0.353439153439153, "aime25": 0.306666666666667, "analystAgent": null, "price1mInputTokens": 0.18, "price1mOutputTokens": 2.1, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.184, "price1mBlended0To3To1": 0.66, "price1mBlended7To2To1": 0.372, "price1mBlended0To1To1": 1.1400000000000001, "price1mBlended100To1To1": 0.1988235294117647, "price1mBlended0To100To1": 0.19900990099009902, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 111.554826565842, "medianTimeToFirstChunk": 2.31517905650003}, "outputSpeedVariance": {"p05": 93.3077503280346, "q25": 100.443590845069, "median": 111.554826565842, "q75": 116.095334349068, "p95": 118.394982715597}, "timeToFirstChunkVariance": {"p05": 2.22245047329999, "q25": 2.27873265650004, "median": 2.31517905650003, "q75": 2.4600113715, "p95": 2.96656717525001}, "performanceByPromptType": {"long": {"medianOutputSpeed": 111.554826565842, "medianTimeToFirstChunk": 2.31517905650003, "medianTimeToFirstAnswerToken": 20.24358306705674, "medianEndToEndResponseTime": 24.725684069695916}}, "endToEndResponseTime": {"input": 2.31517905650003, "reasoning": 17.928404010556708, "answer": 4.482101002639177, "total": 24.725684069695916}, "timeToFirstAnswerToken": {"input": 2.31517905650003, "reasoning": 17.928404010556708, "total": 20.24358306705674}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ded8d96e-835f-4359-947a-a4c3bb78e983", "slug": "phi-3-mini", "name": "Phi-3 Mini Instruct 3.8B", "shortName": "Phi-3 Mini", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-04-23", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "phi-3-mini", "name": "Phi-3 Mini Instruct 3.8B"}, "deprecated": true, "deprecatedTo": "phi-4-mini", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3.8, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 4096, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct", "microevalsEnabled": false, "intelligenceIndex": 5.82401211090128, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.238775510204082, "hle": 0.0496, "gpqa": 0.319191919191919, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.116402116402116, "aime25": 0.00333333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "ef5ce458-9986-4652-915a-e31fac5506b0", "slug": "azure", "name": "Microsoft", "logo": "/img/logos/microsoft_small.svg", "color": "#0078D5", "country": "us", "url": "https://azure.microsoft.com/en-us"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "df4c5a29-4b5c-4fef-9f7f-5e24e118ab65", "slug": "mi-dm-k-2-5-pro-dec28", "name": "Mi:dm K 2.5 Pro", "shortName": "Mi:dm K 2.5 Pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "mi-dm-k-2-5-pro-dec28", "name": "Mi:dm K 2.5 Pro"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 32, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 11.0361387091137, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -59.1833333333333, "omniscienceBreakdown": {"accuracy": 0.17883333333333334, "hallucinationRate": 0.9385021311142683}, "gdpval": null, "itBenchSre": null, "tau2": 0.865497076023392, "tauBanking": null, "terminalbenchHard": 0.0227272727272727, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.09, "ifbench": 0.493197278911565, "hle": 0.0806302131603336, "gpqa": 0.701010101010101, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.656084656084656, "aime25": 0.766666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d5913d27-143c-48be-96b0-8d534047cb5c", "slug": "korea-telecom", "name": "Korea Telecom", "logo": "/img/logos/korea-telecom_small.png", "color": "black", "country": "kr", "url": "https://corp.kt.com/eng/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "df8d14e0-3997-4e4d-b4ad-9c047acc9c69", "slug": "claude-sonnet-4-6-adaptive", "name": "Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)", "shortName": "Claude Sonnet 4.6 (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-17", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "claude-sonnet-4-6", "name": "Claude Sonnet 4.6"}, "deprecated": true, "deprecatedTo": "claude-sonnet-5", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 30.4529361117644, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 34.069218322413406, "strategyAndOps": 30.956580253943788, "legal": 37.69879565433647, "healthcareAndMedical": 31.70005648872874, "engineering": 31.77352915011431, "economics": 42.8544712923271}, "omniscience": 12.2166666666667, "omniscienceBreakdown": {"accuracy": 0.4086666666666667, "hallucinationRate": 0.48449830890642615}, "mlcrOverall": 0.244444444444444, "harveyLab": 0.859748154580981, "gdpPdfAllPass": 0.158, "gdpval": 1295.41, "gdpvalNormalized": 0.39770500000000003, "itBenchSre": 0.398022598870057, "tau2": 0.757309941520468, "tauBanking": 0.344329896907216, "terminalbenchHard": 0.53030303030303, "terminalBench21": 0.711610486891386, "terminalBench40": 0.0303030303030303, "scicode": 0.501157407407407, "lcr": 0.8, "ifbench": 0.565986394557823, "hle": 0.33595922150139, "gpqa": 0.874747474747475, "critpt": 0.0314285714285714, "apexAgents": 0.28023598820059, "mmmuPro": 0.732947976878613, "livecodebench": null, "aime25": null, "analystAgent": 0.2, "automationBenchPartialScore": 0.20098073664518368, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 3.75, "pricePer1k1mpImages": 4, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 2.31, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 0.47058823529411764, "price1mBlended0To100To1": 3.118811881188119, "intelligenceIndexTimePerTask": 1220.0372903933358, "intelligenceIndexCost": {"total": 4924.798685114723, "input": 1436.115245114724, "nonCacheInput": 71.362716, "cacheRead": 879.494471490024, "cacheWrite": 485.2580576247, "output": 3488.68344, "reasoning": 3036.28071, "answer": 452.40272999999996}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.4858655963942224, "input": 1.362104484669172, "nonCacheInput": 0.04949527408476984, "cacheRead": 0.9678192221737382, "cacheWrite": 0.34478998841066416, "output": 1.1237611117250506, "reasoning": 0.8431464688922031, "answer": 0.2806146428328475}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.361927256731525}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.19373623019893466}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.05915981322741919}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.3280966734115978}, {"slug": "scicode", "weightedCostPerTask": 0.015019713541666667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.09146132544022244}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.060612000000000006}, {"slug": "critpt", "weightedCostPerTask": 0.3499978971428571}, {"slug": "omniscience", "weightedCostPerTask": 0.0065998407}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.019254846}]}, "canonicalIntelligenceIndexTokenCount": {"input": 3084837959, "output": 232578896, "answer": 30160182, "reasoning": 202418714}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 56209.76459281355, "answer": 18707.64285552317, "output": 74917.40744833671}, "briefcaseBreakdown": {"overall": {"elo": 1065.11, "lower95ci": 1059.48, "upper95ci": 1071}, "rubricPassRate": 0.289198606271777, "analyticalQuality": {"elo": 983.57, "lower95ci": 971.99, "upper95ci": 993.76}, "presentation": {"elo": 1177.46, "lower95ci": 1167.07, "upper95ci": 1188.88}}, "briefcaseTotalCost": 219.56920241712515, "timescaleData": {"medianOutputSpeed": 46.2957807305678, "medianTimeToFirstChunk": 81.915188999}, "outputSpeedVariance": {"p05": 40.3638458106342, "q25": 41.7724838764102, "median": 46.2957807305678, "q75": 61.4131937755592, "p95": 77.1406040665667}, "timeToFirstChunkVariance": {"p05": 34.9710271564, "q25": 65.04405954, "median": 81.915188999, "q75": 151.714607023, "p95": 507.3007922816}, "performanceByPromptType": {"long": {"medianOutputSpeed": 46.2957807305678, "medianTimeToFirstChunk": 81.915188999, "medianTimeToFirstAnswerToken": 81.915188999, "medianEndToEndResponseTime": 92.71530927151252}}, "endToEndResponseTime": {"input": 81.915188999, "reasoning": 0, "answer": 10.800120272512524, "total": 92.71530927151252}, "timeToFirstAnswerToken": {"input": 81.915188999, "reasoning": 0, "total": 81.915188999}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "df95f83f-5ebb-466a-9d2d-b95efc8c012c", "slug": "deepseek-r1-distill-qwen-32b", "name": "DeepSeek R1 Distill Qwen 32B", "shortName": "DeepSeek R1 Distill Qwen 32B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-20", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "deepseek-r1-distill-qwen-32b", "name": "DeepSeek R1 Distill Qwen 32B"}, "deprecated": true, "deprecatedTo": "deepseek-v3-0324", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 32, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 128000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "microevalsEnabled": false, "intelligenceIndex": 8.37720334584862, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.0866666666666667, "ifbench": 0.229251700680272, "hle": 0.0458, "gpqa": 0.615151515151515, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.26984126984127, "aime25": 0.63, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "dfb9292d-bc7c-4425-a260-4256217e709f", "slug": "deepseek-v3-1-terminus", "name": "DeepSeek V3.1 Terminus (Non-reasoning)", "shortName": "DeepSeek V3.1 Terminus (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-09-22", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v3-1-terminus", "name": "DeepSeek V3.1 Terminus"}, "deprecated": true, "deprecatedTo": "deepseek-v3-2", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus", "microevalsEnabled": false, "intelligenceIndex": 13.930676595341, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -43.4666666666667, "omniscienceBreakdown": {"accuracy": 0.23516666666666666, "hallucinationRate": 0.8757899324471562}, "gdpval": null, "itBenchSre": null, "tau2": 0.371345029239766, "tauBanking": null, "terminalbenchHard": 0.318181818181818, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.453333333333333, "ifbench": 0.412244897959184, "hle": 0.0866543095458758, "gpqa": 0.750505050505051, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.529100529100529, "aime25": 0.536666666666667, "analystAgent": null, "price1mInputTokens": 0.27, "price1mOutputTokens": 1, "cacheHitPrice": 0.27, "cacheHitDiscountPercent": 0.5185185185185186, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.4525, "price1mBlended7To2To1": 0.343, "price1mBlended0To1To1": 0.635, "price1mBlended100To1To1": 0.27715686274509804, "price1mBlended0To100To1": 0.27722772277227725, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 3, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "dfeeb904-e784-4d5c-ad66-9400146b150b", "slug": "gemini-2-0-flash-thinking-exp-1219", "name": "Gemini 2.0 Flash Thinking Experimental (Dec '24)", "shortName": "Gemini 2.0 Flash Thinking exp. (Dec)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-19", "knowledgeCutoffDate": "2024-08-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-2-0-flash-thinking-exp-1219", "name": "Gemini 2.0 Flash Thinking Experimental (Dec '24)"}, "deprecated": true, "deprecatedTo": "gemini-2-0-flash-thinking-exp-0121", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 2000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 6.55531350618149, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e0099b99-d368-4562-b0de-4016ea58af54", "slug": "midm-250-pro-rsnsft", "name": "Mi:dm K 2.5 Pro Preview", "shortName": "Mi:dm K 2.5 Pro Preview", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-12-11", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "midm-250-pro-rsnsft", "name": "Mi:dm K 2.5 Pro Preview"}, "deprecated": true, "deprecatedTo": "mi-dm-k-2-5-pro-dec28", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": null, "intelligenceIndexIsEstimated": false, "capabilities": {}, "omniscience": -62.7333333333333, "omniscienceBreakdown": {"accuracy": 0.16416666666666666, "hallucinationRate": 0.9469591226321037}, "gdpval": null, "itBenchSre": null, "tau2": 0.494152046783626, "tauBanking": null, "terminalbenchHard": 0.0303030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.146666666666667, "ifbench": 0.45578231292517, "hle": 0.0908248378127896, "gpqa": 0.722222222222222, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.575661375661376, "aime25": 0.786666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d5913d27-143c-48be-96b0-8d534047cb5c", "slug": "korea-telecom", "name": "Korea Telecom", "logo": "/img/logos/korea-telecom_small.png", "color": "black", "country": "kr", "url": "https://corp.kt.com/eng/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e05a4828-0536-4876-870d-a235023f992b", "slug": "gpt-6-astra-high", "name": "GPT-6 Astra (high)", "shortName": "GPT-6 Astra (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-03", "knowledgeCutoffDate": "2026-04-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-6-astra", "name": "GPT-6 Astra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 51.0480721636152, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 53.46002119455936, "strategyAndOps": 55.767607339732606, "legal": 58.11627840084444, "engineering": 53.13874014399256, "economics": 58.632748088507874}, "omniscience": 43.7333333333333, "omniscienceBreakdown": {"accuracy": 0.6113333333333333, "hallucinationRate": 0.44768439108061747}, "gdpPdfAllPass": 0.31, "gdpval": 1529.7, "gdpvalNormalized": 0.51485, "itBenchSre": null, "tau2": null, "tauBanking": 0.4, "terminalbenchHard": null, "terminalBench21": 0.898876404494382, "terminalBench40": 0.54040404040404, "scicode": 0.554398148148148, "lcr": 0.8, "ifbench": null, "hle": 0.530583873957368, "gpqa": 0.94949494949495, "critpt": 0.288571428571429, "apexAgents": null, "mmmuPro": 0.864161849710983, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.666122174975011, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 1, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 12.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.7, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 1.5686274509803921, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 225.2132502270858, "intelligenceIndexCost": {"total": 2916.6070288352003, "input": 1607.2251788352003, "nonCacheInput": 280.98856, "cacheRead": 656.1626951012869, "cacheWrite": 670.0739237339134, "output": 1309.3818500000002, "reasoning": 701.0664, "answer": 608.31545}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.7214332536034334, "input": 1.1316902764026926, "nonCacheInput": 0.21694027018629464, "cacheRead": 0.5018655420565792, "cacheWrite": 0.4128844641598186, "output": 0.5897429772007414, "reasoning": 0.2353828194960955, "answer": 0.3543601577046459}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.7145288690796738}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.23939998401256243}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.06475923848785373}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.40469926217499436}, {"slug": "scicode", "weightedCostPerTask": 0.006957760416666668}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.016184757645968488}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.17948240999999998}, {"slug": "critpt", "weightedCostPerTask": 0.04335251428571428}, {"slug": "omniscience", "weightedCostPerTask": 0.0040825474999999995}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.04798591000000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 737867465, "output": 26187637, "answer": 12166309, "reasoning": 14021328}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 4707.65638992191, "answer": 7087.203154092917, "output": 11794.859544014827}, "briefcaseBreakdown": {"overall": {"elo": 1493.87, "lower95ci": 1485.18, "upper95ci": 1504.23}, "rubricPassRate": 0.5080808080808081, "analyticalQuality": {"elo": 1670.47, "lower95ci": 1654.52, "upper95ci": 1687.23}, "presentation": {"elo": 1438.35, "lower95ci": 1421.43, "upper95ci": 1454.19}}, "briefcaseTotalCost": 433.4808472416688, "timescaleData": {"medianOutputSpeed": 51.9487729533075, "medianTimeToFirstChunk": 37.2229942935001}, "outputSpeedVariance": {"p05": 43.1799925602833, "q25": 45.823011155124, "median": 51.9487729533075, "q75": 61.7143188976684, "p95": 67.4343325459197}, "timeToFirstChunkVariance": {"p05": 13.1190844643, "q25": 27.50683446825, "median": 37.2229942935001, "q75": 71.6603588215, "p95": 167.15638317405}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 51.7025774025851, "medianTimeToFirstChunk": 33.2189521025, "medianTimeToFirstAnswerToken": 33.2189521025, "medianEndToEndResponseTime": 42.889649872685055}, "long": {"medianOutputSpeed": 51.9487729533075, "medianTimeToFirstChunk": 37.2229942935001, "medianTimeToFirstAnswerToken": 37.2229942935001, "medianEndToEndResponseTime": 46.84786070659919}, "hundredK": {"medianOutputSpeed": 55.892270032137, "medianTimeToFirstChunk": 32.048179217, "medianTimeToFirstAnswerToken": 32.048179217, "medianEndToEndResponseTime": 40.993960086385144}, "mediumParallel": {"medianOutputSpeed": 54.161488181558, "medianTimeToFirstChunk": 52.264170467, "medianTimeToFirstAnswerToken": 52.264170467, "medianEndToEndResponseTime": 61.4958222695487}}, "endToEndResponseTime": {"input": 37.2229942935001, "reasoning": 0, "answer": 9.624866413099095, "total": 46.84786070659919}, "timeToFirstAnswerToken": {"input": 37.2229942935001, "reasoning": 0, "total": 37.2229942935001}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e18e5e6a-5a31-4c0b-b80b-ac401392f446", "slug": "gpt-5-nano", "name": "GPT-5 nano (high)", "shortName": "GPT-5 nano (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-05-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5-nano", "name": "GPT-5 nano"}, "deprecated": true, "deprecatedTo": "gpt-5-4-nano", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.992236382483, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -28.6666666666667, "omniscienceBreakdown": {"accuracy": 0.19083333333333333, "hallucinationRate": 0.5901132852729145}, "gdpval": null, "itBenchSre": null, "tau2": 0.365497076023392, "tauBanking": null, "terminalbenchHard": 0.121212121212121, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.45, "ifbench": 0.675510204081633, "hle": 0.0949953660797034, "gpqa": 0.675757575757576, "critpt": 0, "apexAgents": null, "mmmuPro": 0.609826589595376, "livecodebench": 0.789417989417989, "aime25": 0.836666666666667, "analystAgent": null, "price1mInputTokens": 0.05, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.005, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.13, "price1mBlended0To3To1": 0.1375, "price1mBlended7To2To1": 0.053500000000000006, "price1mBlended0To1To1": 0.225, "price1mBlended100To1To1": 0.009313725490196078, "price1mBlended0To100To1": 0.05346534653465347, "openness": {"opennessIndex": 5.555555555555555, "modelAvailability": 1, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 162.743189626185, "medianTimeToFirstChunk": 102.1775980735}, "outputSpeedVariance": {"p05": 119.139246580882, "q25": 142.731932100329, "median": 162.743189626185, "q75": 199.180356433997, "p95": 217.608072790106}, "timeToFirstChunkVariance": {"p05": 33.41412567085, "q25": 71.4061760095, "median": 102.1775980735, "q75": 139.328078216, "p95": 169.85576999175}, "performanceByPromptType": {"long": {"medianOutputSpeed": 162.743189626185, "medianTimeToFirstChunk": 102.1775980735, "medianTimeToFirstAnswerToken": 102.1775980735, "medianEndToEndResponseTime": 105.24992325742002}}, "endToEndResponseTime": {"input": 102.1775980735, "reasoning": 0, "answer": 3.072325183920023, "total": 105.24992325742002}, "timeToFirstAnswerToken": {"input": 102.1775980735, "reasoning": 0, "total": 102.1775980735}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e1bfc488-5f48-4d42-abf6-7f3c53d79f9c", "slug": "lfm2-5-2-6b", "name": "LFM2.5-2.6B", "shortName": "LFM2.5-2.6B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-04", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "lfm2-5-2-6b", "name": "LFM2.5-2.6B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 2.7, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 128000, "licenseName": "lfm 1.0", "licenseUrl": "https://huggingface.co/LiquidAI/LFM2-2.6B-Exp/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LiquidAI/LFM2.5-2.6B", "microevalsEnabled": false, "intelligenceIndex": 8.38708534765242, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -10.95, "omniscienceBreakdown": {"accuracy": 0.0435, "hallucinationRate": 0.159958180867747}, "gdpval": 202.35, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": null, "tauBanking": 0.0721649484536082, "terminalbenchHard": null, "terminalBench21": 0.0449438202247191, "terminalBench40": null, "scicode": 0.143518518518519, "lcr": 0.0566666666666667, "ifbench": null, "hle": 0.06209453197405, "gpqa": 0.557575757575758, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 5, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Liquid AI"}, "hostModelCount": 1, "creator": {"id": "5b1886c4-43ba-4007-b840-9d21a2b7d42c", "slug": "liquidai", "name": "Liquid AI", "logo": "/img/logos/liquidai_small.svg", "color": "#000000", "country": "us", "url": "https://www.liquid.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e1cfa926-9e2b-4a0d-8c31-48366a5041c5", "slug": "llama-nemotron-super-49b-v1-5-reasoning", "name": "Llama Nemotron Super 49B v1.5 (Reasoning)", "shortName": "Llama Nemotron Super 49B v1.5", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-25", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "llama-nemotron-super-49b-v1-5", "name": "Llama Nemotron Super 49B v1.5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 49, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 128000, "licenseName": "NVIDIA Open Model License Agreement", "licenseUrl": "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", "microevalsEnabled": true, "intelligenceIndex": 9.01435430969758, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -47.6, "omniscienceBreakdown": {"accuracy": 0.17166666666666666, "hallucinationRate": 0.7818913480885312}, "gdpval": null, "itBenchSre": null, "tau2": 0.280701754385965, "tauBanking": null, "terminalbenchHard": 0.053030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": 0.370068027210884, "hle": 0.0732159406858202, "gpqa": 0.748484848484849, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.736507936507937, "aime25": 0.766666666666667, "analystAgent": null, "price1mInputTokens": 0.4, "price1mOutputTokens": 0.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.4, "price1mBlended7To2To1": 0.4000000000000001, "price1mBlended0To1To1": 0.4, "price1mBlended100To1To1": 0.39999999999999997, "price1mBlended0To100To1": 0.39999999999999997, "openness": {"opennessIndex": 52.77777777777778, "modelAvailability": 4, "transparencyMethodology": 4, "transparencyPostTrainingData": 1, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 46.1931417382663, "medianTimeToFirstChunk": 9.28985072200021}, "outputSpeedVariance": {"p05": 15.8887257709623, "q25": 25.6244802600735, "median": 46.1931417382663, "q75": 77.8231060462814, "p95": 163.094799638087}, "timeToFirstChunkVariance": {"p05": 2.69075634399996, "q25": 4.61900566199995, "median": 9.28985072200021, "q75": 11.97603665, "p95": 30.783082468}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 46.2589521212435, "medianTimeToFirstChunk": 7.57244074, "medianTimeToFirstAnswerToken": 50.80731546777274, "medianEndToEndResponseTime": 61.61603414971592}, "long": {"medianOutputSpeed": 46.1931417382663, "medianTimeToFirstChunk": 9.28985072200021, "medianTimeToFirstAnswerToken": 52.58632125288866, "medianEndToEndResponseTime": 63.41043888561077}, "hundredK": {"medianOutputSpeed": 68.1684059018139, "medianTimeToFirstChunk": 22.209403281, "medianTimeToFirstAnswerToken": 51.54850801055305, "medianEndToEndResponseTime": 58.88328419294131}, "mediumParallel": {"medianOutputSpeed": 74.6720164783597, "medianTimeToFirstChunk": 6.95276404600008, "medianTimeToFirstAnswerToken": 33.73655929250464, "medianEndToEndResponseTime": 40.432508104130775}}, "endToEndResponseTime": {"input": 9.28985072200021, "reasoning": 43.29647053088845, "answer": 10.824117632722112, "total": 63.41043888561077}, "timeToFirstAnswerToken": {"input": 9.28985072200021, "reasoning": 43.29647053088845, "total": 52.58632125288866}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e2b664ca-7992-4de6-8839-4867f035c892", "slug": "lfm2-5-8b-a1b", "name": "LFM2.5-8B-A1B", "shortName": "LFM2.5-8B-A1B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-28", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "lfm2-5-8b-a1b", "name": "LFM2.5-8B-A1B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 8.3, "inferenceParametersActiveBillions": 1.5, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "lfm 1.0", "licenseUrl": "https://huggingface.co/LiquidAI/LFM2-8B-A1B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LiquidAI/LFM2.5-8B-A1B", "microevalsEnabled": false, "intelligenceIndex": 7.21643567343487, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -33.2, "omniscienceBreakdown": {"accuracy": 0.09333333333333334, "hallucinationRate": 0.46911764705882353}, "gdpval": null, "itBenchSre": null, "tau2": 0.160818713450292, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.556462585034014, "hle": 0.0685820203892493, "gpqa": 0.513131313131313, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "openness": {"opennessIndex": 33.333333333333336, "modelAvailability": 4, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "5b1886c4-43ba-4007-b840-9d21a2b7d42c", "slug": "liquidai", "name": "Liquid AI", "logo": "/img/logos/liquidai_small.svg", "color": "#000000", "country": "us", "url": "https://www.liquid.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e2e9ddc3-8c2d-4bf5-a60a-83a1afe61034", "slug": "gpt-4o-realtime-dec-2024", "name": "GPT-4o Realtime (Dec '24)", "shortName": "GPT-4o Realtime (Dec)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-17", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4o-realtime-dec-24", "name": "GPT-4o Realtime (Dec '24)"}, "deprecated": true, "deprecatedTo": "gpt-realtime-aug-25", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": null, "intelligenceIndexIsEstimated": false, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": true, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": true, "outputModalityVideo": false}, {"id": "e3396f8f-7994-4df5-bdab-43745681ef0a", "slug": "gpt-5-5-pro", "name": "GPT-5.5 Pro (xhigh)", "shortName": "GPT-5.5 Pro (xhigh)", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2026-04-23", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "gpt-5-5-pro", "name": "GPT-5.5 Pro"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 922000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": null, "intelligenceIndexIsEstimated": false, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": 0.305714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e33dc369-ae81-40e0-8c4e-28b002d02197", "slug": "ling-3-0-flash", "name": "Ling 3.0 Flash", "shortName": "Ling 3.0 Flash", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-04", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "ling-3-0-flash", "name": "Ling 3.0 Flash"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 124, "inferenceParametersActiveBillions": 5.1, "sizeClass": "medium", "contextWindowTokens": 262144, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 20.6349521865481, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 20.33588052270783, "strategyAndOps": 14.346191733258195, "legal": 22.275060782483425, "engineering": 24.20029276446445, "economics": 31.51620395041705}, "omniscience": -17.8833333333333, "omniscienceBreakdown": {"accuracy": 0.18166666666666667, "hallucinationRate": 0.4405295315682281}, "gdpPdfAllPass": 0.054, "gdpval": 1017.28, "gdpvalNormalized": 0.25864, "itBenchSre": null, "tau2": null, "tauBanking": 0.272164948453608, "terminalbenchHard": null, "terminalBench21": 0.554307116104869, "terminalBench40": 0, "scicode": 0.420138888888889, "lcr": 0.73, "ifbench": null, "hle": 0.236793327154773, "gpqa": 0.854545454545454, "critpt": 0.0171428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.03219648917147413, "price1mInputTokens": 0.075, "price1mOutputTokens": 0.22, "cacheHitPrice": 0.015, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.11124999999999999, "price1mBlended7To2To1": 0.0475, "price1mBlended0To1To1": 0.1475, "price1mBlended100To1To1": 0.017598039215686274, "price1mBlended0To100To1": 0.07643564356435643, "intelligenceIndexTimePerTask": 128.27182971446678, "intelligenceIndexCost": {"total": 100.66678012539768, "input": 43.18545622539768, "nonCacheInput": 1.300712925, "cacheRead": 16.883727693650577, "cacheWrite": 25.001015606747103, "output": 57.48132390000001, "reasoning": 49.56612496, "answer": 7.915198940000001}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.03365667359054066, "input": 0.02294333770881802, "nonCacheInput": 0.000752062421397982, "cacheRead": 0.009273311947255305, "cacheWrite": 0.012917963340164727, "output": 0.010713335881722649, "reasoning": 0.007305554727283867, "answer": 0.0034077811544387807}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.0057266424049117574}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.0024367039418151486}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.002282536929645311}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.016512177475583586}, {"slug": "scicode", "weightedCostPerTask": 0.0003688481041666667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.001570696810936052}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00049043027}, {"slug": "critpt", "weightedCostPerTask": 0.0035394471428571435}, {"slug": "omniscience", "weightedCostPerTask": 0.00030413031562499994}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.000425060195}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1476271560, "output": 261278745, "answer": 35978177, "reasoning": 225300568}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 33207.0669421994, "answer": 15489.914338358092, "output": 48696.98128055749}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 802.47, "lower95ci": 794.4, "upper95ci": 809.69}, "rubricPassRate": 0.17373737373737375, "analyticalQuality": {"elo": 678.31, "lower95ci": 662.45, "upper95ci": 695.02}, "presentation": {"elo": 894.91, "lower95ci": 880.24, "upper95ci": 908.64}}, "briefcaseTotalCost": 3.4741630589797996, "timescaleData": {"medianOutputSpeed": 339.440503086787, "medianTimeToFirstChunk": 2.53066013949995}, "outputSpeedVariance": {"p05": 267.771874775427, "q25": 305.827503637598, "median": 339.440503086787, "q75": 366.99161735805, "p95": 449.423160144617}, "timeToFirstChunkVariance": {"p05": 2.13706068795002, "q25": 2.42541335074981, "median": 2.53066013949995, "q75": 2.97676809524995, "p95": 3.36507511779996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 348.446772496426, "medianTimeToFirstChunk": 1.67202992049992, "medianTimeToFirstAnswerToken": 7.411787489987851, "medianEndToEndResponseTime": 8.846726882359834}, "long": {"medianOutputSpeed": 339.440503086787, "medianTimeToFirstChunk": 2.53066013949995, "medianTimeToFirstAnswerToken": 8.422708913327766, "medianEndToEndResponseTime": 9.89572110678472}, "hundredK": {"medianOutputSpeed": 371.400447325026, "medianTimeToFirstChunk": 8.43157578250007, "medianTimeToFirstAnswerToken": 13.81659891428356, "medianEndToEndResponseTime": 15.162854697229431}, "mediumParallel": {"medianOutputSpeed": 330.596025698771, "medianTimeToFirstChunk": 1.64963736649997, "medianTimeToFirstAnswerToken": 7.699316868159615, "medianEndToEndResponseTime": 9.211736743574527}}, "endToEndResponseTime": {"input": 2.53066013949995, "reasoning": 5.892048773827815, "answer": 1.4730121934569538, "total": 9.89572110678472}, "timeToFirstAnswerToken": {"input": 2.53066013949995, "reasoning": 5.892048773827815, "total": 8.422708913327766}, "performanceDataSource": {"type": "firstParty", "providerName": "InclusionAI"}, "hostModelCount": 2, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e34ffffb-d8e1-4f5c-a2c7-3ca19c235eeb", "slug": "gpt-5-5-instant-05-26", "name": "GPT-5.5 Instant (May 2026)", "shortName": "GPT-5.5 Instant (May 2026)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-05", "knowledgeCutoffDate": "2025-08-31", "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "gpt-5-5-instant-05-26", "name": "GPT-5.5 Instant (May 2026)"}, "deprecated": true, "deprecatedTo": "gpt-5-5-instant-06-26", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 22.6863693000789, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 11.15, "omniscienceBreakdown": {"accuracy": 0.4625, "hallucinationRate": 0.6530232558139535}, "gdpval": null, "itBenchSre": null, "tau2": 0.494152046783626, "tauBanking": null, "terminalbenchHard": 0.424242424242424, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.663333333333333, "ifbench": 0.714965986394558, "hle": 0.215940685820204, "gpqa": 0.846464646464646, "critpt": 0.0257142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 5, "price1mOutputTokens": 30, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 11.25, "price1mBlended7To2To1": 4.35, "price1mBlended0To1To1": 17.5, "price1mBlended100To1To1": 0.8333333333333334, "price1mBlended0To100To1": 5.247524752475248, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e410e854-104d-4b35-a171-899ff9d974bb", "slug": "qwen2-5-coder-7b-instruct", "name": "Qwen2.5 Coder Instruct 7B", "shortName": "Qwen2.5 Coder 7B ", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-09-19", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen2-5-coder-7b-instruct", "name": "Qwen2.5 Coder Instruct 7B"}, "deprecated": true, "deprecatedTo": "qwen3-8b-instruct", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 7.62, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 5.78716786538995, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0489, "gpqa": 0.339393939393939, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.125925925925926, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e46198a7-cd29-4afd-933d-cdf180f0f305", "slug": "qwen3-4b-instruct", "name": "Qwen3 4B (Non-reasoning)", "shortName": "Qwen3 4B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-4b-instruct", "name": "Qwen3 4B"}, "deprecated": true, "deprecatedTo": "qwen3-4b-2507-instruct", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 4.02, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 32000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-4B", "microevalsEnabled": false, "intelligenceIndex": 6.61043815916972, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0332, "gpqa": 0.397979797979798, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.232804232804233, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e58bbffd-fdc2-412a-b6d7-ca0e3f5d611a", "slug": "nova-premier", "name": "Nova Premier", "shortName": "Nova Premier", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "nova-premier", "name": "Nova Premier"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 9.15908119897819, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -35.3833333333333, "omniscienceBreakdown": {"accuracy": 0.2125, "hallucinationRate": 0.7191534391534391}, "gdpval": null, "itBenchSre": null, "tau2": 0.383040935672515, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.343333333333333, "ifbench": 0.361904761904762, "hle": 0.0417052826691381, "gpqa": 0.568686868686869, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.317460317460317, "aime25": 0.173333333333333, "analystAgent": null, "price1mInputTokens": 2.5, "price1mOutputTokens": 12.5, "cacheHitPrice": 0.625, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 5, "price1mBlended7To2To1": 2.1875, "price1mBlended0To1To1": 7.5, "price1mBlended100To1To1": 0.7598039215686274, "price1mBlended0To100To1": 2.599009900990099, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 31.0580521568856, "medianTimeToFirstChunk": 2.859272696}, "outputSpeedVariance": {"p05": 20.6469830734599, "q25": 26.2629606941427, "median": 31.0580521568856, "q75": 33.7584658711899, "p95": 35.4156026300678}, "timeToFirstChunkVariance": {"p05": 2.74248177175002, "q25": 2.78614490025012, "median": 2.859272696, "q75": 3.14055569375, "p95": 5.3015811964}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 64.0866716134687, "medianTimeToFirstChunk": 0.982592391499992, "medianTimeToFirstAnswerToken": 0.982592391499992, "medianEndToEndResponseTime": 8.784526669124704}, "long": {"medianOutputSpeed": 31.0580521568856, "medianTimeToFirstChunk": 2.859272696, "medianTimeToFirstAnswerToken": 2.859272696, "medianEndToEndResponseTime": 18.95815737409626}, "hundredK": {"medianOutputSpeed": 31.2075021002744, "medianTimeToFirstChunk": 42.8569291435, "medianTimeToFirstAnswerToken": 42.8569291435, "medianEndToEndResponseTime": 58.878717699130775}, "mediumParallel": {"medianOutputSpeed": 64.039106605707, "medianTimeToFirstChunk": 2.87914884799978, "medianTimeToFirstAnswerToken": 2.87914884799978, "medianEndToEndResponseTime": 10.686878007598038}}, "endToEndResponseTime": {"input": 2.859272696, "reasoning": 0, "answer": 16.09888467809626, "total": 18.95815737409626}, "timeToFirstAnswerToken": {"input": 2.859272696, "reasoning": 0, "total": 2.859272696}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e5dd499f-c330-45ec-9ff0-a99209c82af7", "slug": "mistral-small-3", "name": "Mistral Small 3", "shortName": "Mistral Small 3", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "mistral-small-3", "name": "Mistral Small 3"}, "deprecated": true, "deprecatedTo": "mistral-small-3-1", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 24, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501", "microevalsEnabled": false, "intelligenceIndex": 6.67120856746569, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0.195906432748538, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.263945578231293, "hle": 0.0376, "gpqa": 0.461616161616162, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.251851851851852, "aime25": 0.0433333333333333, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15000000000000002, "price1mBlended7To2To1": 0.12000000000000002, "price1mBlended0To1To1": 0.2, "price1mBlended100To1To1": 0.10196078431372549, "price1mBlended0To100To1": 0.10198019801980199, "timescaleData": {"medianOutputSpeed": 153.889957831054, "medianTimeToFirstChunk": 0.818382171999986}, "outputSpeedVariance": {"p05": 88.9915757120093, "q25": 135.539561280287, "median": 153.889957831054, "q75": 176.3312823353, "p95": 185.549666307139}, "timeToFirstChunkVariance": {"p05": 0.65700133029998, "q25": 0.72126486699996, "median": 0.818382171999986, "q75": 1.04565428675005, "p95": 1.36038482399994}, "performanceByPromptType": {"long": {"medianOutputSpeed": 153.889957831054, "medianTimeToFirstChunk": 0.818382171999986, "medianTimeToFirstAnswerToken": 0.818382171999986, "medianEndToEndResponseTime": 4.067457076217702}}, "endToEndResponseTime": {"input": 0.818382171999986, "reasoning": 0, "answer": 3.249074904217715, "total": 4.067457076217702}, "timeToFirstAnswerToken": {"input": 0.818382171999986, "reasoning": 0, "total": 0.818382171999986}, "performanceDataSource": {"type": "firstParty", "providerName": "Mistral"}, "hostModelCount": 2, "creator": {"id": "b5c0639a-cc9c-443b-a07e-bae6b7088933", "slug": "mistral", "name": "Mistral", "logo": "/img/logos/mistral_small.png", "color": "#fd6f00", "country": "fr", "url": "https://mistral.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e8aa417f-18fe-46b0-ba62-ef99785a9585", "slug": "glm-5-2-non-reasoning", "name": "GLM-5.2 (Non-reasoning)", "shortName": "GLM-5.2 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-16", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "glm-5-2", "name": "GLM-5.2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 753, "inferenceParametersActiveBillions": 40, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-5.2", "microevalsEnabled": false, "intelligenceIndex": 22.4323469590326, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -6.56666666666667, "omniscienceBreakdown": {"accuracy": 0.20283333333333334, "hallucinationRate": 0.3368178967175413}, "gdpval": 1306.43, "gdpvalNormalized": 0.40321500000000005, "itBenchSre": null, "tau2": null, "tauBanking": 0.167010309278351, "terminalbenchHard": null, "terminalBench21": 0.51685393258427, "terminalBench40": null, "scicode": null, "lcr": 0.423333333333333, "ifbench": null, "hle": 0.097775718257646, "gpqa": 0.685858585858586, "critpt": 0.0314285714285714, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.4, "price1mOutputTokens": 4.4, "cacheHitPrice": 0.26, "cacheHitDiscountPercent": 0.8320176484617219, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2.15, "price1mBlended7To2To1": 0.9019999999999999, "price1mBlended0To1To1": 2.9000000000000004, "price1mBlended100To1To1": 0.3117647058823529, "price1mBlended0To100To1": 1.4297029702970299, "timescaleData": {"medianOutputSpeed": 139.518129188851, "medianTimeToFirstChunk": 1.78941877549982}, "outputSpeedVariance": {"p05": 51.9111632840733, "q25": 87.5809375231641, "median": 139.518129188851, "q75": 255.266060775762, "p95": 382.838543491259}, "timeToFirstChunkVariance": {"p05": 0.678298352950017, "q25": 1.07035499875001, "median": 1.78941877549982, "q75": 2.47612733050001, "p95": 7.58312925094996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 126.945848117738, "medianTimeToFirstChunk": 1.09379177300003, "medianTimeToFirstAnswerToken": 1.09379177300003, "medianEndToEndResponseTime": 5.032479074819203}, "long": {"medianOutputSpeed": 139.518129188851, "medianTimeToFirstChunk": 1.78941877549982, "medianTimeToFirstAnswerToken": 1.78941877549982, "medianEndToEndResponseTime": 5.373182426195012}, "hundredK": {"medianOutputSpeed": 159.143878337598, "medianTimeToFirstChunk": 7.78515002800009, "medianTimeToFirstAnswerToken": 7.78515002800009, "medianEndToEndResponseTime": 10.926961106270602}, "mediumParallel": {"medianOutputSpeed": 112.03056958577, "medianTimeToFirstChunk": 1.54297208000003, "medianTimeToFirstAnswerToken": 1.54297208000003, "medianEndToEndResponseTime": 6.006039632443407}}, "endToEndResponseTime": {"input": 1.78941877549982, "reasoning": 0, "answer": 3.5837636506951918, "total": 5.373182426195012}, "timeToFirstAnswerToken": {"input": 1.78941877549982, "reasoning": 0, "total": 1.78941877549982}, "performanceDataSource": {"type": "median"}, "hostModelCount": 8, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e8d4100e-165b-4c5d-ac11-ac553590a334", "slug": "o1-pro", "name": "o1-pro", "shortName": "o1-pro", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-19", "knowledgeCutoffDate": "2023-10-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "o1-pro", "name": "o1-pro"}, "deprecated": true, "deprecatedTo": "o3-pro", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.4164514124427, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 150, "price1mOutputTokens": 600, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 114.75, "price1mBlended0To3To1": 262.5, "price1mBlended7To2To1": 195, "price1mBlended0To1To1": 375, "price1mBlended100To1To1": 154.41176470588235, "price1mBlended0To100To1": 154.45544554455446, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e8ffd75b-766f-4551-8c52-6e54706220eb", "slug": "jamba-1-6-mini", "name": "Jamba 1.6 Mini", "shortName": "Jamba 1.6 Mini", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-03-06", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "jamba-1-6-mini", "name": "Jamba 1.6 Mini"}, "deprecated": true, "deprecatedTo": "jamba-1-7-mini", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 52, "inferenceParametersActiveBillions": 12, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": "Jamba Open Model License Agreement", "licenseUrl": "https://www.ai21.com/licenses/jamba-open-model-license", "modelWeightsSourceUrl": "https://huggingface.co/ai21labs/AI21-Jamba-Mini-1.6", "microevalsEnabled": false, "intelligenceIndex": 5.16209285058134, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0431, "gpqa": 0.3, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0708994708994709, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "6216c686-bc60-4dbb-9f25-83e9dba803d1", "slug": "ai21-labs", "name": "AI21 Labs", "logo": "/img/logos/ai21_small.svg", "color": "#d63864", "country": "il", "url": "https://www.ai21.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e97a4ef5-e817-480e-9595-12f81dc4974f", "slug": "gpt-6-astra-medium", "name": "GPT-6 Astra (medium)", "shortName": "GPT-6 Astra (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-03", "knowledgeCutoffDate": "2026-04-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gpt-6-astra", "name": "GPT-6 Astra"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 49.6685363034369, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 52.37401759660499, "strategyAndOps": 54.430686678541164, "legal": 56.772177795297544, "engineering": 51.77462294191751, "economics": 57.9456753745752}, "omniscience": 42.2166666666667, "omniscienceBreakdown": {"accuracy": 0.6056666666666667, "hallucinationRate": 0.46534234995773455}, "gdpPdfAllPass": 0.304, "gdpval": 1500.67, "gdpvalNormalized": 0.5003350000000001, "itBenchSre": null, "tau2": null, "tauBanking": 0.354639175257732, "terminalbenchHard": null, "terminalBench21": 0.895131086142322, "terminalBench40": 0.494949494949495, "scicode": 0.541666666666667, "lcr": 0.796666666666667, "ifbench": null, "hle": 0.527340129749768, "gpqa": 0.939393939393939, "critpt": 0.291428571428571, "apexAgents": null, "mmmuPro": 0.850867052023121, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.6459498850561176, "price1mInputTokens": 10, "price1mOutputTokens": 50, "cacheHitPrice": 1, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 12.5, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 20, "price1mBlended7To2To1": 7.7, "price1mBlended0To1To1": 30, "price1mBlended100To1To1": 1.5686274509803921, "price1mBlended0To100To1": 10.396039603960396, "intelligenceIndexTimePerTask": 181.20281942242354, "intelligenceIndexCost": {"total": 2434.121104657961, "input": 1488.441754657961, "nonCacheInput": 280.95775, "cacheRead": 614.4100061166989, "cacheWrite": 593.073998541262, "output": 945.67935, "reasoning": 405.18989999999997, "answer": 540.48945}, "intelligenceIndexCostPerTask": {"cost": {"total": 1.5406493220021167, "input": 1.0611692893193365, "nonCacheInput": 0.2168692546108978, "cacheRead": 0.4804451305927465, "cacheWrite": 0.3638549041156922, "output": 0.4794800326827803, "reasoning": 0.17108503858355434, "answer": 0.3083949940992259}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.5909978493212386}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.182241260783478}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.05885103741150899}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.4430107637760555}, {"slug": "scicode", "weightedCostPerTask": 0.005087506944444445}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.010052880908248378}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.17198085999999999}, {"slug": "critpt", "weightedCostPerTask": 0.028512042857142858}, {"slug": "omniscience", "weightedCostPerTask": 0.00225261}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.047662510000000005}]}, "canonicalIntelligenceIndexTokenCount": {"input": 689951701, "output": 18913587, "answer": 10809789, "reasoning": 8103798}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 3421.700771671087, "answer": 6167.899881984518, "output": 9589.600653655605}, "briefcaseBreakdown": {"overall": {"elo": 1450.6, "lower95ci": 1441.48, "upper95ci": 1459.45}, "rubricPassRate": 0.47474747474747475, "analyticalQuality": {"elo": 1641.21, "lower95ci": 1623.99, "upper95ci": 1658.24}, "presentation": {"elo": 1389.68, "lower95ci": 1374.27, "upper95ci": 1405.72}}, "briefcaseTotalCost": 358.5386952548847, "timescaleData": {"medianOutputSpeed": 53.2424035818575, "medianTimeToFirstChunk": 4.45788101450006}, "outputSpeedVariance": {"p05": 43.3219503761214, "q25": 44.2740886995076, "median": 53.2424035818575, "q75": 60.3314770604515, "p95": 70.0253060073187}, "timeToFirstChunkVariance": {"p05": 3.59497375280004, "q25": 3.84633554075005, "median": 4.45788101450006, "q75": 7.59083253024998, "p95": 18.6749466667999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 49.9067035746242, "medianTimeToFirstChunk": 5.70441741999997, "medianTimeToFirstAnswerToken": 5.70441741999997, "medianEndToEndResponseTime": 15.72311158705436}, "long": {"medianOutputSpeed": 53.2424035818575, "medianTimeToFirstChunk": 4.45788101450006, "medianTimeToFirstAnswerToken": 4.45788101450006, "medianEndToEndResponseTime": 13.848892057629909}, "hundredK": {"medianOutputSpeed": 60.7138417104377, "medianTimeToFirstChunk": 6.38979896199995, "medianTimeToFirstAnswerToken": 6.38979896199995, "medianEndToEndResponseTime": 14.625153304830835}, "mediumParallel": {"medianOutputSpeed": 50.2881939923931, "medianTimeToFirstChunk": 12.1095241135, "medianTimeToFirstAnswerToken": 12.1095241135, "medianEndToEndResponseTime": 22.05221563421027}}, "endToEndResponseTime": {"input": 4.45788101450006, "reasoning": 0, "answer": 9.391011043129849, "total": 13.848892057629909}, "timeToFirstAnswerToken": {"input": 4.45788101450006, "reasoning": 0, "total": 4.45788101450006}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e98e911e-9fb2-4a9a-826e-3d681d0cdca8", "slug": "gpt-4o-2024-05-13", "name": "GPT-4o (May '24)", "shortName": "GPT-4o (May)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-05-13", "knowledgeCutoffDate": "2023-10-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-4o-2024-05-13", "name": "GPT-4o (May '24)"}, "deprecated": true, "deprecatedTo": "gpt-4o-2024-08-06", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.33166741584823, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0176, "gpqa": 0.526262626262626, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.334391534391534, "aime25": null, "analystAgent": null, "price1mInputTokens": 5, "price1mOutputTokens": 15, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 3.83, "price1mBlended0To3To1": 7.5, "price1mBlended7To2To1": 6, "price1mBlended0To1To1": 10, "price1mBlended100To1To1": 5.098039215686274, "price1mBlended0To100To1": 5.099009900990099, "timescaleData": {"medianOutputSpeed": 64.0596725557382, "medianTimeToFirstChunk": 1.45930614700001}, "outputSpeedVariance": {"p05": 34.5441444444727, "q25": 60.3215748814659, "median": 64.0596725557382, "q75": 83.9052189846421, "p95": 135.271140713799}, "timeToFirstChunkVariance": {"p05": 1.05215952270002, "q25": 1.19705448249999, "median": 1.45930614700001, "q75": 2.06729462999999, "p95": 6.18126929889999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 64.0596725557382, "medianTimeToFirstChunk": 1.45930614700001, "medianTimeToFirstAnswerToken": 1.45930614700001, "medianEndToEndResponseTime": 9.264528684860329}}, "endToEndResponseTime": {"input": 1.45930614700001, "reasoning": 0, "answer": 7.8052225378603195, "total": 9.264528684860329}, "timeToFirstAnswerToken": {"input": 1.45930614700001, "reasoning": 0, "total": 1.45930614700001}, "performanceDataSource": {"type": "firstParty", "providerName": "OpenAI"}, "hostModelCount": 2, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "e9a09db3-8fd6-41dd-ba2f-20e0a2bff7f2", "slug": "claude-opus-4-7", "name": "Claude Opus 4.7 (Adaptive Reasoning, Max Effort)", "shortName": "Claude Opus 4.7 (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-16", "knowledgeCutoffDate": "2026-01-01", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "claude-opus-4-7", "name": "Claude Opus 4.7"}, "deprecated": true, "deprecatedTo": "claude-opus-4-8", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 40.6897928205908, "intelligenceIndexIsEstimated": true, "capabilities": {"economics": 50.339342542434096}, "omniscience": 27.2666666666667, "omniscienceBreakdown": {"accuracy": 0.48883333333333334, "hallucinationRate": 0.4228888164329964}, "gdpval": 1395.78, "gdpvalNormalized": 0.44789, "itBenchSre": 0.466572504708098, "tau2": 0.885964912280702, "tauBanking": 0.34639175257732, "terminalbenchHard": 0.515151515151515, "terminalBench21": 0.831460674157303, "terminalBench40": null, "scicode": null, "lcr": 0.786666666666667, "ifbench": 0.586394557823129, "hle": 0.423076923076923, "gpqa": 0.914141414141414, "critpt": 0.12, "apexAgents": null, "mmmuPro": 0.788439306358382, "livecodebench": null, "aime25": null, "analystAgent": 0.4375, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.7, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "briefcaseBreakdown": {"overall": {"elo": 1251.5, "lower95ci": 1245.86, "upper95ci": 1257.98}, "rubricPassRate": 0.39337474120082816, "analyticalQuality": {"elo": 1244.35, "lower95ci": 1233.29, "upper95ci": 1255.61}, "presentation": {"elo": 1322.87, "lower95ci": 1312.46, "upper95ci": 1333.9}}, "briefcaseTotalCost": 1302.702528425893, "timescaleData": {"medianOutputSpeed": 52.2337311952895, "medianTimeToFirstChunk": 17.783215209}, "outputSpeedVariance": {"p05": 37.3266686146615, "q25": 42.3135566986508, "median": 52.2337311952895, "q75": 64.2658553828795, "p95": 80.6688679834754}, "timeToFirstChunkVariance": {"p05": 3.0405994494002, "q25": 4.17168507325005, "median": 17.783215209, "q75": 46.4296686735, "p95": 208.1093978536}, "performanceByPromptType": {"long": {"medianOutputSpeed": 52.2337311952895, "medianTimeToFirstChunk": 17.783215209, "medianTimeToFirstAnswerToken": 17.783215209, "medianEndToEndResponseTime": 27.355573693800157}}, "endToEndResponseTime": {"input": 17.783215209, "reasoning": 0, "answer": 9.572358484800155, "total": 27.355573693800157}, "timeToFirstAnswerToken": {"input": 17.783215209, "reasoning": 0, "total": 17.783215209}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ea5d2c10-1051-437d-95c2-18d5e4d14ff3", "slug": "cogito-v2-1-reasoning", "name": "Cogito v2.1 (Reasoning)", "shortName": "Cogito v2.1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-18", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "cogito-v2-1", "name": "Cogito v2.1"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 671, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepcogito/cogito-671b-v2.1", "microevalsEnabled": false, "intelligenceIndex": null, "intelligenceIndexIsEstimated": false, "capabilities": {}, "omniscience": -25.7833333333333, "omniscienceBreakdown": {"accuracy": 0.30183333333333334, "hallucinationRate": 0.8016232991167344}, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": 0.166666666666667, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.226666666666667, "ifbench": 0.462585034013605, "hle": 0.120018535681186, "gpqa": 0.767676767676768, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.687830687830688, "aime25": 0.726666666666667, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 1.25, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.25, "price1mBlended7To2To1": 1.25, "price1mBlended0To1To1": 1.25, "price1mBlended100To1To1": 1.25, "price1mBlended0To100To1": 1.25, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "e92cc1e2-153b-4f0a-ac19-c376aaa7c878", "slug": "deepcogito", "name": "Deep Cogito", "logo": "/img/logos/deepcogito_small.png", "color": "#5080ec", "country": "us", "url": "https://www.deepcogito.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "eab1492c-b853-4852-aa71-06b0ec2481c1", "slug": "gpt-5-chatgpt", "name": "GPT-5 (ChatGPT)", "shortName": "GPT-5 (ChatGPT)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-07", "knowledgeCutoffDate": "2024-09-30", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gpt-5-chatgpt", "name": "GPT-5 (ChatGPT)"}, "deprecated": true, "deprecatedTo": "gpt-5-1", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 128000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 10.4439365979985, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.128787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.65, "ifbench": 0.450340136054422, "hle": 0.0662650602409639, "gpqa": 0.685858585858586, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.542857142857143, "aime25": 0.483333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "eb0d4272-7204-42b9-b875-8866fed58548", "slug": "gemini-3-7-flash-medium", "name": "Gemini 3.7 Flash (medium)", "shortName": "Gemini 3.7 Flash (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-13", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "gemini-3-7-flash", "name": "Gemini 3.7 Flash"}, "deprecated": true, "deprecatedTo": "gemini-3-8-flash-medium", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 39.617751842555, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 23.7, "omniscienceBreakdown": {"accuracy": 0.54, "hallucinationRate": 0.658695652173913}, "gdpval": 1406.6, "gdpvalNormalized": 0.4533, "itBenchSre": null, "tau2": null, "tauBanking": 0.354639175257732, "terminalbenchHard": null, "terminalBench21": 0.782771535580524, "terminalBench40": null, "scicode": 0.59837962962963, "lcr": 0.83, "ifbench": null, "hle": 0.389712696941613, "gpqa": 0.921212121212121, "critpt": 0.0942857142857143, "apexAgents": null, "mmmuPro": 0.847398843930636, "livecodebench": null, "aime25": null, "analystAgent": null, "enterpriseOpsGym": 0.5040286481647269, "price1mInputTokens": 0.75, "price1mOutputTokens": 3.75, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.75, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5, "price1mBlended7To2To1": 0.5775, "price1mBlended0To1To1": 2.25, "price1mBlended100To1To1": 0.11764705882352941, "price1mBlended0To100To1": 0.7797029702970297, "timescaleData": {"medianOutputSpeed": 306.011030451663, "medianTimeToFirstChunk": 4.26135421499987}, "outputSpeedVariance": {"p05": 220.315686048675, "q25": 242.700988018198, "median": 306.011030451663, "q75": 343.445617009954, "p95": 394.777400198125}, "timeToFirstChunkVariance": {"p05": 1.88083603475003, "q25": 3.40877548225005, "median": 4.26135421499987, "q75": 6.06158318900002, "p95": 10.3323879850501}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 313.271956250071, "medianTimeToFirstChunk": 4.34678616100007, "medianTimeToFirstAnswerToken": 4.34678616100007, "medianEndToEndResponseTime": 5.942843484435917}, "long": {"medianOutputSpeed": 306.011030451663, "medianTimeToFirstChunk": 4.26135421499987, "medianTimeToFirstAnswerToken": 4.26135421499987, "medianEndToEndResponseTime": 5.89528224452879}, "hundredK": {"medianOutputSpeed": 295.552469616199, "medianTimeToFirstChunk": 2.26644562899992, "medianTimeToFirstAnswerToken": 2.26644562899992, "medianEndToEndResponseTime": 3.958192616089198}, "mediumParallel": {"medianOutputSpeed": 315.254067609523, "medianTimeToFirstChunk": 4.60399653449985, "medianTimeToFirstAnswerToken": 4.60399653449985, "medianEndToEndResponseTime": 6.1900188935176095}}, "endToEndResponseTime": {"input": 4.26135421499987, "reasoning": 0, "answer": 1.63392802952892, "total": 5.89528224452879}, "timeToFirstAnswerToken": {"input": 4.26135421499987, "reasoning": 0, "total": 4.26135421499987}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "eb4ba465-3fcd-4065-9fe2-e8225e7b2c6c", "slug": "ring-2-6-1t", "name": "Ring-2.6-1T", "shortName": "Ring-2.6-1T", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-05-08", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "xhigh", "label": "xhigh", "level": 50}, "release": {"slug": "ring-2-6-1t", "name": "Ring-2.6-1T"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 1000, "inferenceParametersActiveBillions": 63, "sizeClass": "large", "contextWindowTokens": 262144, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/inclusionAI/Ring-2.6-1T", "microevalsEnabled": true, "intelligenceIndex": 17.2770613768618, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 16.31767985987095, "strategyAndOps": 12.09431731119277, "legal": 17.092456514510058, "engineering": 20.12982282918432, "economics": 22.770907067407848}, "omniscience": -37.7, "omniscienceBreakdown": {"accuracy": 0.257, "hallucinationRate": 0.8532974427994616}, "gdpPdfAllPass": 0.038, "gdpval": 863.62, "gdpvalNormalized": 0.18181, "itBenchSre": null, "tau2": 0.923976608187135, "tauBanking": 0.179381443298969, "terminalbenchHard": 0.287878787878788, "terminalBench21": 0.430711610486891, "terminalBench40": 0.00505050505050505, "scicode": 0.450231481481481, "lcr": 0.7, "ifbench": 0.445578231292517, "hle": 0.215940685820204, "gpqa": 0.856565656565657, "critpt": 0.0371428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.007178659181731186, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.52, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.32156862745098036, "price1mBlended0To100To1": 0.3217821782178218, "intelligenceIndexTimePerTask": 321.36435467073886, "intelligenceIndexCost": {"total": 575.601981, "input": 277.7700435, "nonCacheInput": 5.7958065, "cacheRead": 0, "cacheWrite": 271.97423699999996, "output": 297.8319375, "reasoning": 249.8113075, "answer": 48.020630000000004}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.2871573189066596, "input": 0.17771985804269738, "nonCacheInput": 0.004381473015231696, "cacheRead": 0, "cacheWrite": 0.17333838502746568, "output": 0.10943746086396217, "reasoning": 0.06526377158983732, "answer": 0.04417368927412484}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.11310711214285714}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.02871769240909091}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.011598446461187215}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.0920109393939394}, {"slug": "scicode", "weightedCostPerTask": 0.0010353965972222223}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.008039426923076923}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0024486517000000003}, {"slug": "critpt", "weightedCostPerTask": 0.027925967714285713}, {"slug": "omniscience", "weightedCostPerTask": 0.000727814765}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0015458708}]}, "canonicalIntelligenceIndexTokenCount": {"input": 925900145, "output": 119132775, "answer": 19208252, "reasoning": 99924523}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 26105.508635934922, "answer": 17669.475709649934, "output": 43774.98434558486}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 654.34, "lower95ci": 644.6, "upper95ci": 663.38}, "rubricPassRate": 0.10929519918283963, "analyticalQuality": {"elo": 503.03, "lower95ci": 484.64, "upper95ci": 521.7}, "presentation": {"elo": 754.65, "lower95ci": 737.23, "upper95ci": 772.3}}, "briefcaseTotalCost": 68.6183147, "timescaleData": {"medianOutputSpeed": 123.30252706457, "medianTimeToFirstChunk": 3.777108155}, "outputSpeedVariance": {"p05": 103.385592935774, "q25": 117.013191216124, "median": 123.30252706457, "q75": 141.193212380729, "p95": 146.586808463026}, "timeToFirstChunkVariance": {"p05": 3.33674939230001, "q25": 3.6120253185, "median": 3.777108155, "q75": 4.13367785024995, "p95": 4.85194876324999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 131.637244542633, "medianTimeToFirstChunk": 2.06096688100001, "medianTimeToFirstAnswerToken": 17.25423537388665, "medianEndToEndResponseTime": 21.052552497108312}, "long": {"medianOutputSpeed": 123.30252706457, "medianTimeToFirstChunk": 3.777108155, "medianTimeToFirstAnswerToken": 19.997375878731706, "medianEndToEndResponseTime": 24.052442809664633}, "hundredK": {"medianOutputSpeed": 132.393165823158, "medianTimeToFirstChunk": 18.4928557360001, "medianTimeToFirstAnswerToken": 33.59937568032613, "medianEndToEndResponseTime": 37.376005666407636}, "mediumParallel": {"medianOutputSpeed": 117.146265573421, "medianTimeToFirstChunk": 1.90244472, "medianTimeToFirstAnswerToken": 18.97511869906515, "medianEndToEndResponseTime": 23.243287193831435}}, "endToEndResponseTime": {"input": 3.777108155, "reasoning": 16.220267723731705, "answer": 4.055066930932926, "total": 24.052442809664633}, "timeToFirstAnswerToken": {"input": 3.777108155, "reasoning": 16.220267723731705, "total": 19.997375878731706}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "4df238a9-d4fd-4cf2-ab1e-d12956c41f9b", "slug": "inclusionai", "name": "InclusionAI", "logo": "/img/logos/inclusionai_small.jpg", "color": "#4fb5ff", "country": "cn", "url": "https://www.inclusion-ai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "eb689f7a-f210-4a87-b407-f249897f2764", "slug": "solar-pro-2-reasoning", "name": "Solar Pro 2 (Reasoning)", "shortName": "Solar Pro 2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-09", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "solar-pro-2", "name": "Solar Pro 2"}, "deprecated": true, "deprecatedTo": "solar-pro-3", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 65536, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 7.49170414062443, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -55.8833333333333, "omniscienceBreakdown": {"accuracy": 0.1995, "hallucinationRate": 0.9473245887986675}, "gdpval": null, "itBenchSre": null, "tau2": 0.280701754385965, "tauBanking": null, "terminalbenchHard": 0.0303030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.370748299319728, "hle": 0.0736793327154773, "gpqa": 0.686868686868687, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.615873015873016, "aime25": 0.613333333333333, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "64ff7f06-c6fb-42ea-ba24-9cd103ab2d61", "slug": "upstage", "name": "Upstage", "logo": "/img/logos/upstage_small.svg", "color": "#7c59f5", "country": "kr", "url": "https://www.upstage.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ebf3b39f-0be6-43a1-a37a-f9b2978c9916", "slug": "muse-spark", "name": "Muse Spark", "shortName": "Muse Spark", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-08", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "muse-spark", "name": "Muse Spark"}, "deprecated": true, "deprecatedTo": "muse-spark-1-1", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 262144, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 31.2991113054345, "intelligenceIndexIsEstimated": true, "capabilities": {"economics": 39.58259957136237}, "omniscience": 7.16666666666667, "omniscienceBreakdown": {"accuracy": 0.496, "hallucinationRate": 0.841931216931217}, "gdpval": 1076.31, "gdpvalNormalized": 0.288155, "itBenchSre": null, "tau2": 0.915204678362573, "tauBanking": null, "terminalbenchHard": 0.454545454545455, "terminalBench21": 0.621722846441948, "terminalBench40": null, "scicode": null, "lcr": 0.78, "ifbench": 0.759183673469388, "hle": 0.406858202038925, "gpqa": 0.883838383838384, "critpt": 0.11330612244898, "apexAgents": null, "mmmuPro": 0.805202312138728, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "briefcaseBreakdown": {"overall": {"elo": 644.1, "lower95ci": 636.64, "upper95ci": 650.65}, "rubricPassRate": 0.16767676767676767, "analyticalQuality": {"elo": 587.61, "lower95ci": 573.95, "upper95ci": 600.64}, "presentation": {"elo": 526.58, "lower95ci": 510.82, "upper95ci": 541.55}}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ec3b22e6-48ac-416a-b4ae-55565a4f3046", "slug": "grok-3-reasoning", "name": "Grok 3 Reasoning Beta", "shortName": "Grok 3 Reasoning Beta", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "grok-3-reasoning", "name": "Grok 3 Reasoning Beta"}, "deprecated": true, "deprecatedTo": "grok-4", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 10.3553917819163, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ec60e57e-76d3-42e3-a0e3-80662225a639", "slug": "openchat-35", "name": "OpenChat 3.5 (1210)", "shortName": "OpenChat 3.5", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-12-18", "knowledgeCutoffDate": "2023-11-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "openchat-35", "name": "OpenChat 3.5 (1210)"}, "deprecated": true, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 8192, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/openchat/openchat-3.5-1210", "microevalsEnabled": false, "intelligenceIndex": 5.28995755703256, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0479, "gpqa": 0.23030303030303, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.115343915343915, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "14b780e1-14fb-4aae-af03-ae2d99699bb1", "slug": "openchat", "name": "OpenChat", "logo": "/img/logos/openchat_small.png", "color": "#5a80de", "country": "cn", "url": "https://github.com/imoneoi/openchat"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ecc6524a-d521-458a-8327-5009e8ce6549", "slug": "qwen3-14b-instruct", "name": "Qwen3 14B (Non-reasoning)", "shortName": "Qwen3 14B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-14b-instruct", "name": "Qwen3 14B"}, "deprecated": true, "deprecatedTo": "qwen3-30b-a3b-2507", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 14.8, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-14B", "microevalsEnabled": false, "intelligenceIndex": 6.7030362726921, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -66.6666666666667, "omniscienceBreakdown": {"accuracy": 0.13333333333333333, "hallucinationRate": 0.9230769230769231}, "gdpval": null, "itBenchSre": null, "tau2": 0.321637426900585, "tauBanking": null, "terminalbenchHard": 0.053030303030303, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.239455782312925, "hle": 0.0409, "gpqa": 0.46969696969697, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.28042328042328, "aime25": 0.58, "analystAgent": null, "price1mInputTokens": 0.35, "price1mOutputTokens": 1.4, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.6124999999999999, "price1mBlended7To2To1": 0.4549999999999999, "price1mBlended0To1To1": 0.875, "price1mBlended100To1To1": 0.3602941176470588, "price1mBlended0To100To1": 0.3603960396039604, "timescaleData": {"medianOutputSpeed": 62.7719571493957, "medianTimeToFirstChunk": 2.69471407849997}, "outputSpeedVariance": {"p05": 47.0266869967816, "q25": 57.8577580963029, "median": 62.7719571493957, "q75": 64.0052048667652, "p95": 64.9219016059588}, "timeToFirstChunkVariance": {"p05": 2.63286117129984, "q25": 2.65564250375013, "median": 2.69471407849997, "q75": 2.816753173, "p95": 3.4574706384}, "performanceByPromptType": {"long": {"medianOutputSpeed": 62.7719571493957, "medianTimeToFirstChunk": 2.69471407849997, "medianTimeToFirstAnswerToken": 2.69471407849997, "medianEndToEndResponseTime": 10.660054378628137}}, "endToEndResponseTime": {"input": 2.69471407849997, "reasoning": 0, "answer": 7.965340300128167, "total": 10.660054378628137}, "timeToFirstAnswerToken": {"input": 2.69471407849997, "reasoning": 0, "total": 2.69471407849997}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ee708f92-374e-4123-b900-e22d7b2afc19", "slug": "phi-4", "name": "Phi-4", "shortName": "Phi-4", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-12", "knowledgeCutoffDate": "2024-06-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "phi-4", "name": "Phi-4"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 14, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 16000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/microsoft/phi-4", "microevalsEnabled": false, "intelligenceIndex": 5.92257028113751, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -55.7, "omniscienceBreakdown": {"accuracy": 0.14066666666666666, "hallucinationRate": 0.8118696664080682}, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0.0378787878787879, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.235374149659864, "hle": 0.0376, "gpqa": 0.574747474747475, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.230687830687831, "aime25": 0.18, "analystAgent": null, "price1mInputTokens": 0.125, "price1mOutputTokens": 0.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.21875, "price1mBlended7To2To1": 0.1625, "price1mBlended0To1To1": 0.3125, "price1mBlended100To1To1": 0.12867647058823528, "price1mBlended0To100To1": 0.12871287128712872, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {"medianOutputSpeed": 36.3714385267619, "medianTimeToFirstChunk": 2.55631877899987}, "outputSpeedVariance": {"p05": 24.6652056620064, "q25": 30.7909890380534, "median": 36.3714385267619, "q75": 41.5319696080526, "p95": 41.8642253587515}, "timeToFirstChunkVariance": {"p05": 2.35049296949998, "q25": 2.44473133949993, "median": 2.55631877899987, "q75": 2.78140926899999, "p95": 3.15265914019996}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 43.3593040522572, "medianTimeToFirstChunk": 0.955528598000001, "medianTimeToFirstAnswerToken": 0.955528598000001, "medianEndToEndResponseTime": 12.48707899828764}, "long": {"medianOutputSpeed": 36.3714385267619, "medianTimeToFirstChunk": 2.55631877899987, "medianTimeToFirstAnswerToken": 2.55631877899987, "medianEndToEndResponseTime": 16.303369218924118}, "mediumParallel": {"medianOutputSpeed": 39.6884990457676, "medianTimeToFirstChunk": 1.74109509649997, "medianTimeToFirstAnswerToken": 1.74109509649997, "medianEndToEndResponseTime": 14.339203163610668}}, "endToEndResponseTime": {"input": 2.55631877899987, "reasoning": 0, "answer": 13.74705043992425, "total": 16.303369218924118}, "timeToFirstAnswerToken": {"input": 2.55631877899987, "reasoning": 0, "total": 2.55631877899987}, "performanceDataSource": {"type": "firstParty", "providerName": "Microsoft"}, "hostModelCount": 2, "creator": {"id": "ef5ce458-9986-4652-915a-e31fac5506b0", "slug": "azure", "name": "Microsoft", "logo": "/img/logos/microsoft_small.svg", "color": "#0078D5", "country": "us", "url": "https://azure.microsoft.com/en-us"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "eebfef01-709e-4ffe-b72f-0db75ef2434b", "slug": "qwen3-5-35b-a3b-non-reasoning", "name": "Qwen3.5 35B A3B (Non-reasoning)", "shortName": "Qwen3.5 35B A3B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-24", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-5-35b-a3b", "name": "Qwen3.5 35B A3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 36, "inferenceParametersActiveBillions": 3, "sizeClass": "small", "contextWindowTokens": 262144, "licenseName": "Apache 2.0", "licenseUrl": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3.5-35B-A3B", "microevalsEnabled": false, "intelligenceIndex": 15.1159818387307, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -63.0166666666667, "omniscienceBreakdown": {"accuracy": 0.15716666666666668, "hallucinationRate": 0.9341506822226616}, "gdpval": 740.47, "gdpvalNormalized": 0.12023500000000001, "itBenchSre": null, "tau2": 0.862573099415205, "tauBanking": 0.0494845360824742, "terminalbenchHard": 0.106060606060606, "terminalBench21": 0.408239700374532, "terminalBench40": null, "scicode": null, "lcr": 0.63, "ifbench": 0.444897959183673, "hle": 0.134383688600556, "gpqa": 0.819191919191919, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": 0.691907514450867, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.25, "price1mOutputTokens": 2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.256, "price1mBlended0To3To1": 0.6875, "price1mBlended7To2To1": 0.425, "price1mBlended0To1To1": 1.125, "price1mBlended100To1To1": 0.26715686274509803, "price1mBlended0To100To1": 0.26732673267326734, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 165.180380076869, "medianTimeToFirstChunk": 2.040629648}, "outputSpeedVariance": {"p05": 137.165695121131, "q25": 146.681230875998, "median": 165.180380076869, "q75": 183.802360441823, "p95": 204.876562651404}, "timeToFirstChunkVariance": {"p05": 1.96569642159996, "q25": 1.993073912, "median": 2.040629648, "q75": 2.1385756315, "p95": 2.41238373160002}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 162.642207580228, "medianTimeToFirstChunk": 1.13899556499999, "medianTimeToFirstAnswerToken": 1.13899556499999, "medianEndToEndResponseTime": 4.2132283083877144}, "long": {"medianOutputSpeed": 165.180380076869, "medianTimeToFirstChunk": 2.040629648, "medianTimeToFirstAnswerToken": 2.040629648, "medianEndToEndResponseTime": 5.067623530489664}, "hundredK": {"medianOutputSpeed": 187.241421275263, "medianTimeToFirstChunk": 16.589666074, "medianTimeToFirstAnswerToken": 16.589666074, "medianEndToEndResponseTime": 19.260015383434858}, "mediumParallel": {"medianOutputSpeed": 178.176025871324, "medianTimeToFirstChunk": 1.18556746849998, "medianTimeToFirstAnswerToken": 1.18556746849998, "medianEndToEndResponseTime": 3.9917811414948665}}, "endToEndResponseTime": {"input": 2.040629648, "reasoning": 0, "answer": 3.0269938824896636, "total": 5.067623530489664}, "timeToFirstAnswerToken": {"input": 2.040629648, "reasoning": 0, "total": 2.040629648}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 3, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "effcd151-7c31-4437-af3d-e88daeae9385", "slug": "claude-sonnet-5-medium", "name": "Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)", "shortName": "Claude Sonnet 5 (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "claude-sonnet-5", "name": "Claude Sonnet 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 28.4376468379456, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 30.533470352491715, "strategyAndOps": 31.089372307740067, "legal": 32.13994837735745, "engineering": 29.05796423656665, "economics": 38.02684584491813}, "omniscience": -6.86666666666667, "omniscienceBreakdown": {"accuracy": 0.371, "hallucinationRate": 0.6989931107578167}, "gdpPdfAllPass": 0.116, "gdpval": 1222.52, "gdpvalNormalized": 0.36125999999999997, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": 0.0202020202020202, "scicode": 0.516203703703704, "lcr": 0.736666666666667, "ifbench": null, "hle": 0.299814643188137, "gpqa": null, "critpt": 0.0857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.27872150606397167, "price1mInputTokens": 2, "price1mOutputTokens": 10, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 2.5, "pricePer1k1mpImages": 4.116, "price1mBlended0To3To1": 4, "price1mBlended7To2To1": 1.54, "price1mBlended0To1To1": 6, "price1mBlended100To1To1": 0.3137254901960784, "price1mBlended0To100To1": 2.0792079207920793, "intelligenceIndexTimePerTask": 249.06999660993023, "intelligenceIndexCost": {"total": 1218.167579445637, "input": 706.943449445637, "nonCacheInput": 70.624006, "cacheRead": 420.5130075264664, "cacheWrite": 215.8064359191706, "output": 511.22413, "reasoning": 324.99507, "answer": 186.22906}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.9991061406688175, "input": 0.7257353602627111, "nonCacheInput": 0.05142167231121703, "cacheRead": 0.5067724390222788, "cacheWrite": 0.1675412489292154, "output": 0.27337078040610624, "reasoning": 0.15441265439863025, "answer": 0.118958126007476}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.259836511522951}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.05286853952633941}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.021556186810874338}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.5533320628316333}, {"slug": "scicode", "weightedCostPerTask": 0.0017141576388888888}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.008466346895273402}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.039505314}, {"slug": "critpt", "weightedCostPerTask": 0.04689477714285715}, {"slug": "omniscience", "weightedCostPerTask": 0.00015627629999999997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.014775968}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2224199615, "output": 51122413, "answer": 18622906, "reasoning": 32499507}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 15441.265439863024, "answer": 11895.8126007476, "output": 27337.078040610624}, "briefcaseBreakdown": {"overall": {"elo": 1053.88, "lower95ci": 1047.5, "upper95ci": 1060.18}, "rubricPassRate": 0.2909090909090909, "analyticalQuality": {"elo": 1033.76, "lower95ci": 1021.12, "upper95ci": 1045.68}, "presentation": {"elo": 1087.5, "lower95ci": 1076.28, "upper95ci": 1099.08}}, "briefcaseTotalCost": 157.63415032392362, "timescaleData": {"medianOutputSpeed": 65.7194652041802, "medianTimeToFirstChunk": 2.07727663949993}, "outputSpeedVariance": {"p05": 48.9521803730789, "q25": 55.9456237035784, "median": 65.7194652041802, "q75": 84.6100243128757, "p95": 86.4649104908464}, "timeToFirstChunkVariance": {"p05": 0.729557867099981, "q25": 1.37440112124998, "median": 2.07727663949993, "q75": 4.93004728300012, "p95": 14.9227854293}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 68.3527028437861, "medianTimeToFirstChunk": 1.67572716150001, "medianTimeToFirstAnswerToken": 1.67572716150001, "medianEndToEndResponseTime": 8.990726849847443}, "long": {"medianOutputSpeed": 65.7194652041802, "medianTimeToFirstChunk": 2.07727663949993, "medianTimeToFirstAnswerToken": 2.07727663949993, "medianEndToEndResponseTime": 9.68537263429504}, "hundredK": {"medianOutputSpeed": 69.0590929075317, "medianTimeToFirstChunk": 2.289766292, "medianTimeToFirstAnswerToken": 2.289766292, "medianEndToEndResponseTime": 9.529942479507802}, "mediumParallel": {"medianOutputSpeed": 62.9147721290776, "medianTimeToFirstChunk": 2.16334379599993, "medianTimeToFirstAnswerToken": 2.16334379599993, "medianEndToEndResponseTime": 10.110602970271227}}, "endToEndResponseTime": {"input": 2.07727663949993, "reasoning": 0, "answer": 7.608095994795111, "total": 9.68537263429504}, "timeToFirstAnswerToken": {"input": 2.07727663949993, "reasoning": 0, "total": 2.07727663949993}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f0083258-8646-45b8-8082-7aaf6c2ea82a", "slug": "gpt-oss-120b", "name": "gpt-oss-120b (high)", "shortName": "gpt-oss-120b (high)", "chartDefaultSelected": true, "chartHighlighted": false, "releaseDate": "2025-08-05", "knowledgeCutoffDate": "2024-05-31", "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-oss-120b", "name": "gpt-oss-120b"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 117, "inferenceParametersActiveBillions": 5.1, "sizeClass": "medium", "contextWindowTokens": 131072, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/openai/gpt-oss-120b", "microevalsEnabled": true, "intelligenceIndex": 12.3483931512592, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 13.337748411389779, "strategyAndOps": 9.164541440694887, "legal": 12.267307529095435, "healthcareAndMedical": 11.617669482927457, "engineering": 15.885350999602808, "economics": 19.267643999073215}, "omniscience": -49.25, "omniscienceBreakdown": {"accuracy": 0.21783333333333332, "hallucinationRate": 0.9081610909865757}, "mlcrOverall": 0.0111111111111111, "harveyLab": 0.138949196699957, "gdpPdfAllPass": 0.04, "gdpval": 744.74, "gdpvalNormalized": 0.12237, "itBenchSre": 0.0564971751412429, "tau2": 0.657894736842105, "tauBanking": 0.127835051546392, "terminalbenchHard": 0.234848484848485, "terminalBench21": 0.262172284644195, "terminalBench40": 0, "scicode": 0.340277777777778, "lcr": 0.52, "ifbench": 0.689795918367347, "hle": 0.196014828544949, "gpqa": 0.781818181818182, "critpt": 0.0114285714285714, "apexAgents": 0.0309734513274336, "mmmuPro": null, "livecodebench": 0.878306878306878, "aime25": 0.934416666666667, "analystAgent": null, "automationBenchPartialScore": 0.0019906990691605595, "enterpriseOpsGym": 0.25544613548194567, "price1mInputTokens": 0.15, "price1mOutputTokens": 0.595, "cacheHitPrice": 0.125, "cacheHitDiscountPercent": 0.47500000000000003, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.26125, "price1mBlended7To2To1": 0.177, "price1mBlended0To1To1": 0.3725, "price1mBlended100To1To1": 0.1298529411764706, "price1mBlended0To100To1": 0.1544059405940594, "intelligenceIndexTimePerTask": 146.15272438925763, "intelligenceIndexCost": {"total": 122.29214927499999, "input": 72.21144254999999, "nonCacheInput": 2.2861243499999997, "cacheRead": 0, "cacheWrite": 69.92531819999999, "output": 50.080706725, "reasoning": 44.168710565, "answer": 5.91199616}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.10742452290394947, "input": 0.09138690981620429, "nonCacheInput": 0.0012983781736299591, "cacheRead": 0, "cacheWrite": 0.09008853164257433, "output": 0.016037613087745158, "reasoning": 0.00897526104444921, "answer": 0.0070623520432959485}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.08486605465384615}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.010508925954545454}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.0001628942713089802}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.006430462272727272}, {"slug": "scicode", "weightedCostPerTask": 0.0003877964079861111}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0013666466390176088}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0009230063349999999}, {"slug": "critpt", "weightedCostPerTask": 0.001835933207142857}, {"slug": "omniscience", "weightedCostPerTask": 0.00017367673237499997}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0007691264300000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 481409617, "output": 84169255, "answer": 9936128, "reasoning": 74233127}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 15084.472343612117, "answer": 11869.499232430167, "output": 26953.971576042284}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "rubricPassRate": 0.023232323232323233, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 0, "lower95ci": 0, "upper95ci": 0}}, "briefcaseTotalCost": 51.48540649, "timescaleData": {"medianOutputSpeed": 174.326274099814, "medianTimeToFirstChunk": 0.860782774999961}, "outputSpeedVariance": {"p05": 38.080061281276, "q25": 82.1825878535184, "median": 174.326274099814, "q75": 322.622572875778, "p95": 1557.16104048261}, "timeToFirstChunkVariance": {"p05": 0.277498485000001, "q25": 0.597040327000059, "median": 0.860782774999961, "q75": 1.24110786100005, "p95": 3.3398781972}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 167.235262155469, "medianTimeToFirstChunk": 0.53857455900004, "medianTimeToFirstAnswerToken": 12.4977748749042, "medianEndToEndResponseTime": 15.487574953880241}, "long": {"medianOutputSpeed": 174.326274099814, "medianTimeToFirstChunk": 0.860782774999961, "medianTimeToFirstAnswerToken": 12.333522672227732, "medianEndToEndResponseTime": 15.201707646534674}, "hundredK": {"medianOutputSpeed": 155.863589569739, "medianTimeToFirstChunk": 3.72037416599999, "medianTimeToFirstAnswerToken": 16.55210738554789, "medianEndToEndResponseTime": 19.760040690434867}, "mediumParallel": {"medianOutputSpeed": 179.329273718624, "medianTimeToFirstChunk": 0.581914829500193, "medianTimeToFirstAnswerToken": 11.73458365220503, "medianEndToEndResponseTime": 14.52275085788124}}, "endToEndResponseTime": {"input": 0.860782774999961, "reasoning": 11.47273989722777, "answer": 2.8681849743069425, "total": 15.201707646534674}, "timeToFirstAnswerToken": {"input": 0.860782774999961, "reasoning": 11.47273989722777, "total": 12.333522672227732}, "performanceDataSource": {"type": "median"}, "hostModelCount": 20, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f164b41f-44c5-4675-bca3-fea1db4bd9ae", "slug": "glm-5-non-reasoning", "name": "GLM-5 (Non-reasoning)", "shortName": "GLM-5 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-11", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "glm-5", "name": "GLM-5"}, "deprecated": true, "deprecatedTo": "glm-5-1-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 744, "inferenceParametersActiveBillions": 40, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-5", "microevalsEnabled": false, "intelligenceIndex": 21.7826479737062, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -11.8, "omniscienceBreakdown": {"accuracy": 0.2305, "hallucinationRate": 0.45289148797920725}, "gdpval": null, "itBenchSre": null, "tau2": 0.973684210526316, "tauBanking": null, "terminalbenchHard": 0.393939393939394, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.436666666666667, "ifbench": 0.551700680272109, "hle": 0.0764596848934198, "gpqa": 0.665656565656566, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1, "price1mOutputTokens": 3.2, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.55, "price1mBlended7To2To1": 0.66, "price1mBlended0To1To1": 2.1, "price1mBlended100To1To1": 0.2372549019607843, "price1mBlended0To100To1": 1.0217821782178218, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 53.9549407019927, "medianTimeToFirstChunk": 1.71098728949999}, "outputSpeedVariance": {"p05": 19.0532227130861, "q25": 33.6487308776127, "median": 53.9549407019927, "q75": 67.7826347022379, "p95": 79.3880168232145}, "timeToFirstChunkVariance": {"p05": 0.832041317499904, "q25": 1.40322808550002, "median": 1.71098728949999, "q75": 2.10068131225012, "p95": 4.00294144450006}, "performanceByPromptType": {"long": {"medianOutputSpeed": 53.9549407019927, "medianTimeToFirstChunk": 1.71098728949999, "medianTimeToFirstAnswerToken": 1.71098728949999, "medianEndToEndResponseTime": 10.97797921822124}}, "endToEndResponseTime": {"input": 1.71098728949999, "reasoning": 0, "answer": 9.26699192872125, "total": 10.97797921822124}, "timeToFirstAnswerToken": {"input": 1.71098728949999, "reasoning": 0, "total": 1.71098728949999}, "performanceDataSource": {"type": "median"}, "hostModelCount": 4, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f1d52583-9d20-4099-99ac-b5df9430c3b6", "slug": "nvidia-nemotron-nano-9b-v2-reasoning", "name": "NVIDIA Nemotron Nano 9B V2 (Reasoning)", "shortName": "NVIDIA Nemotron Nano 9B V2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-18", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "nvidia-nemotron-nano-9b-v2", "name": "NVIDIA Nemotron Nano 9B V2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 9, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 131072, "licenseName": "NVIDIA Open Model License Agreement", "licenseUrl": "https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/", "modelWeightsSourceUrl": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Nano-9B-v2", "microevalsEnabled": false, "intelligenceIndex": 7.42882284148722, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -41.55, "omniscienceBreakdown": {"accuracy": 0.118, "hallucinationRate": 0.604875283446712}, "gdpval": null, "itBenchSre": null, "tau2": 0.219298245614035, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.226666666666667, "ifbench": 0.276190476190476, "hle": 0.0486561631139944, "gpqa": 0.56969696969697, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.723809523809524, "aime25": 0.696666666666667, "analystAgent": null, "price1mInputTokens": 0.04, "price1mOutputTokens": 0.16, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.07, "price1mBlended7To2To1": 0.052000000000000005, "price1mBlended0To1To1": 0.1, "price1mBlended100To1To1": 0.041176470588235294, "price1mBlended0To100To1": 0.04118811881188119, "openness": {"opennessIndex": 72.22222222222223, "modelAvailability": 6, "transparencyMethodology": 4, "transparencyPostTrainingData": 1.5, "transparencyPreTrainingData": 1.5}, "timescaleData": {"medianOutputSpeed": 105.332875576145, "medianTimeToFirstChunk": 7.007974112}, "outputSpeedVariance": {"p05": 40.8471861119418, "q25": 76.4617720396706, "median": 105.332875576145, "q75": 125.18236071368, "p95": 166.71950190432}, "timeToFirstChunkVariance": {"p05": 2.921401236, "q25": 3.79143334849999, "median": 7.007974112, "q75": 17.90748253575, "p95": 31.36264194025}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 88.8487969095478, "medianTimeToFirstChunk": 10.444278326, "medianTimeToFirstAnswerToken": 32.95443118756427, "medianEndToEndResponseTime": 38.58196940295534}, "long": {"medianOutputSpeed": 105.332875576145, "medianTimeToFirstChunk": 7.007974112, "medianTimeToFirstAnswerToken": 25.99539839962616, "medianEndToEndResponseTime": 30.7422544715327}, "hundredK": {"medianOutputSpeed": 152.908809035364, "medianTimeToFirstChunk": 14.1982038574999, "medianTimeToFirstAnswerToken": 27.277895031717666, "medianEndToEndResponseTime": 30.547817825272105}, "mediumParallel": {"medianOutputSpeed": 104.390103559948, "medianTimeToFirstChunk": 8.02712603199996, "medianTimeToFirstAnswerToken": 27.186030293949102, "medianEndToEndResponseTime": 31.97575635943639}}, "endToEndResponseTime": {"input": 7.007974112, "reasoning": 18.987424287626162, "answer": 4.7468560719065405, "total": 30.7422544715327}, "timeToFirstAnswerToken": {"input": 7.007974112, "reasoning": 18.987424287626162, "total": 25.99539839962616}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "0c303112-430d-4367-a484-51defaa2e166", "slug": "nvidia", "name": "NVIDIA", "logo": "/img/logos/nvidia_small.svg", "color": "#76b900", "country": "us", "url": "https://www.nvidia.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f2e21112-192e-4aed-ae82-68ca3b38e667", "slug": "claude-sonnet-4-6-non-reasoning-low-effort", "name": "Claude Sonnet 4.6 (Non-reasoning, Low Effort)", "shortName": "Claude Sonnet 4.6 (Non-reasoning, low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-17", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "claude-sonnet-4-6", "name": "Claude Sonnet 4.6"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 23.3035011715443, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -2.1, "omniscienceBreakdown": {"accuracy": 0.36516666666666664, "hallucinationRate": 0.6082961407193489}, "mlcrOverall": 0.205555555555556, "gdpval": null, "itBenchSre": null, "tau2": 0.789473684210526, "tauBanking": null, "terminalbenchHard": 0.424242424242424, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.693333333333333, "ifbench": 0.423809523809524, "hle": 0.112140871177016, "gpqa": 0.796969696969697, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": 0.691907514450867, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 3.75, "pricePer1k1mpImages": 4, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 2.31, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 0.47058823529411764, "price1mBlended0To100To1": 3.118811881188119, "timescaleData": {"medianOutputSpeed": 42.0349573774363, "medianTimeToFirstChunk": 1.40933617100001}, "outputSpeedVariance": {"p05": 34.5296678331542, "q25": 37.630641592105, "median": 42.0349573774363, "q75": 53.4066635224899, "p95": 76.0480192952926}, "timeToFirstChunkVariance": {"p05": 0.887265460550004, "q25": 1.07844557499996, "median": 1.40933617100001, "q75": 1.92802600825001, "p95": 3.06079284424999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 55.885061672727, "medianTimeToFirstChunk": 1.22152915949997, "medianTimeToFirstAnswerToken": 1.22152915949997, "medianEndToEndResponseTime": 10.168463904389224}, "long": {"medianOutputSpeed": 42.0349573774363, "medianTimeToFirstChunk": 1.40933617100001, "medianTimeToFirstAnswerToken": 1.40933617100001, "medianEndToEndResponseTime": 13.304197762280987}, "hundredK": {"medianOutputSpeed": 52.4318668005508, "medianTimeToFirstChunk": 2.63751022700006, "medianTimeToFirstAnswerToken": 2.63751022700006, "medianEndToEndResponseTime": 12.173695575921252}, "mediumParallel": {"medianOutputSpeed": 48.9036041754787, "medianTimeToFirstChunk": 1.31195976350003, "medianTimeToFirstAnswerToken": 1.31195976350003, "medianEndToEndResponseTime": 11.536155064236382}}, "endToEndResponseTime": {"input": 1.40933617100001, "reasoning": 0, "answer": 11.894861591280977, "total": 13.304197762280987}, "timeToFirstAnswerToken": {"input": 1.40933617100001, "reasoning": 0, "total": 1.40933617100001}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 1, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f2f60e3a-e5f5-4471-acd2-9f2f29c76007", "slug": "claude-4-1-opus", "name": "Claude 4.1 Opus (Non-reasoning)", "shortName": "Claude 4.1 Opus (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-05", "knowledgeCutoffDate": "2025-03-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "claude-4-1-opus", "name": "Claude 4.1 Opus"}, "deprecated": true, "deprecatedTo": "claude-opus-4-5", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 200000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 18.5669784317462, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 15, "price1mOutputTokens": 75, "cacheHitPrice": 1.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 18.75, "pricePer1k1mpImages": 20.01, "price1mBlended0To3To1": 30, "price1mBlended7To2To1": 11.55, "price1mBlended0To1To1": 45, "price1mBlended100To1To1": 2.3529411764705883, "price1mBlended0To100To1": 15.594059405940595, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 4, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f3169f25-8c6f-48e4-ae87-0cf872dc0ec1", "slug": "qwen3-30b-a3b-instruct", "name": "Qwen3 30B A3B (Non-reasoning)", "shortName": "Qwen3 30B (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-04-28", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-30b-a3b-instruct", "name": "Qwen3 30B A3B"}, "deprecated": true, "deprecatedTo": "qwen3-30b-a3b-2507", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 30.5, "inferenceParametersActiveBillions": 3.3, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-30B-A3B", "microevalsEnabled": false, "intelligenceIndex": 6.62259542880934, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -65.9833333333333, "omniscienceBreakdown": {"accuracy": 0.11966666666666667, "hallucinationRate": 0.8854600530102233}, "gdpval": null, "itBenchSre": null, "tau2": 0.222222222222222, "tauBanking": null, "terminalbenchHard": 0.0681818181818182, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.319047619047619, "hle": 0.046, "gpqa": 0.515151515151515, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.321693121693122, "aime25": 0.216666666666667, "analystAgent": null, "price1mInputTokens": 0.2, "price1mOutputTokens": 0.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.35000000000000003, "price1mBlended7To2To1": 0.26000000000000006, "price1mBlended0To1To1": 0.5, "price1mBlended100To1To1": 0.20588235294117646, "price1mBlended0To100To1": 0.20594059405940596, "timescaleData": {"medianOutputSpeed": 104.847578181162, "medianTimeToFirstChunk": 2.22757071550001}, "outputSpeedVariance": {"p05": 90.1259069075528, "q25": 98.2381870959052, "median": 104.847578181162, "q75": 111.23001378434, "p95": 114.150193229075}, "timeToFirstChunkVariance": {"p05": 2.09493367080001, "q25": 2.13767327375001, "median": 2.22757071550001, "q75": 2.46078501975004, "p95": 3.20361738619999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 104.847578181162, "medianTimeToFirstChunk": 2.22757071550001, "medianTimeToFirstAnswerToken": 2.22757071550001, "medianEndToEndResponseTime": 6.99639808064973}}, "endToEndResponseTime": {"input": 2.22757071550001, "reasoning": 0, "answer": 4.768827365149719, "total": 6.99639808064973}, "timeToFirstAnswerToken": {"input": 2.22757071550001, "reasoning": 0, "total": 2.22757071550001}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 2, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f371ad68-6947-4767-a78f-1f6c81f96b93", "slug": "qwen3-6-plus", "name": "Qwen3.6 Plus", "shortName": "Qwen3.6 Plus", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 5550, "release": {"slug": "qwen3-6-plus", "name": "Qwen3.6 Plus"}, "deprecated": true, "deprecatedTo": "qwen3-7-plus", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 27.0099232636747, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 0.883333333333333, "omniscienceBreakdown": {"accuracy": 0.2638333333333333, "hallucinationRate": 0.34638895177722434}, "gdpval": 1065.83, "gdpvalNormalized": 0.28291499999999997, "itBenchSre": null, "tau2": 0.976608187134503, "tauBanking": 0.208247422680412, "terminalbenchHard": 0.439393939393939, "terminalBench21": 0.614232209737828, "terminalBench40": null, "scicode": null, "lcr": 0.783333333333333, "ifbench": 0.751700680272109, "hle": 0.278498609823911, "gpqa": 0.881818181818182, "critpt": 0.0285714285714286, "apexAgents": null, "mmmuPro": 0.779768786127168, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.5, "price1mOutputTokens": 3, "cacheHitPrice": 0.05, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.625, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.125, "price1mBlended7To2To1": 0.43499999999999994, "price1mBlended0To1To1": 1.75, "price1mBlended100To1To1": 0.08333333333333333, "price1mBlended0To100To1": 0.5247524752475248, "timescaleData": {"medianOutputSpeed": 56.1736058129674, "medianTimeToFirstChunk": 2.10283385800005}, "outputSpeedVariance": {"p05": 52.0113015365786, "q25": 54.9437566165091, "median": 56.1736058129674, "q75": 57.2877366314829, "p95": 61.9095473125496}, "timeToFirstChunkVariance": {"p05": 1.91193213750001, "q25": 1.95531584700001, "median": 2.10283385800005, "q75": 2.23953517549998, "p95": 2.58794867990002}, "performanceByPromptType": {"long": {"medianOutputSpeed": 56.1736058129674, "medianTimeToFirstChunk": 2.10283385800005, "medianTimeToFirstAnswerToken": 100.90368382442342, "medianEndToEndResponseTime": 109.80466129887598}}, "endToEndResponseTime": {"input": 2.10283385800005, "reasoning": 98.80084996642337, "answer": 8.900977474452556, "total": 109.80466129887598}, "timeToFirstAnswerToken": {"input": 2.10283385800005, "reasoning": 98.80084996642337, "total": 100.90368382442342}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 1, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f3a0e101-086f-44b3-a1b2-d23498f9716b", "slug": "agnes-2-5-pro-beta", "name": "Agnes 2.5 Pro Beta", "shortName": "Agnes 2.5 Pro Beta", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-26", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "agnes-2-5-pro-beta", "name": "Agnes 2.5 Pro Beta"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 35.2413300369053, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -10.5333333333333, "omniscienceBreakdown": {"accuracy": 0.16766666666666666, "hallucinationRate": 0.3279935923107729}, "gdpval": 1375.77, "gdpvalNormalized": 0.43788499999999997, "itBenchSre": null, "tau2": null, "tauBanking": 0.356701030927835, "terminalbenchHard": null, "terminalBench21": 0.696629213483146, "terminalBench40": null, "scicode": 0.488425925925926, "lcr": 0.83, "ifbench": null, "hle": 0.375347544022243, "gpqa": 0.905050505050505, "critpt": 0.157142857142857, "apexAgents": null, "mmmuPro": 0.754335260115607, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.3, "cacheHitPrice": 0.01, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15000000000000002, "price1mBlended7To2To1": 0.05700000000000001, "price1mBlended0To1To1": 0.2, "price1mBlended100To1To1": 0.013725490196078433, "price1mBlended0To100To1": 0.10198019801980199, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Sapiens AI"}, "hostModelCount": 1, "creator": {"id": "5db3af1a-e372-4c62-98bd-f6027eeaf990", "slug": "agnes-ai", "name": "Sapiens AI", "logo": "/img/logos/sapiens.svg", "color": "#1521a9", "country": "sg", "url": "https://agnes-ai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f4274721-ef28-4121-aa88-8e97267a5a82", "slug": "nova-2-0-pro-reasoning-low", "name": "Nova 2.0 Pro Preview (low)", "shortName": "Nova 2.0 Pro Preview (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-27", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "nova-2-0-pro-preview", "name": "Nova 2.0 Pro Preview"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 12.7754507441167, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -40.5333333333333, "omniscienceBreakdown": {"accuracy": 0.171, "hallucinationRate": 0.6952151186168074}, "gdpval": 600.77, "gdpvalNormalized": 0.05038499999999999, "itBenchSre": null, "tau2": 0.906432748538012, "tauBanking": null, "terminalbenchHard": 0.174242424242424, "terminalBench21": 0.194756554307116, "terminalBench40": null, "scicode": null, "lcr": 0.646666666666667, "ifbench": 0.795918367346939, "hle": 0.0518999073215941, "gpqa": 0.750505050505051, "critpt": 0, "apexAgents": null, "mmmuPro": 0.627167630057804, "livecodebench": 0.638095238095238, "aime25": 0.633333333333333, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 10, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 1.76, "price1mBlended0To3To1": 3.4375, "price1mBlended7To2To1": 2.125, "price1mBlended0To1To1": 5.625, "price1mBlended100To1To1": 1.3357843137254901, "price1mBlended0To100To1": 1.3366336633663367, "timescaleData": {"medianOutputSpeed": 112.677988326384, "medianTimeToFirstChunk": 9.14851314449998}, "outputSpeedVariance": {"p05": 101.042315976882, "q25": 108.851615997214, "median": 112.677988326384, "q75": 138.864310363056, "p95": 152.102666115303}, "timeToFirstChunkVariance": {"p05": 5.55110151594997, "q25": 6.91498190575004, "median": 9.14851314449998, "q75": 15.14383662775, "p95": 19.0360225336498}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 138.403892741306, "medianTimeToFirstChunk": 3.53555588749999, "medianTimeToFirstAnswerToken": 17.986016495123557, "medianEndToEndResponseTime": 21.59863164702945}, "long": {"medianOutputSpeed": 112.677988326384, "medianTimeToFirstChunk": 9.14851314449998, "medianTimeToFirstAnswerToken": 26.89820880117769, "medianEndToEndResponseTime": 31.33563271534712}, "hundredK": {"medianOutputSpeed": 131.375605079565, "medianTimeToFirstChunk": 16.5668161724999, "medianTimeToFirstAnswerToken": 31.790342631531168, "medianEndToEndResponseTime": 35.59622424628898}, "mediumParallel": {"medianOutputSpeed": 126.773030837624, "medianTimeToFirstChunk": 6.04607033750002, "medianTimeToFirstAnswerToken": 21.822296454249415, "medianEndToEndResponseTime": 25.76635298343676}}, "endToEndResponseTime": {"input": 9.14851314449998, "reasoning": 17.749695656677712, "answer": 4.437423914169428, "total": 31.33563271534712}, "timeToFirstAnswerToken": {"input": 9.14851314449998, "reasoning": 17.749695656677712, "total": 26.89820880117769}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f4e8194a-d0e6-48eb-92be-4307de5aeeec", "slug": "gemini-2-5-flash-lite-reasoning", "name": "Gemini 2.5 Flash-Lite (Reasoning)", "shortName": "Gemini 2.5 Flash-Lite", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-06-17", "knowledgeCutoffDate": "2025-01-01", "isReasoning": true, "reasoningTokens": 0, "release": {"slug": "gemini-2-5-flash-lite", "name": "Gemini 2.5 Flash-Lite"}, "deprecated": true, "deprecatedTo": "gemini-2-5-flash-lite-preview-09-2025-reasoning", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.54563691769003, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -45.6166666666667, "omniscienceBreakdown": {"accuracy": 0.179, "hallucinationRate": 0.7736500203004466}, "mlcrOverall": 0.0222222222222222, "gdpval": null, "itBenchSre": null, "tau2": 0.184210526315789, "tauBanking": null, "terminalbenchHard": 0.0454545454545455, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.556666666666667, "ifbench": 0.498639455782313, "hle": 0.0681186283595922, "gpqa": 0.625252525252525, "critpt": 0, "apexAgents": null, "mmmuPro": 0.582080924855491, "livecodebench": 0.592592592592593, "aime25": 0.533333333333333, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.4, "cacheHitPrice": 0.01, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": 0.1032, "price1mBlended0To3To1": 0.17500000000000002, "price1mBlended7To2To1": 0.067, "price1mBlended0To1To1": 0.25, "price1mBlended100To1To1": 0.014705882352941176, "price1mBlended0To100To1": 0.10297029702970298, "timescaleData": {"medianOutputSpeed": 380.040652637826, "medianTimeToFirstChunk": 24.42282024}, "outputSpeedVariance": {"p05": 260.496609135837, "q25": 319.273070586534, "median": 380.040652637826, "q75": 428.918332359035, "p95": 496.111454604144}, "timeToFirstChunkVariance": {"p05": 11.5336979141, "q25": 17.4004912659999, "median": 24.42282024, "q75": 32.20183999975, "p95": 54.2384616082499}, "performanceByPromptType": {"long": {"medianOutputSpeed": 380.040652637826, "medianTimeToFirstChunk": 24.42282024, "medianTimeToFirstAnswerToken": 24.42282024, "medianEndToEndResponseTime": 25.738468964760226}}, "endToEndResponseTime": {"input": 24.42282024, "reasoning": 0, "answer": 1.3156487247602267, "total": 25.738468964760226}, "timeToFirstAnswerToken": {"input": 24.42282024, "reasoning": 0, "total": 24.42282024}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f5d83128-047f-496d-ba49-8a428abe8345", "slug": "qwen3-vl-4b-instruct", "name": "Qwen3 VL 4B Instruct", "shortName": "Qwen3 VL 4B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-14", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-vl-4b-instruct", "name": "Qwen3 VL 4B Instruct"}, "deprecated": true, "deprecatedTo": "qwen3-5-4b-non-reasoning", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 4.44, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 5.65532227476457, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -75.9666666666667, "omniscienceBreakdown": {"accuracy": 0.10866666666666666, "hallucinationRate": 0.9741959611069558}, "gdpval": null, "itBenchSre": null, "tau2": 0.233918128654971, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.14, "ifbench": 0.318367346938775, "hle": 0.036144578313253, "gpqa": 0.370707070707071, "critpt": 0, "apexAgents": null, "mmmuPro": 0.438728323699422, "livecodebench": 0.28994708994709, "aime25": 0.37, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f6ccbe1d-bd7e-484b-9795-18cc9f91552d", "slug": "qwen3-235b-a22b-instruct-2507-reasoning", "name": "Qwen3 235B A22B 2507 (Reasoning)", "shortName": "Qwen3 235B A22B 2507", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-07-25", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-235b-a22b-instruct-2507", "name": "Qwen3 235B A22B 2507"}, "deprecated": true, "deprecatedTo": "qwen3-5-397b-a17b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 235, "inferenceParametersActiveBillions": 22, "sizeClass": "large", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507", "microevalsEnabled": false, "intelligenceIndex": 12.7108511527974, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 11.312373850706216, "strategyAndOps": 7.940311925664784, "legal": 11.751833004124581, "engineering": 14.966651992585732, "economics": 17.61552131603337}, "omniscience": -46.5166666666667, "omniscienceBreakdown": {"accuracy": 0.22816666666666666, "hallucinationRate": 0.8982941049449363}, "gdpPdfAllPass": 0.048, "gdpval": 495.33, "gdpvalNormalized": 0, "itBenchSre": null, "tau2": 0.532163742690059, "tauBanking": 0.0783505154639175, "terminalbenchHard": 0.136363636363636, "terminalBench21": 0.119850187265918, "terminalBench40": 0, "scicode": 0.414351851851852, "lcr": 0.72, "ifbench": 0.512244897959184, "hle": 0.158943466172382, "gpqa": 0.78989898989899, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.788359788359788, "aime25": 0.91, "analystAgent": null, "automationBenchPartialScore": 0.021540366122608224, "price1mInputTokens": 0.23, "price1mOutputTokens": 2.3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.7474999999999999, "price1mBlended7To2To1": 0.437, "price1mBlended0To1To1": 1.265, "price1mBlended100To1To1": 0.25029411764705883, "price1mBlended0To100To1": 0.2504950495049505, "intelligenceIndexTimePerTask": 404.68405031851887, "intelligenceIndexCost": {"total": 234.7197495, "input": 35.2593703, "nonCacheInput": 3.45111895, "cacheRead": 0, "cacheWrite": 31.80825135, "output": 199.4603792, "reasoning": 187.5887084, "answer": 11.8716708}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.08055542892015415, "input": 0.02331126027350876, "nonCacheInput": 0.001990099181455529, "cacheRead": 0, "cacheWrite": 0.02132116109205323, "output": 0.057244168646645374, "reasoning": 0.050878485587035824, "answer": 0.00636568305960955}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.016483159780219782}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.010396523668181817}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.004083681174277017}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.02991081522727273}, {"slug": "scicode", "weightedCostPerTask": 0.0015317894583333335}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.004237001604726598}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0031903058499999997}, {"slug": "critpt", "weightedCostPerTask": 0.008511718757142857}, {"slug": "omniscience", "weightedCostPerTask": 0.00050082845}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.00170960495}]}, "canonicalIntelligenceIndexTokenCount": {"input": 153301610, "output": 86721904, "answer": 5161596, "reasoning": 81560308}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 22121.080690015577, "answer": 2767.6882867867616, "output": 24888.768976802337}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 189.93, "lower95ci": 178.32, "upper95ci": 200.28}, "rubricPassRate": 0.047474747474747475, "analyticalQuality": {"elo": 0, "lower95ci": 0, "upper95ci": 0}, "presentation": {"elo": 105.11, "lower95ci": 82.16, "upper95ci": 125.05}}, "briefcaseTotalCost": 9.9997836, "timescaleData": {"medianOutputSpeed": 58.6939866906423, "medianTimeToFirstChunk": 2.81376835900005}, "outputSpeedVariance": {"p05": 42.1344926997833, "q25": 50.001057529232, "median": 58.6939866906423, "q75": 70.6521021351106, "p95": 82.8262625542821}, "timeToFirstChunkVariance": {"p05": 2.57986242259983, "q25": 2.67558730099995, "median": 2.81376835900005, "q75": 2.95257603750002, "p95": 4.13064667129999}, "performanceByPromptType": {"long": {"medianOutputSpeed": 58.6939866906423, "medianTimeToFirstChunk": 2.81376835900005, "medianTimeToFirstAnswerToken": 36.88880930895931, "medianEndToEndResponseTime": 45.407569546449125}}, "endToEndResponseTime": {"input": 2.81376835900005, "reasoning": 34.07504094995926, "answer": 8.518760237489815, "total": 45.407569546449125}, "timeToFirstAnswerToken": {"input": 2.81376835900005, "reasoning": 34.07504094995926, "total": 36.88880930895931}, "performanceDataSource": {"type": "firstParty", "providerName": "Alibaba"}, "hostModelCount": 3, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f6db039b-0f3b-485c-9d7f-982988e44f26", "slug": "gemini-3-8-flash-low", "name": "Gemini 3.8 Flash (low)", "shortName": "Gemini 3.8 Flash (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-09-02", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "gemini-3-8-flash", "name": "Gemini 3.8 Flash"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 33.7857356699132, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 39.5417117085147, "strategyAndOps": 39.074876948833015, "legal": 44.92568311045428, "engineering": 34.8190558710366, "economics": 45.97168516373185}, "omniscience": 21.35, "omniscienceBreakdown": {"accuracy": 0.5221666666666667, "hallucinationRate": 0.6459713986745728}, "gdpPdfAllPass": 0.186, "gdpval": 1358.55, "gdpvalNormalized": 0.42927499999999996, "itBenchSre": null, "tau2": null, "tauBanking": 0.331958762886598, "terminalbenchHard": null, "terminalBench21": 0.831460674157303, "terminalBench40": 0.101010101010101, "scicode": 0.549768518518518, "lcr": 0.806666666666667, "ifbench": null, "hle": 0.370713623725672, "gpqa": 0.92020202020202, "critpt": 0.04, "apexAgents": null, "mmmuPro": 0.845086705202312, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.3650940461486253, "price1mInputTokens": 0.75, "price1mOutputTokens": 3.75, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 0.75, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5, "price1mBlended7To2To1": 0.5775, "price1mBlended0To1To1": 2.25, "price1mBlended100To1To1": 0.11764705882352941, "price1mBlended0To100To1": 0.7797029702970297, "briefcaseBreakdown": {"overall": {"elo": 1055.59, "lower95ci": 1046.25, "upper95ci": 1064.87}, "rubricPassRate": 0.35454545454545455, "analyticalQuality": {"elo": 941.31, "lower95ci": 923.5, "upper95ci": 958.64}, "presentation": {"elo": 1080.25, "lower95ci": 1063.75, "upper95ci": 1096.16}}, "timescaleData": {}, "performanceByPromptType": {"hundredK": {"medianOutputSpeed": 203.108245512815, "medianTimeToFirstChunk": 1.499173723, "medianTimeToFirstAnswerToken": 1.499173723, "medianEndToEndResponseTime": 3.9609152379128094}}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f73f4711-9c61-40a7-a258-b71c14727f53", "slug": "tulu3-405b", "name": "Llama 3.1 Tulu3 405B", "shortName": "Tulu3 405B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-01-30", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "tulu3-405b", "name": "Llama 3.1 Tulu3 405B"}, "deprecated": true, "deprecatedTo": "llama-3-3-instruct-70b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 405, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "LLAMA 3.1 COMMUNITY LICENSE AGREEMENT", "licenseUrl": "https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/allenai/Llama-3.1-Tulu-3-405B", "microevalsEnabled": false, "intelligenceIndex": 7.19889208713507, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0328, "gpqa": 0.516161616161616, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.291005291005291, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "ab6c5270-d7b9-4c09-92fe-62662618c631", "slug": "ai2", "name": "Allen Institute for AI", "logo": "/img/logos/ai2_small.svg", "color": "#F0529C", "country": "us", "url": "https://allenai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f74ea286-cd29-4eb4-af14-1389b19c21e5", "slug": "minimax-m2", "name": "MiniMax-M2", "shortName": "MiniMax-M2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-26", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "minimax-m2", "name": "MiniMax-M2"}, "deprecated": true, "deprecatedTo": "minimax-m2-1", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 230, "inferenceParametersActiveBillions": 10, "sizeClass": "large", "contextWindowTokens": 204800, "licenseName": "Modified MIT", "licenseUrl": "https://github.com/MiniMax-AI/MiniMax-M2/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "microevalsEnabled": false, "intelligenceIndex": 18.6256708551149, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -46.55, "omniscienceBreakdown": {"accuracy": 0.23233333333333334, "hallucinationRate": 0.9090316977854972}, "gdpval": null, "itBenchSre": null, "tau2": 0.868421052631579, "tauBanking": null, "terminalbenchHard": 0.257575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.643333333333333, "ifbench": 0.72312925170068, "hle": 0.136700648748842, "gpqa": 0.776767676767677, "critpt": 0.00857142857142857, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.826455026455027, "aime25": 0.783333333333333, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 1.2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5249999999999999, "price1mBlended7To2To1": 0.39, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.3088235294117647, "price1mBlended0To100To1": 0.3089108910891089, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 94.6882310904483, "medianTimeToFirstChunk": 1.69757985599992}, "outputSpeedVariance": {"p05": 65.4463490440549, "q25": 76.1895597311055, "median": 94.6882310904483, "q75": 107.7215068791, "p95": 122.379316316234}, "timeToFirstChunkVariance": {"p05": 1.32863521075011, "q25": 1.58019646474999, "median": 1.69757985599992, "q75": 1.81324939700011, "p95": 2.38296639440013}, "performanceByPromptType": {"long": {"medianOutputSpeed": 94.6882310904483, "medianTimeToFirstChunk": 1.69757985599992, "medianTimeToFirstAnswerToken": 22.819528982809096, "medianEndToEndResponseTime": 28.10001626451139}}, "endToEndResponseTime": {"input": 1.69757985599992, "reasoning": 21.121949126809177, "answer": 5.280487281702294, "total": 28.10001626451139}, "timeToFirstAnswerToken": {"input": 1.69757985599992, "reasoning": 21.121949126809177, "total": 22.819528982809096}, "performanceDataSource": {"type": "firstParty", "providerName": "MiniMax"}, "hostModelCount": 4, "creator": {"id": "a31a9071-6144-4dbb-92dc-2e02d653ecea", "slug": "minimax", "name": "MiniMax", "logo": "/img/logos/minimax_small.svg", "color": "#EB3568", "country": "cn", "url": "https://minimaxi.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f78138d6-2e04-4a84-919a-20d177cb6ff1", "slug": "jamba-reasoning-3b", "name": "Jamba Reasoning 3B", "shortName": "Jamba Reasoning 3B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-08", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "jamba-reasoning-3b", "name": "Jamba Reasoning 3B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 3, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 262000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/ai21labs/AI21-Jamba-Reasoning-3B", "microevalsEnabled": false, "intelligenceIndex": 5.66829948484426, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -57.7166666666667, "omniscienceBreakdown": {"accuracy": 0.067, "hallucinationRate": 0.6904251518399428}, "gdpval": null, "itBenchSre": null, "tau2": 0.157894736842105, "tauBanking": null, "terminalbenchHard": 0.00757575757575758, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.0633333333333333, "ifbench": 0.524489795918367, "hle": 0.0375347544022243, "gpqa": 0.333333333333333, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.20952380952381, "aime25": 0.106666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "6216c686-bc60-4dbb-9f25-83e9dba803d1", "slug": "ai21-labs", "name": "AI21 Labs", "logo": "/img/logos/ai21_small.svg", "color": "#d63864", "country": "il", "url": "https://www.ai21.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f7a4ea75-e548-4069-80d4-9be8bc7c009b", "slug": "glm-5-2", "name": "GLM-5.2 (max)", "shortName": "GLM-5.2 (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "glm-5-2", "name": "GLM-5.2"}, "deprecated": true, "deprecatedTo": "glm-5-3", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 753, "inferenceParametersActiveBillions": 40, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/zai-org/GLM-5.2", "microevalsEnabled": true, "intelligenceIndex": 34.0052322377545, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 33.66713315179837, "strategyAndOps": 31.051752815937093, "legal": 34.571871048531705, "healthcareAndMedical": 32.73121528247194, "engineering": 37.432218415119024, "economics": 45.87795344840902}, "omniscience": 4.43333333333333, "omniscienceBreakdown": {"accuracy": 0.24333333333333335, "hallucinationRate": 0.2629955947136564}, "mlcrOverall": 0.0722222222222222, "harveyLab": 0.909683022145028, "gdpPdfAllPass": 0.104, "gdpval": 1406.07, "gdpvalNormalized": 0.45303499999999997, "itBenchSre": 0.426553672316384, "tau2": 0.991228070175439, "tauBanking": 0.34639175257732, "terminalbenchHard": 0.507575757575758, "terminalBench21": 0.779026217228464, "terminalBench40": 0.0101010101010101, "scicode": 0.511574074074074, "lcr": 0.783333333333333, "ifbench": 0.733333333333333, "hle": 0.411492122335496, "gpqa": 0.894949494949495, "critpt": 0.208571428571429, "apexAgents": 0.337020648967552, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.2839897721005435, "enterpriseOpsGym": 0.42733512384362876, "price1mInputTokens": 1.4, "price1mOutputTokens": 4.4, "cacheHitPrice": 0.26, "cacheHitDiscountPercent": 0.8142857142857143, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 2.15, "price1mBlended7To2To1": 0.9019999999999999, "price1mBlended0To1To1": 2.9000000000000004, "price1mBlended100To1To1": 0.3117647058823529, "price1mBlended0To100To1": 1.4297029702970299, "intelligenceIndexTimePerTask": 860.8311782967395, "intelligenceIndexCost": {"total": 1559.051065645, "input": 777.776765245, "nonCacheInput": 22.4713594, "cacheRead": 476.65792869500007, "cacheWrite": 278.64747715, "output": 781.2743004000001, "reasoning": 692.3474052000001, "answer": 88.9268952}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.9648813120929373, "input": 0.6818863885552096, "nonCacheInput": 0.013477682489526825, "cacheRead": 0.44964710740613795, "cacheWrite": 0.2187615986595448, "output": 0.2829949235377277, "reasoning": 0.22323332437035828, "answer": 0.059761599167369436}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.2794802135884616}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.09702278391272727}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.026808277717199402}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.47096907159999996}, {"slug": "scicode", "weightedCostPerTask": 0.005536939097222223}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.017903486941612604}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.009927198399999998}, {"slug": "critpt", "weightedCostPerTask": 0.04823906228571429}, {"slug": "omniscience", "weightedCostPerTask": 0.0012884874500000002}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0077057911}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2048384609, "output": 177562341, "answer": 20210658, "reasoning": 157351683}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 50734.846447808704, "answer": 13582.181628947597, "output": 64317.0280767563}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1231.38, "lower95ci": 1225.72, "upper95ci": 1238.34}, "rubricPassRate": 0.3606060606060606, "analyticalQuality": {"elo": 1269.3, "lower95ci": 1257.48, "upper95ci": 1281.8}, "presentation": {"elo": 1262.7, "lower95ci": 1252.07, "upper95ci": 1274.4}}, "briefcaseTotalCost": 169.55132957700002, "timescaleData": {"medianOutputSpeed": 69.3183863744251, "medianTimeToFirstChunk": 8.21885546249996}, "outputSpeedVariance": {"p05": 55.2698912574142, "q25": 66.4738172931602, "median": 69.3183863744251, "q75": 73.8147144536063, "p95": 86.7321706352387}, "timeToFirstChunkVariance": {"p05": 3.24296418029999, "q25": 3.48402381400013, "median": 8.21885546249996, "q75": 9.47627104024997, "p95": 10.14465719235}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 72.8070487789286, "medianTimeToFirstChunk": 8.4910530635, "medianTimeToFirstAnswerToken": 35.960920796675154, "medianEndToEndResponseTime": 42.82838772996894}, "long": {"medianOutputSpeed": 69.3183863744251, "medianTimeToFirstChunk": 8.21885546249996, "medianTimeToFirstAnswerToken": 37.07122933625038, "medianEndToEndResponseTime": 44.28432280468799}, "hundredK": {"medianOutputSpeed": 90.8669695349309, "medianTimeToFirstChunk": 9.78528889749997, "medianTimeToFirstAnswerToken": 31.795486995183463, "medianEndToEndResponseTime": 37.29803651960434}, "mediumParallel": {"medianOutputSpeed": 67.1991039096123, "medianTimeToFirstChunk": 8.83383106149995, "medianTimeToFirstAnswerToken": 38.596132694125075, "medianEndToEndResponseTime": 46.03670810228136}}, "endToEndResponseTime": {"input": 8.21885546249996, "reasoning": 28.85237387375042, "answer": 7.213093468437605, "total": 44.28432280468799}, "timeToFirstAnswerToken": {"input": 8.21885546249996, "reasoning": 28.85237387375042, "total": 37.07122933625038}, "performanceDataSource": {"type": "firstParty", "providerName": "Z AI"}, "hostModelCount": 21, "creator": {"id": "67437eb6-7dc1-4e93-befd-22c8b8ec2065", "slug": "zai", "name": "Z AI", "logo": "/img/logos/zai_small.svg", "color": "#1c7ff8", "country": "cn", "url": "https://z.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f7d2fc3e-1f7b-405f-818c-07952a4af78f", "slug": "kimi-k3", "name": "Kimi K3 (max)", "shortName": "Kimi K3 (max)", "chartDefaultSelected": true, "chartHighlighted": true, "releaseDate": "2026-07-16", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "kimi-k3", "name": "Kimi K3"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 2800, "inferenceParametersActiveBillions": 104, "sizeClass": "large", "contextWindowTokens": 1048576, "licenseName": "Kimi K3 License", "licenseUrl": "https://huggingface.co/moonshotai/Kimi-K3/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/moonshotai/Kimi-K3", "microevalsEnabled": true, "intelligenceIndex": 43.7841729518782, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 46.89391098470186, "strategyAndOps": 50.47626941624067, "legal": 48.647627542730916, "healthcareAndMedical": 45.04705688458811, "engineering": 43.27116611841973, "economics": 53.39749152378746}, "omniscience": 19.7, "omniscienceBreakdown": {"accuracy": 0.47583333333333333, "hallucinationRate": 0.5319554848966613}, "mlcrOverall": 0.383333333333333, "harveyLab": 0.946446663771892, "gdpPdfAllPass": 0.22, "gdpval": 1547.63, "gdpvalNormalized": 0.523815, "itBenchSre": 0.476930320150659, "tau2": null, "tauBanking": 0.45979381443299, "terminalbenchHard": null, "terminalBench21": 0.850187265917603, "terminalBench40": 0.126262626262626, "scicode": 0.594907407407407, "lcr": 0.886666666666667, "ifbench": null, "hle": 0.468952734012975, "gpqa": 0.935353535353535, "critpt": 0.234285714285714, "apexAgents": 0.412979351032448, "mmmuPro": 0.805202312138728, "livecodebench": null, "aime25": null, "analystAgent": 0.3875, "automationBenchPartialScore": 0.5827297780015204, "enterpriseOpsGym": 0.45329752312742466, "price1mInputTokens": 3, "price1mOutputTokens": 15, "cacheHitPrice": 0.3, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 6, "price1mBlended7To2To1": 2.31, "price1mBlended0To1To1": 9, "price1mBlended100To1To1": 0.47058823529411764, "price1mBlended0To100To1": 3.118811881188119, "intelligenceIndexTimePerTask": 1285.5499754671625, "intelligenceIndexCost": {"total": 3658.0675385043187, "input": 1246.3665035043184, "nonCacheInput": 87.547077, "cacheRead": 715.8620619439646, "cacheWrite": 442.9573645603539, "output": 2411.701035, "reasoning": 2089.534725, "answer": 322.16631}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.0001323004425493, "input": 1.2733038189208699, "nonCacheInput": 0.0661781678374818, "cacheRead": 0.8018463373535905, "cacheWrite": 0.40527931372979753, "output": 0.7268284815216798, "reasoning": 0.4867969126902008, "answer": 0.24003156883147875}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 1.0102003664573502}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.21451724213415857}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.03164048708376542}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.5088442114308581}, {"slug": "scicode", "weightedCostPerTask": 0.006016669791666668}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.03936033975903614}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.064014921}, {"slug": "critpt", "weightedCostPerTask": 0.09018507428571428}, {"slug": "omniscience", "weightedCostPerTask": 0.019923866999999998}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.015429121500000002}]}, "canonicalIntelligenceIndexTokenCount": {"input": 2563041687, "output": 160780069, "answer": 21477754, "reasoning": 139302315}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 32453.12751268007, "answer": 16002.10458876525, "output": 48455.23210144532}, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 4, "transparencyMethodology": 3, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1488.1, "lower95ci": 1482.93, "upper95ci": 1494.46}, "rubricPassRate": 0.5097236438075742, "analyticalQuality": {"elo": 1651.95, "lower95ci": 1642.16, "upper95ci": 1663.52}, "presentation": {"elo": 1428.74, "lower95ci": 1418.46, "upper95ci": 1439.25}}, "briefcaseTotalCost": 612.8548889841259, "timescaleData": {"medianOutputSpeed": 36.8066443436354, "medianTimeToFirstChunk": 4.33747654900003}, "outputSpeedVariance": {"p05": 28.6328192917332, "q25": 32.6334842225897, "median": 36.8066443436354, "q75": 40.3158064967725, "p95": 45.5806068559057}, "timeToFirstChunkVariance": {"p05": 2.55900384280004, "q25": 3.55312903600001, "median": 4.33747654900003, "q75": 6.17032015749998, "p95": 9.30838537899999}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 38.4523639782006, "medianTimeToFirstChunk": 3.77310720550001, "medianTimeToFirstAnswerToken": 55.78551406646282, "medianEndToEndResponseTime": 68.78861578170351}, "long": {"medianOutputSpeed": 36.8066443436354, "medianTimeToFirstChunk": 4.33747654900003, "medianTimeToFirstAnswerToken": 58.675491754285645, "medianEndToEndResponseTime": 72.25999555560705}, "hundredK": {"medianOutputSpeed": 48.5858038970933, "medianTimeToFirstChunk": 9.58880844749996, "medianTimeToFirstAnswerToken": 50.753095946706125, "medianEndToEndResponseTime": 61.04416782150767}, "mediumParallel": {"medianOutputSpeed": 34.2788545985073, "medianTimeToFirstChunk": 3.00518560800003, "medianTimeToFirstAnswerToken": 61.350192272461086, "medianEndToEndResponseTime": 75.93644393857635}}, "endToEndResponseTime": {"input": 4.33747654900003, "reasoning": 54.338015205285615, "answer": 13.584503801321404, "total": 72.25999555560705}, "timeToFirstAnswerToken": {"input": 4.33747654900003, "reasoning": 54.338015205285615, "total": 58.675491754285645}, "performanceDataSource": {"type": "firstParty", "providerName": "Kimi"}, "hostModelCount": 17, "creator": {"id": "0a177021-87dd-4250-9a37-f01df196bfe0", "slug": "kimi", "name": "Kimi", "logo": "/img/logos/kimi.jpg", "color": "#047AFE", "country": "cn", "url": "https://www.moonshot.cn/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f818a7bb-6f23-4b24-8d52-6b9c1a5ca628", "slug": "olmo-2-7b", "name": "OLMo 2 7B", "shortName": "OLMo 2 7B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-11-26", "knowledgeCutoffDate": "2023-12-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "olmo-2-7b", "name": "OLMo 2 7B"}, "deprecated": true, "deprecatedTo": "olmo-3-7b-think", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 7.3, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 4096, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct", "microevalsEnabled": false, "intelligenceIndex": 5.57740289284295, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": 0, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.24421768707483, "hle": 0.0537534754402224, "gpqa": 0.287878787878788, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.0412698412698413, "aime25": 0.00666666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 88.88888888888889, "modelAvailability": 6, "transparencyMethodology": 6, "transparencyPostTrainingData": 2, "transparencyPreTrainingData": 2}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "ab6c5270-d7b9-4c09-92fe-62662618c631", "slug": "ai2", "name": "Allen Institute for AI", "logo": "/img/logos/ai2_small.svg", "color": "#F0529C", "country": "us", "url": "https://allenai.org/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f93d0750-b659-4ceb-a123-7e657904ef2b", "slug": "qwen3-vl-4b-reasoning", "name": "Qwen3 VL 4B (Reasoning)", "shortName": "Qwen3 VL 4B (Reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-14", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "qwen3-vl-4b", "name": "Qwen3 VL 4B (Reasoning)"}, "deprecated": true, "deprecatedTo": "qwen3-5-4b", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 4.44, "inferenceParametersActiveBillions": null, "sizeClass": "tiny", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-VL-4B-Thinking", "microevalsEnabled": false, "intelligenceIndex": 7.04880477911409, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -68.3833333333333, "omniscienceBreakdown": {"accuracy": 0.12216666666666667, "hallucinationRate": 0.9181697360926524}, "gdpval": null, "itBenchSre": null, "tau2": 0.154970760233918, "tauBanking": null, "terminalbenchHard": 0.0151515151515152, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.213333333333333, "ifbench": 0.365986394557823, "hle": 0.0458758109360519, "gpqa": 0.493939393939394, "critpt": 0, "apexAgents": null, "mmmuPro": 0.520231213872832, "livecodebench": 0.31957671957672, "aime25": 0.256666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 50, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0.5}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "f9739750-6d42-450f-ba1e-2f76c869b4fe", "slug": "quasar-438b", "name": "Quasar 438B (max, based on GLM-5.2)", "shortName": "Quasar 438B (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-08-10", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "quasar-438b", "name": "Quasar 438B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": 438, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 27.1275286607816, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 24.76332440687201, "strategyAndOps": 24.862012794704054, "legal": 27.017748110880767, "engineering": 29.572305685077975, "economics": 35.616311244979904}, "omniscience": -2.6, "omniscienceBreakdown": {"accuracy": 0.15516666666666667, "hallucinationRate": 0.21444071809035312}, "gdpPdfAllPass": 0.054, "gdpval": 1239.08, "gdpvalNormalized": 0.36954, "itBenchSre": null, "tau2": null, "tauBanking": 0.28659793814433, "terminalbenchHard": null, "terminalBench21": 0.692883895131086, "terminalBench40": 0.0101010101010101, "scicode": 0.481481481481481, "lcr": 0.763333333333333, "ifbench": null, "hle": 0.186746987951807, "gpqa": 0.732323232323232, "critpt": 0.0942857142857143, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.23864439593997933, "price1mInputTokens": 0.6, "price1mOutputTokens": 1.8, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.8999999999999999, "price1mBlended7To2To1": 0.72, "price1mBlended0To1To1": 1.2, "price1mBlended100To1To1": 0.6117647058823529, "price1mBlended0To100To1": 0.6118811881188119, "intelligenceIndexTimePerTask": 412.9432707084837, "intelligenceIndexCost": {"total": 2503.6975926, "input": 1825.8793272, "nonCacheInput": 13.454358, "cacheRead": 0, "cacheWrite": 1812.4249692, "output": 677.8182654, "reasoning": 622.437831, "answer": 55.380434400000006}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.024611832657714, "input": 1.894071417145625, "nonCacheInput": 0.010527316651972506, "cacheRead": 0, "cacheWrite": 1.8835441004936526, "output": 0.1305404155120891, "reasoning": 0.0960824386958299, "answer": 0.034457976816259187}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.564326648901099}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.1390296902727273}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.03696224388127854}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 1.21357738}, {"slug": "scicode", "weightedCostPerTask": 0.003209045416666667}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.019101952103799814}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.005408711399999999}, {"slug": "critpt", "weightedCostPerTask": 0.035755140857142854}, {"slug": "omniscience", "weightedCostPerTask": 0.002695990125}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.004545029700000001}]}, "canonicalIntelligenceIndexTokenCount": {"input": 3043132212, "output": 376565703, "answer": 30766908, "reasoning": 345798795}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 53379.13260879439, "answer": 19143.32045347732, "output": 72522.45306227171}, "briefcaseBreakdown": {"overall": {"elo": 1123.48, "lower95ci": 1113.5, "upper95ci": 1133.51}, "rubricPassRate": 0.3434343434343434, "analyticalQuality": {"elo": 1077.11, "lower95ci": 1060.34, "upper95ci": 1094.39}, "presentation": {"elo": 1184.1, "lower95ci": 1167.22, "upper95ci": 1201.48}}, "briefcaseTotalCost": 342.35816700000004, "timescaleData": {"medianOutputSpeed": 166.982085596115, "medianTimeToFirstChunk": 1.07683363199999}, "outputSpeedVariance": {"p05": 110.294372775623, "q25": 127.735141939688, "median": 166.982085596115, "q75": 215.010704145446, "p95": 249.305092773387}, "timeToFirstChunkVariance": {"p05": 0.850176166399978, "q25": 0.960692258000052, "median": 1.07683363199999, "q75": 1.27520612400002, "p95": 1.6942372287}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 147.22489917845, "medianTimeToFirstChunk": 0.671204853000006, "medianTimeToFirstAnswerToken": 14.255863502185548, "medianEndToEndResponseTime": 17.652028164481933}, "long": {"medianOutputSpeed": 166.982085596115, "medianTimeToFirstChunk": 1.07683363199999, "medianTimeToFirstAnswerToken": 13.054166367186117, "medianEndToEndResponseTime": 16.048499550982648}, "hundredK": {"medianOutputSpeed": 116.965702221576, "medianTimeToFirstChunk": 10.316043747, "medianTimeToFirstAnswerToken": 27.41507330877073, "medianEndToEndResponseTime": 31.68983069921341}, "mediumParallel": {"medianOutputSpeed": 120.478279804577, "medianTimeToFirstChunk": 0.56109974200001, "medianTimeToFirstAnswerToken": 17.161602365743644, "medianEndToEndResponseTime": 21.311728021679553}}, "endToEndResponseTime": {"input": 1.07683363199999, "reasoning": 11.977332735186126, "answer": 2.9943331837965315, "total": 16.048499550982648}, "timeToFirstAnswerToken": {"input": 1.07683363199999, "reasoning": 11.977332735186126, "total": 13.054166367186117}, "performanceDataSource": {"type": "firstParty", "providerName": "Multiverse Computing"}, "hostModelCount": 1, "creator": {"id": "7d59f244-cf07-4d56-8f28-e1f1379f31c8", "slug": "multiversecomputing", "name": "Multiverse Computing", "logo": "/img/logos/multiversecomputing_small.svg", "color": "#f11338", "country": "es", "url": "https://multiversecomputing.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fb112343-c82c-4b43-afea-996bd5101d62", "slug": "kat-coder-pro-v1", "name": "KAT-Coder-Pro V1", "shortName": "KAT-Coder-Pro V1", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-11", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "kat-coder-pro-v1", "name": "KAT-Coder-Pro V1"}, "deprecated": true, "deprecatedTo": "kat-coder-pro-v2", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 18.5862731794299, "intelligenceIndexIsEstimated": true, "capabilities": {"economics": 27.984312306919975}, "omniscience": -37.7333333333333, "omniscienceBreakdown": {"accuracy": 0.177, "hallucinationRate": 0.6735520453624949}, "gdpval": 845.3, "gdpvalNormalized": 0.17264999999999997, "itBenchSre": null, "tau2": 0.885964912280702, "tauBanking": null, "terminalbenchHard": 0.0909090909090909, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.386666666666667, "ifbench": 0.683673469387755, "hle": 0.336422613531047, "gpqa": 0.763636363636364, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.747089947089947, "aime25": 0.946666666666667, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "briefcaseBreakdown": {"overall": {"elo": 602.09, "lower95ci": 593.76, "upper95ci": 609.85}, "rubricPassRate": 0.13271604938271606, "analyticalQuality": {"elo": 457, "lower95ci": 442.03, "upper95ci": 471.83}, "presentation": {"elo": 603.45, "lower95ci": 588.01, "upper95ci": 619.7}}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "2703c169-86d9-406b-8be1-ae5be8177f3c", "slug": "kwaikat", "name": "KwaiKAT", "logo": "/img/logos/kwaikat_small.svg", "color": "#489034", "country": "cn", "url": "https://www.streamlake.ai/product/kat-coder"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fb65266f-5a7d-403c-85d5-ccdf0d1ca838", "slug": "deepseek-v3-1", "name": "DeepSeek V3.1 (Non-reasoning)", "shortName": "DeepSeek V3.1 (Non-reasoning)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-08-21", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "deepseek-v3-1", "name": "DeepSeek V3.1"}, "deprecated": true, "deprecatedTo": "deepseek-v3-1-terminus", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 685, "inferenceParametersActiveBillions": 37, "sizeClass": "large", "contextWindowTokens": 128000, "licenseName": "MIT", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V3.1", "microevalsEnabled": false, "intelligenceIndex": 13.707850604044, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -42.75, "omniscienceBreakdown": {"accuracy": 0.23133333333333334, "hallucinationRate": 0.8571118820468343}, "gdpval": null, "itBenchSre": null, "tau2": 0.347953216374269, "tauBanking": null, "terminalbenchHard": 0.242424242424242, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.47, "ifbench": 0.378231292517007, "hle": 0.0667284522706209, "gpqa": 0.735353535353535, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.576719576719577, "aime25": 0.496666666666667, "analystAgent": null, "price1mInputTokens": 0.5700000000000001, "price1mOutputTokens": 1.68, "cacheHitPrice": 0.5700000000000001, "cacheHitDiscountPercent": 0.48, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.8475, "price1mBlended7To2To1": 0.681, "price1mBlended0To1To1": 1.125, "price1mBlended100To1To1": 0.5808823529411765, "price1mBlended0To100To1": 0.5809900990099011, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 8, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fbc58677-e324-4b45-a979-7fd8eec555cd", "slug": "lfm2-24b-a2b", "name": "LFM2 24B A2B", "shortName": "LFM2 24B A2B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-25", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "lfm2-24b-a2b", "name": "LFM2 24B A2B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 23.8, "inferenceParametersActiveBillions": 2.3, "sizeClass": "small", "contextWindowTokens": 32768, "licenseName": "lfm 1.0", "licenseUrl": "https://huggingface.co/LiquidAI/LFM2-8B-A1B/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/LiquidAI/LFM2-24B-A2B", "microevalsEnabled": false, "intelligenceIndex": 5.94753271655266, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -58.1, "omniscienceBreakdown": {"accuracy": 0.06466666666666666, "hallucinationRate": 0.6903064861012117}, "gdpval": null, "itBenchSre": null, "tau2": 0.111111111111111, "tauBanking": null, "terminalbenchHard": 0, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0, "ifbench": 0.458503401360544, "hle": 0.0421686746987952, "gpqa": 0.473737373737374, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "openness": {"opennessIndex": 27.77777777777778, "modelAvailability": 4, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "5b1886c4-43ba-4007-b840-9d21a2b7d42c", "slug": "liquidai", "name": "Liquid AI", "logo": "/img/logos/liquidai_small.svg", "color": "#000000", "country": "us", "url": "https://www.liquid.ai"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fbdf8da1-b341-448c-b3cb-8aff1d8f70b9", "slug": "nova-2-0-lite-reasoning-medium", "name": "Nova 2.0 Lite (medium)", "shortName": "Nova 2.0 Lite (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-10-29", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "nova-2-0-lite", "name": "Nova 2.0 Lite"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 12.4823794919822, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -56.9666666666667, "omniscienceBreakdown": {"accuracy": 0.18166666666666667, "hallucinationRate": 0.9181262729124237}, "gdpval": null, "itBenchSre": null, "tau2": 0.757309941520468, "tauBanking": null, "terminalbenchHard": 0.174242424242424, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.6, "ifbench": 0.685034013605442, "hle": 0.0898980537534754, "gpqa": 0.767676767676768, "critpt": 0, "apexAgents": null, "mmmuPro": 0.625433526011561, "livecodebench": 0.663492063492063, "aime25": 0.886666666666667, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 2.5, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0.42, "price1mBlended0To3To1": 0.85, "price1mBlended7To2To1": 0.52, "price1mBlended0To1To1": 1.4, "price1mBlended100To1To1": 0.32156862745098036, "price1mBlended0To100To1": 0.3217821782178218, "timescaleData": {"medianOutputSpeed": 166.993420574022, "medianTimeToFirstChunk": 17.5018777005001}, "outputSpeedVariance": {"p05": 124.817052720436, "q25": 136.707261053755, "median": 166.993420574022, "q75": 203.511739440365, "p95": 277.62595829382}, "timeToFirstChunkVariance": {"p05": 8.04621464549998, "q25": 11.564904047, "median": 17.5018777005001, "q75": 22.40034272025, "p95": 40.1860410716501}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 191.432951851931, "medianTimeToFirstChunk": 12.1210798640001, "medianTimeToFirstAnswerToken": 22.568601989380866, "medianEndToEndResponseTime": 25.18048252072606}, "long": {"medianOutputSpeed": 166.993420574022, "medianTimeToFirstChunk": 17.5018777005001, "medianTimeToFirstAnswerToken": 29.478397452746712, "medianEndToEndResponseTime": 32.47252739080837}, "hundredK": {"medianOutputSpeed": 150.585599650327, "medianTimeToFirstChunk": 19.0646968045001, "medianTimeToFirstAnswerToken": 32.346179261283325, "medianEndToEndResponseTime": 35.666549875479134}, "mediumParallel": {"medianOutputSpeed": 213.037927354456, "medianTimeToFirstChunk": 17.868298124, "medianTimeToFirstAnswerToken": 27.256297832954957, "medianEndToEndResponseTime": 29.603297760193694}}, "endToEndResponseTime": {"input": 17.5018777005001, "reasoning": 11.976519752246611, "answer": 2.994129938061653, "total": 32.47252739080837}, "timeToFirstAnswerToken": {"input": 17.5018777005001, "reasoning": 11.976519752246611, "total": 29.478397452746712}, "performanceDataSource": {"type": "firstParty", "providerName": "Amazon"}, "hostModelCount": 1, "creator": {"id": "bb5a4e55-7969-4ab4-8702-3b9fd6547dc2", "slug": "aws", "name": "Amazon", "logo": "/img/logos/aws_small.svg", "color": "#FF9900", "country": "us", "url": "https://aws.amazon.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fc4223e8-4586-4ca1-97ca-bb55ff586947", "slug": "kat-coder-pro-v2", "name": "KAT Coder Pro V2", "shortName": "KAT-Coder-Pro V2", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-03-27", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "kat-coder-pro-v2", "name": "KAT Coder Pro V2"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 21.7045082420985, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -22.4666666666667, "omniscienceBreakdown": {"accuracy": 0.21483333333333332, "hallucinationRate": 0.5597537677775419}, "gdpval": 843.25, "gdpvalNormalized": 0.171625, "itBenchSre": null, "tau2": 0.894736842105263, "tauBanking": 0.045360824742268, "terminalbenchHard": 0.492424242424242, "terminalBench21": 0.700374531835206, "terminalBench40": null, "scicode": null, "lcr": 0.73, "ifbench": 0.666666666666667, "hle": 0.161260426320667, "gpqa": 0.854545454545454, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.06, "cacheHitDiscountPercent": 0.8, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5249999999999999, "price1mBlended7To2To1": 0.22199999999999998, "price1mBlended0To1To1": 0.75, "price1mBlended100To1To1": 0.07352941176470588, "price1mBlended0To100To1": 0.3089108910891089, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "2703c169-86d9-406b-8be1-ae5be8177f3c", "slug": "kwaikat", "name": "KwaiKAT", "logo": "/img/logos/kwaikat_small.svg", "color": "#489034", "country": "cn", "url": "https://www.streamlake.ai/product/kat-coder"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fc92f822-04b7-420d-9c07-a21af5e9aac7", "slug": "qwen3-coder-next", "name": "Qwen3 Coder Next", "shortName": "Qwen3 Coder Next", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-02-03", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "qwen3-coder-next", "name": "Qwen3 Coder Next"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 79.7, "inferenceParametersActiveBillions": 3, "sizeClass": "medium", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/Qwen/Qwen3-Coder-Next", "microevalsEnabled": true, "intelligenceIndex": 10.0530720321917, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 8.920318159958269, "strategyAndOps": 6.961950544595012, "legal": 9.366847157351565, "engineering": 10.008792817423545, "economics": 13.036337407321605}, "omniscience": -62.4, "omniscienceBreakdown": {"accuracy": 0.1615, "hallucinationRate": 0.9367918902802623}, "gdpPdfAllPass": 0.026, "gdpval": 664.31, "gdpvalNormalized": 0.08215499999999998, "itBenchSre": null, "tau2": 0.795321637426901, "tauBanking": 0.0536082474226804, "terminalbenchHard": 0.181818181818182, "terminalBench21": 0.382022471910112, "terminalBench40": 0, "scicode": 0.362268518518519, "lcr": 0.47, "ifbench": 0.352380952380952, "hle": 0.101482854494903, "gpqa": 0.737373737373737, "critpt": 0, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.010593550691766297, "price1mInputTokens": 0.35, "price1mOutputTokens": 1.2, "cacheHitPrice": 0.35, "cacheHitDiscountPercent": 0.41666666666666663, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.5625, "price1mBlended7To2To1": 0.43499999999999994, "price1mBlended0To1To1": 0.7749999999999999, "price1mBlended100To1To1": 0.3583333333333334, "price1mBlended0To100To1": 0.35841584158415846, "intelligenceIndexTimePerTask": 138.53949929378237, "intelligenceIndexCost": {"total": 476.03205395000003, "input": 435.26912555, "nonCacheInput": 5.76517445, "cacheRead": 0, "cacheWrite": 429.5039511, "output": 40.7629284, "reasoning": 0, "answer": 40.7629284}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.5517146290167634, "input": 0.5335468961430659, "nonCacheInput": 0.0035746843854585005, "cacheRead": 0, "cacheWrite": 0.5299722117576076, "output": 0.0181677328736971, "reasoning": 0, "answer": 0.0181677328736971}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.22871088049450547}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.028516177090909086}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.004247320011415525}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.2833180543181818}, {"slug": "scicode", "weightedCostPerTask": 0.0002522740277777778}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.0010857972914735865}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.0016222275999999997}, {"slug": "critpt", "weightedCostPerTask": 0.001988538}, {"slug": "omniscience", "weightedCostPerTask": 1.64872825e-05}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0019568729}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1243626073, "output": 33969107, "answer": 33969107, "reasoning": 0}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 0, "answer": 15139.777394747589, "output": 15139.777394747589}, "openness": {"opennessIndex": 41.666666666666664, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0.5, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 413.75, "lower95ci": 403.65, "upper95ci": 423.69}, "rubricPassRate": 0.07867494824016563, "analyticalQuality": {"elo": 214.27, "lower95ci": 194.76, "upper95ci": 233.9}, "presentation": {"elo": 378.02, "lower95ci": 359.23, "upper95ci": 396.74}}, "briefcaseTotalCost": 138.75126749999998, "timescaleData": {"medianOutputSpeed": 104.562894620083, "medianTimeToFirstChunk": 1.22740057299995}, "outputSpeedVariance": {"p05": 34.8958802747396, "q25": 67.6912202066471, "median": 104.562894620083, "q75": 162.584682739597, "p95": 206.577879929971}, "timeToFirstChunkVariance": {"p05": 0.876908664999974, "q25": 0.996768347, "median": 1.22740057299995, "q75": 2.55915900550008, "p95": 4.05796938050003}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 102.121573836904, "medianTimeToFirstChunk": 0.915534075999972, "medianTimeToFirstAnswerToken": 0.915534075999972, "medianEndToEndResponseTime": 5.811659167046241}, "long": {"medianOutputSpeed": 104.562894620083, "medianTimeToFirstChunk": 1.22740057299995, "medianTimeToFirstAnswerToken": 1.22740057299995, "medianEndToEndResponseTime": 6.009211576001457}, "hundredK": {"medianOutputSpeed": 130.167284369666, "medianTimeToFirstChunk": 3.70494796949998, "medianTimeToFirstAnswerToken": 3.70494796949998, "medianEndToEndResponseTime": 7.546158934461306}, "mediumParallel": {"medianOutputSpeed": 100.268639961017, "medianTimeToFirstChunk": 1.3035796675, "medianTimeToFirstAnswerToken": 1.3035796675, "medianEndToEndResponseTime": 6.290183656487911}}, "endToEndResponseTime": {"input": 1.22740057299995, "reasoning": 0, "answer": 4.781811003001507, "total": 6.009211576001457}, "timeToFirstAnswerToken": {"input": 1.22740057299995, "reasoning": 0, "total": 1.22740057299995}, "performanceDataSource": {"type": "median"}, "hostModelCount": 4, "creator": {"id": "d874d370-74d3-4fa0-ba00-5272f92f946b", "slug": "alibaba", "name": "Alibaba", "logo": "/img/logos/alibaba_small.svg", "color": "#ff7018", "country": "cn", "url": "https://www.alibabacloud.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fd4454ff-e703-46c0-a7f5-fa69af09486d", "slug": "gpt-5-1-codex-mini", "name": "GPT-5.1 Codex mini (high)", "shortName": "GPT-5.1 Codex mini (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-11-13", "knowledgeCutoffDate": "2024-09-30", "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "gpt-5-1-codex-mini", "name": "GPT-5.1 Codex mini"}, "deprecated": true, "deprecatedTo": "gpt-5-2-codex", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 400000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 20.3781988302265, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -16.4166666666667, "omniscienceBreakdown": {"accuracy": 0.232, "hallucinationRate": 0.5158420138888888}, "gdpval": null, "itBenchSre": null, "tau2": 0.628654970760234, "tauBanking": null, "terminalbenchHard": 0.333333333333333, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.666666666666667, "ifbench": 0.67891156462585, "hle": 0.184893419833179, "gpqa": 0.813131313131313, "critpt": 0, "apexAgents": null, "mmmuPro": 0.690173410404624, "livecodebench": 0.835978835978836, "aime25": 0.916666666666667, "analystAgent": null, "price1mInputTokens": 0.25, "price1mOutputTokens": 2, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.6875, "price1mBlended7To2To1": 0.425, "price1mBlended0To1To1": 1.125, "price1mBlended100To1To1": 0.26715686274509803, "price1mBlended0To100To1": 0.26732673267326734, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "e67e56e3-15cd-43db-b679-da4660a69f41", "slug": "openai", "name": "OpenAI", "logo": "/img/logos/openai_small.svg", "color": "#1f1f1f", "country": "us", "url": "https://openai.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fddb72bd-60d3-41af-acc5-3df9a290eb8e", "slug": "gemini-2-0-flash-experimental", "name": "Gemini 2.0 Flash (experimental)", "shortName": "Gemini 2.0 Flash (exp)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2024-12-11", "knowledgeCutoffDate": "2024-08-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "gemini-2-0-flash-experimental", "name": "Gemini 2.0 Flash (experimental)"}, "deprecated": true, "deprecatedTo": "gemini-2-0-flash", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": null, "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 8.21731795326663, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0407, "gpqa": 0.636363636363636, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.20952380952381, "aime25": null, "analystAgent": null, "price1mInputTokens": 0, "price1mOutputTokens": 0, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": 0, "price1mBlended0To3To1": 0, "price1mBlended7To2To1": 0, "price1mBlended0To1To1": 0, "price1mBlended100To1To1": 0, "price1mBlended0To100To1": 0, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "firstParty", "providerName": "Google"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fe11ab6c-a4dd-4c28-9fef-07da76d5ed14", "slug": "llama-65b", "name": "Llama 65B", "shortName": "Llama 65B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-02-24", "knowledgeCutoffDate": null, "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-65b", "name": "Llama 65B"}, "deprecated": true, "deprecatedTo": "llama-3-instruct-70b", "isOpenWeights": true, "openSourceCategorization": "non-commercial", "parameters": 65, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 2048, "licenseName": "LLaMA LICENSE AGREEMENT", "licenseUrl": "https://huggingface.co/huggyllama/llama-65b/blob/main/LICENSE", "modelWeightsSourceUrl": "https://huggingface.co/huggyllama/llama-65b", "microevalsEnabled": false, "intelligenceIndex": 5.03498213171439, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": null, "gpqa": null, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": null, "price1mOutputTokens": null, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": null, "price1mBlended7To2To1": null, "price1mBlended0To1To1": null, "price1mBlended100To1To1": null, "price1mBlended0To100To1": null, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 0, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fe2c2289-d261-4433-8681-46448372c1f6", "slug": "grok-4-3-low", "name": "Grok 4.3 (low)", "shortName": "Grok 4.3 (low)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-04-30", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "low", "label": "low", "level": 20}, "release": {"slug": "grok-4-3", "name": "Grok 4.3"}, "deprecated": true, "deprecatedTo": "grok-4-6-low", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": true, "intelligenceIndex": 24.2958998564863, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": 13.9333333333333, "omniscienceBreakdown": {"accuracy": 0.2668333333333333, "hallucinationRate": 0.1739031598090475}, "gdpval": null, "itBenchSre": null, "tau2": 0.888888888888889, "tauBanking": null, "terminalbenchHard": 0.265151515151515, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.74, "ifbench": 0.80952380952381, "hle": 0.183503243744208, "gpqa": 0.843434343434343, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": 0.727745664739884, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 1.25, "price1mOutputTokens": 2.5, "cacheHitPrice": 0.2, "cacheHitDiscountPercent": 0.84, "cacheWritePrice": 1.25, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 1.5625, "price1mBlended7To2To1": 0.64, "price1mBlended0To1To1": 1.875, "price1mBlended100To1To1": 0.23284313725490197, "price1mBlended0To100To1": 1.2623762376237624, "timescaleData": {"medianOutputSpeed": 101.455969679525, "medianTimeToFirstChunk": 4.54580336250001}, "outputSpeedVariance": {"p05": 84.7223674104686, "q25": 91.2214457636869, "median": 101.455969679525, "q75": 135.14809192413, "p95": 144.801035560597}, "timeToFirstChunkVariance": {"p05": 3.14715168419993, "q25": 3.61356407825002, "median": 4.54580336250001, "q75": 8.79535963049999, "p95": 12.8387601373501}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 118.391000777602, "medianTimeToFirstChunk": 6.81807906800003, "medianTimeToFirstAnswerToken": 6.81807906800003, "medianEndToEndResponseTime": 11.041373040649624}, "long": {"medianOutputSpeed": 101.455969679525, "medianTimeToFirstChunk": 4.54580336250001, "medianTimeToFirstAnswerToken": 4.54580336250001, "medianEndToEndResponseTime": 9.474049591670948}, "hundredK": {"medianOutputSpeed": 100.249542738512, "medianTimeToFirstChunk": 10.6003186645, "medianTimeToFirstAnswerToken": 10.6003186645, "medianEndToEndResponseTime": 15.587872585859875}, "mediumParallel": {"medianOutputSpeed": 96.5573069199833, "medianTimeToFirstChunk": 9.37244376499996, "medianTimeToFirstAnswerToken": 9.37244376499996, "medianEndToEndResponseTime": 14.550715777229426}}, "endToEndResponseTime": {"input": 4.54580336250001, "reasoning": 0, "answer": 4.928246229170937, "total": 9.474049591670948}, "timeToFirstAnswerToken": {"input": 4.54580336250001, "reasoning": 0, "total": 4.54580336250001}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 3, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "fe4c0848-e284-4e52-a79d-cdc28392f1a9", "slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash 0731 (Reasoning, Max Effort)", "shortName": "DeepSeek V4 Flash 0731 (max)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-31", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "max", "label": "max", "level": 60}, "release": {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash 0731"}, "deprecated": true, "deprecatedTo": "deepseek-v4-1-flash", "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 284, "inferenceParametersActiveBillions": 13, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": "Mit", "licenseUrl": "https://opensource.org/license/mit", "modelWeightsSourceUrl": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731", "microevalsEnabled": true, "intelligenceIndex": 34.5281879347816, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 37.51866625291248, "strategyAndOps": 43.13331051359192, "legal": 37.70448907880834, "healthcareAndMedical": 35.431417827284186, "engineering": 34.9593786340166, "economics": 40.320871736947794}, "omniscience": -14.2833333333333, "omniscienceBreakdown": {"accuracy": 0.4038333333333333, "hallucinationRate": 0.9169695275370422}, "mlcrOverall": 0.133333333333333, "gdpPdfAllPass": 0.11, "gdpval": 1441.89, "gdpvalNormalized": 0.47094500000000006, "itBenchSre": null, "tau2": null, "tauBanking": 0.393814432989691, "terminalbenchHard": null, "terminalBench21": 0.786516853932584, "terminalBench40": 0.121212121212121, "scicode": 0.503472222222222, "lcr": 0.796666666666667, "ifbench": null, "hle": 0.385542168674699, "gpqa": 0.908080808080808, "critpt": 0.165714285714286, "apexAgents": null, "mmmuPro": null, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5396771855133674, "price1mInputTokens": 0.44, "price1mOutputTokens": 1.32, "cacheHitPrice": 0.014, "cacheHitDiscountPercent": 0.9681818181818181, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.66, "price1mBlended7To2To1": 0.2298, "price1mBlended0To1To1": 0.88, "price1mBlended100To1To1": 0.030980392156862747, "price1mBlended0To100To1": 0.4487128712871287, "intelligenceIndexTimePerTask": 212.38644268283716, "intelligenceIndexCost": {"total": 474.192204864049, "input": 154.309158744049, "nonCacheInput": 6.94658712, "cacheRead": 57.35814476578243, "cacheWrite": 90.00442685826658, "output": 319.88304612, "reasoning": 287.17127868, "answer": 32.71176744}, "intelligenceIndexCostPerTask": {"cost": {"total": 0.21964484501171036, "input": 0.13773301243426306, "nonCacheInput": 0.0038170423547304677, "cacheRead": 0.06069836367576961, "cacheWrite": 0.07321760640376299, "output": 0.08191183257744733, "reasoning": 0.0600322073002369, "answer": 0.021879625277210428}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.06350738986050165}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.02898553535023347}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.005267885806198829}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.09188874552229055}, {"slug": "scicode", "weightedCostPerTask": 0.004223046819444445}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.004288044793327154}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.00465597088}, {"slug": "critpt", "weightedCostPerTask": 0.011452343885714289}, {"slug": "omniscience", "weightedCostPerTask": 0.002997548994}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.0023783331}]}, "canonicalIntelligenceIndexTokenCount": {"input": 4317353554, "output": 242335641, "answer": 24781642, "reasoning": 217553999}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 45478.944924421885, "answer": 16575.47369485638, "output": 62054.418619278265}, "openness": {"opennessIndex": 44.44444444444444, "modelAvailability": 6, "transparencyMethodology": 2, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "briefcaseBreakdown": {"overall": {"elo": 1253.08, "lower95ci": 1246.98, "upper95ci": 1259.58}, "rubricPassRate": 0.41515151515151516, "analyticalQuality": {"elo": 1341.07, "lower95ci": 1329.8, "upper95ci": 1352.86}, "presentation": {"elo": 1187.03, "lower95ci": 1176.53, "upper95ci": 1198.59}}, "briefcaseTotalCost": 38.527816515371, "timescaleData": {"medianOutputSpeed": 220.465103939663, "medianTimeToFirstChunk": 1.44728312799998}, "outputSpeedVariance": {"p05": 183.689130919508, "q25": 203.131561859465, "median": 220.465103939663, "q75": 242.457235254591, "p95": 259.675114598179}, "timeToFirstChunkVariance": {"p05": 0.820860087900053, "q25": 0.930022054999995, "median": 1.44728312799998, "q75": 1.61736685150004, "p95": 1.9473596931998}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 225.35514586508, "medianTimeToFirstChunk": 0.880391564000007, "medianTimeToFirstAnswerToken": 9.755272110093234, "medianEndToEndResponseTime": 11.973992246616541}, "long": {"medianOutputSpeed": 220.465103939663, "medianTimeToFirstChunk": 1.44728312799998, "medianTimeToFirstAnswerToken": 10.51901359354958, "medianEndToEndResponseTime": 12.786946209936978}, "hundredK": {"medianOutputSpeed": 211.111620054584, "medianTimeToFirstChunk": 3.99939835299998, "medianTimeToFirstAnswerToken": 13.473059724566784, "medianEndToEndResponseTime": 15.841475067458484}, "mediumParallel": {"medianOutputSpeed": 212.432597883093, "medianTimeToFirstChunk": 0.933893664000038, "medianTimeToFirstAnswerToken": 10.348644601145054, "medianEndToEndResponseTime": 12.702332335431308}}, "endToEndResponseTime": {"input": 1.44728312799998, "reasoning": 9.0717304655496, "answer": 2.2679326163874, "total": 12.786946209936978}, "timeToFirstAnswerToken": {"input": 1.44728312799998, "reasoning": 9.0717304655496, "total": 10.51901359354958}, "performanceDataSource": {"type": "firstParty", "providerName": "DeepSeek"}, "hostModelCount": 18, "creator": {"id": "58b835bf-4c87-4f87-a846-df4b692c6e7d", "slug": "deepseek", "name": "DeepSeek", "logo": "/img/logos/deepseek_small.svg", "color": "#2243e6", "country": "cn", "url": "https://www.deepseek.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "feb02d3b-ff8d-4ed4-b165-13f8d4a7192c", "slug": "gemma-4-12b", "name": "Gemma 4 12B (Reasoning)", "shortName": "Gemma 4 12B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-06-03", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "release": {"slug": "gemma-4-12b", "name": "Gemma 4 12B"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": true, "openSourceCategorization": "permissive", "parameters": 12, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 256000, "licenseName": "Apache 2.0", "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0", "modelWeightsSourceUrl": "https://huggingface.co/google/gemma-4-12B-it/tree/main", "microevalsEnabled": false, "intelligenceIndex": 14.1847516647736, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -52.7166666666667, "omniscienceBreakdown": {"accuracy": 0.15616666666666668, "hallucinationRate": 0.8097965633023899}, "gdpval": 590.73, "gdpvalNormalized": 0.04536500000000001, "itBenchSre": null, "tau2": 0.362573099415205, "tauBanking": null, "terminalbenchHard": 0.181818181818182, "terminalBench21": 0.273408239700375, "terminalBench40": null, "scicode": null, "lcr": 0.636666666666667, "ifbench": 0.735374149659864, "hle": 0.156626506024096, "gpqa": 0.752525252525252, "critpt": 0, "apexAgents": null, "mmmuPro": 0.696531791907514, "livecodebench": null, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.1, "price1mOutputTokens": 0.3, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.15000000000000002, "price1mBlended7To2To1": 0.12000000000000002, "price1mBlended0To1To1": 0.2, "price1mBlended100To1To1": 0.10196078431372549, "price1mBlended0To100To1": 0.10198019801980199, "openness": {"opennessIndex": 38.888888888888886, "modelAvailability": 6, "transparencyMethodology": 1, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 111.880270901269, "medianTimeToFirstChunk": 2.42757214549999}, "outputSpeedVariance": {"p05": 99.5375187455471, "q25": 104.692774124719, "median": 111.880270901269, "q75": 117.907724437907, "p95": 126.554791957864}, "timeToFirstChunkVariance": {"p05": 1.82663119169987, "q25": 2.33528261825001, "median": 2.42757214549999, "q75": 2.53072309049998, "p95": 2.63947092389989}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 130.713626286201, "medianTimeToFirstChunk": 1.38646449700002, "medianTimeToFirstAnswerToken": 16.68708813375038, "medianEndToEndResponseTime": 20.51224404293797}, "long": {"medianOutputSpeed": 111.880270901269, "medianTimeToFirstChunk": 2.42757214549999, "medianTimeToFirstAnswerToken": 20.30382489219686, "medianEndToEndResponseTime": 24.77288807887108}, "hundredK": {"medianOutputSpeed": 43.7055903290282, "medianTimeToFirstChunk": 13.6027497795, "medianTimeToFirstAnswerToken": 59.36348621947089, "medianEndToEndResponseTime": 70.80367032946361}, "mediumParallel": {"medianOutputSpeed": 117.665100749737, "medianTimeToFirstChunk": 1.95966423200002, "medianTimeToFirstAnswerToken": 18.95705757341073, "medianEndToEndResponseTime": 23.206405908763408}}, "endToEndResponseTime": {"input": 2.42757214549999, "reasoning": 17.87625274669687, "answer": 4.469063186674218, "total": 24.77288807887108}, "timeToFirstAnswerToken": {"input": 2.42757214549999, "reasoning": 17.87625274669687, "total": 20.30382489219686}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "faddc6d9-2c14-445f-9b28-56726f59c793", "slug": "google", "name": "Google", "logo": "/img/logos/google_small.svg", "color": "#34A853", "country": "us", "url": "https://deepmind.google/technologies/gemini/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": true, "inputModalityVideo": true, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ff51be8f-e362-4a7e-9043-687ba15de207", "slug": "claude-opus-5-medium", "name": "Claude Opus 5 (Adaptive Reasoning, Medium Effort)", "shortName": "Claude Opus 5 (medium)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2026-07-24", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 0, "effort": {"slug": "medium", "label": "medium", "level": 30}, "release": {"slug": "claude-opus-5", "name": "Claude Opus 5"}, "deprecated": false, "deprecatedTo": null, "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "large", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 45.0575765420613, "intelligenceIndexIsEstimated": false, "capabilities": {"financeAndAccounting": 49.40590122958589, "strategyAndOps": 51.51676843950026, "legal": 52.019786912643866, "healthcareAndMedical": 50.02128208922334, "engineering": 47.666205120318104, "economics": 56.22106168906393}, "omniscience": 31.0166666666667, "omniscienceBreakdown": {"accuracy": 0.5706666666666667, "hallucinationRate": 0.6067546583850931}, "mlcrOverall": 0.561111111111111, "gdpPdfAllPass": 0.2, "gdpval": 1524.87, "gdpvalNormalized": 0.512435, "itBenchSre": null, "tau2": null, "tauBanking": 0.385567010309278, "terminalbenchHard": null, "terminalBench21": 0.861423220973783, "terminalBench40": 0.343434343434343, "scicode": 0.515046296296296, "lcr": 0.82, "ifbench": null, "hle": 0.512974976830398, "gpqa": 0.919191919191919, "critpt": 0.268571428571429, "apexAgents": null, "mmmuPro": 0.816184971098266, "livecodebench": null, "aime25": null, "analystAgent": null, "automationBenchPartialScore": 0.5433925431990897, "price1mInputTokens": 5, "price1mOutputTokens": 25, "cacheHitPrice": 0.5, "cacheHitDiscountPercent": 0.9, "cacheWritePrice": 6.25, "pricePer1k1mpImages": 6.86, "price1mBlended0To3To1": 10, "price1mBlended7To2To1": 3.85, "price1mBlended0To1To1": 15, "price1mBlended100To1To1": 0.7843137254901961, "price1mBlended0To100To1": 5.198019801980198, "intelligenceIndexTimePerTask": 335.1071765348904, "intelligenceIndexCost": {"total": 2731.91350481435, "input": 1496.5757048143496, "nonCacheInput": 176.738925, "cacheRead": 859.9063343639696, "cacheWrite": 459.9304454503799, "output": 1235.3378, "reasoning": 702.53945, "answer": 532.79835}, "intelligenceIndexCostPerTask": {"cost": {"total": 2.1894793086538695, "input": 1.4650453890215214, "nonCacheInput": 0.12890489719342937, "cacheRead": 1.0087253194992214, "cacheWrite": 0.32741517232887046, "output": 0.7244339196323479, "reasoning": 0.371722431024414, "answer": 0.3527114886079339}, "evaluations": [{"slug": "aa-briefcase", "weightedCostPerTask": 0.7873853240624725}, {"slug": "gdpval-aa", "weightedCostPerTask": 0.13640985801687963}, {"slug": "automationbench-aa", "weightedCostPerTask": 0.04761634677068585}, {"slug": "terminalbench-4-0", "weightedCostPerTask": 0.9182378646654077}, {"slug": "scicode", "weightedCostPerTask": 0.0036927725694444447}, {"slug": "humanitys-last-exam", "weightedCostPerTask": 0.018695621640407785}, {"slug": "gdp-pdf", "weightedCostPerTask": 0.09929716000000001}, {"slug": "critpt", "weightedCostPerTask": 0.14033117142857143}, {"slug": "omniscience", "weightedCostPerTask": 0.0009256194999999999}, {"slug": "artificial-analysis-long-context-reasoning", "weightedCostPerTask": 0.036887569999999995}]}, "canonicalIntelligenceIndexTokenCount": {"input": 1828749325, "output": 49413512, "answer": 21311934, "reasoning": 28101578}, "intelligenceIndexOutputTokensPerTask": {"reasoning": 14868.897240976565, "answer": 14108.459544317355, "output": 28977.35678529392}, "briefcaseBreakdown": {"overall": {"elo": 1439.04, "lower95ci": 1433.25, "upper95ci": 1445.84}, "rubricPassRate": 0.48484848484848486, "analyticalQuality": {"elo": 1648.2, "lower95ci": 1636.86, "upper95ci": 1660.79}, "presentation": {"elo": 1312.11, "lower95ci": 1300.48, "upper95ci": 1324.39}}, "briefcaseTotalCost": 477.68042993123333, "timescaleData": {"medianOutputSpeed": 52.9055511581054, "medianTimeToFirstChunk": 5.32386102200008}, "outputSpeedVariance": {"p05": 42.2122091170922, "q25": 44.792424240764, "median": 52.9055511581054, "q75": 64.4024951582274, "p95": 71.9279985272897}, "timeToFirstChunkVariance": {"p05": 1.58248794409993, "q25": 3.48660445399998, "median": 5.32386102200008, "q75": 15.02084802375, "p95": 20.90648496905}, "performanceByPromptType": {"medium": {"medianOutputSpeed": 54.9514687156848, "medianTimeToFirstChunk": 9.2278589465, "medianTimeToFirstAnswerToken": 9.2278589465, "medianEndToEndResponseTime": 18.326796821790765}, "long": {"medianOutputSpeed": 52.9055511581054, "medianTimeToFirstChunk": 5.32386102200008, "medianTimeToFirstAnswerToken": 5.32386102200008, "medianEndToEndResponseTime": 14.77466512582232}, "hundredK": {"medianOutputSpeed": 59.8551257016791, "medianTimeToFirstChunk": 6.40570946200003, "medianTimeToFirstAnswerToken": 6.40570946200003, "medianEndToEndResponseTime": 14.75921292788572}, "mediumParallel": {"medianOutputSpeed": 48.4767071193132, "medianTimeToFirstChunk": 10.9454592765, "medianTimeToFirstAnswerToken": 10.9454592765, "medianEndToEndResponseTime": 21.259691197603388}}, "endToEndResponseTime": {"input": 5.32386102200008, "reasoning": 0, "answer": 9.45080410382224, "total": 14.77466512582232}, "timeToFirstAnswerToken": {"input": 5.32386102200008, "reasoning": 0, "total": 5.32386102200008}, "performanceDataSource": {"type": "firstParty", "providerName": "Anthropic"}, "hostModelCount": 3, "creator": {"id": "f0aa413f-e8ae-4fcd-9c48-0e049f4f3128", "slug": "anthropic", "name": "Anthropic", "logo": "/img/logos/anthropic_small.svg", "color": "#cc785c", "country": "us", "url": "https://www.anthropic.com/"}, "inputModalityText": true, "inputModalityImage": true, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ff9bc5e5-a02f-4270-983e-4b3f834f3363", "slug": "grok-3-mini-reasoning", "name": "Grok 3 mini Reasoning (high)", "shortName": "Grok 3 mini Reasoning (high)", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2025-02-19", "knowledgeCutoffDate": null, "isReasoning": true, "reasoningTokens": 2000, "effort": {"slug": "high", "label": "high", "level": 40}, "release": {"slug": "grok-3-mini-reasoning", "name": "Grok 3 mini Reasoning"}, "deprecated": true, "deprecatedTo": "grok-4-3", "isOpenWeights": false, "openSourceCategorization": "proprietary", "parameters": null, "inferenceParametersActiveBillions": null, "sizeClass": "medium", "contextWindowTokens": 1000000, "licenseName": null, "licenseUrl": null, "modelWeightsSourceUrl": null, "microevalsEnabled": false, "intelligenceIndex": 14.6212806219199, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": -6.8, "omniscienceBreakdown": {"accuracy": 0.15116666666666667, "hallucinationRate": 0.2581975260161005}, "gdpval": null, "itBenchSre": null, "tau2": 0.903508771929824, "tauBanking": null, "terminalbenchHard": 0.174242424242424, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": 0.553333333333333, "ifbench": 0.458503401360544, "hle": 0.1101, "gpqa": 0.790909090909091, "critpt": 0.00571428571428571, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.696296296296296, "aime25": 0.846666666666667, "analystAgent": null, "price1mInputTokens": 0.3, "price1mOutputTokens": 0.5, "cacheHitPrice": 0.075, "cacheHitDiscountPercent": 0.75, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.35, "price1mBlended7To2To1": 0.1625, "price1mBlended0To1To1": 0.4, "price1mBlended100To1To1": 0.08137254901960785, "price1mBlended0To100To1": 0.30198019801980197, "openness": {"opennessIndex": 11.11111111111111, "modelAvailability": 2, "transparencyMethodology": 0, "transparencyPostTrainingData": 0, "transparencyPreTrainingData": 0}, "timescaleData": {"medianOutputSpeed": 75.6881766142027, "medianTimeToFirstChunk": 0.707324928999924}, "outputSpeedVariance": {"p05": 24.4037010924667, "q25": 65.534338604677, "median": 75.6881766142027, "q75": 95.2095440262205, "p95": 115.753299672204}, "timeToFirstChunkVariance": {"p05": 0.609012310300016, "q25": 0.625776177499972, "median": 0.707324928999924, "q75": 0.760711021499958, "p95": 19.21429971495}, "performanceByPromptType": {"long": {"medianOutputSpeed": 75.6881766142027, "medianTimeToFirstChunk": 0.707324928999924, "medianTimeToFirstAnswerToken": 27.131531317196952, "medianEndToEndResponseTime": 33.73758291424621}}, "endToEndResponseTime": {"input": 0.707324928999924, "reasoning": 26.424206388197028, "answer": 6.606051597049257, "total": 33.73758291424621}, "timeToFirstAnswerToken": {"input": 0.707324928999924, "reasoning": 26.424206388197028, "total": 27.131531317196952}, "performanceDataSource": {"type": "firstParty", "providerName": "SpaceXAI"}, "hostModelCount": 3, "creator": {"id": "a1e3ddcf-d3e4-44a5-9e8f-029a69850875", "slug": "xai", "name": "SpaceXAI", "logo": "/img/logos/spacexai.svg", "color": "#736cd3", "country": "us", "url": "https://x.ai/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": true, "outputModalitySpeech": false, "outputModalityVideo": false}, {"id": "ffd65ef7-fbdb-4145-98ae-b5d01cda770b", "slug": "llama-2-chat-7b", "name": "Llama 2 Chat 7B", "shortName": "Llama 2 Chat 7B", "chartDefaultSelected": false, "chartHighlighted": false, "releaseDate": "2023-07-18", "knowledgeCutoffDate": "2023-07-01", "isReasoning": false, "reasoningTokens": 0, "release": {"slug": "llama-2-chat-7b", "name": "Llama 2 Chat 7B"}, "deprecated": true, "deprecatedTo": "llama-3-instruct-8b", "isOpenWeights": true, "openSourceCategorization": "commercial-license", "parameters": 7, "inferenceParametersActiveBillions": null, "sizeClass": "small", "contextWindowTokens": 4096, "licenseName": "Llama 2 Community License Agreement", "licenseUrl": "https://ai.meta.com/llama/license/", "modelWeightsSourceUrl": "https://huggingface.co/meta-llama/Llama-2-7b-chat-hf", "microevalsEnabled": false, "intelligenceIndex": 5.71179615992055, "intelligenceIndexIsEstimated": true, "capabilities": {}, "omniscience": null, "gdpval": null, "itBenchSre": null, "tau2": null, "tauBanking": null, "terminalbenchHard": null, "terminalBench21": null, "terminalBench40": null, "scicode": null, "lcr": null, "ifbench": null, "hle": 0.0533, "gpqa": 0.227272727272727, "critpt": null, "apexAgents": null, "mmmuPro": null, "livecodebench": 0.00211640211640212, "aime25": null, "analystAgent": null, "price1mInputTokens": 0.05, "price1mOutputTokens": 0.25, "cacheHitPrice": null, "cacheHitDiscountPercent": null, "cacheWritePrice": null, "pricePer1k1mpImages": null, "price1mBlended0To3To1": 0.1, "price1mBlended7To2To1": 0.07, "price1mBlended0To1To1": 0.15, "price1mBlended100To1To1": 0.051960784313725486, "price1mBlended0To100To1": 0.05198019801980198, "timescaleData": {}, "performanceByPromptType": {}, "performanceDataSource": {"type": "median"}, "hostModelCount": 1, "creator": {"id": "e1694725-0192-4e54-b1b8-c97e816c6cbe", "slug": "meta", "name": "Meta", "logo": "/img/logos/meta_small.svg", "color": "#0089f4", "country": "us", "url": "https://ai.meta.com/"}, "inputModalityText": true, "inputModalityImage": false, "inputModalitySpeech": false, "inputModalityVideo": false, "outputModalityText": true, "outputModalityImage": false, "outputModalitySpeech": false, "outputModalityVideo": false}] \ No newline at end of file diff --git a/slop/research/wvs/20260917_artificialanalysis/artificialanalysis_models_hle_manifest_2026-09-17T101320Z.html b/slop/research/wvs/20260917_artificialanalysis/artificialanalysis_models_hle_manifest_2026-09-17T101320Z.html new file mode 100644 index 0000000..7eb5107 --- /dev/null +++ b/slop/research/wvs/20260917_artificialanalysis/artificialanalysis_models_hle_manifest_2026-09-17T101320Z.html @@ -0,0 +1 @@ +Comparison of AI Models across Intelligence, Performance, and Price | Artificial Analysis

Comparison of Models: Intelligence, Performance & Price Analysis

Microevals Playground
Click on any model to see detailed metrics. For more details including relating to our methodology, see our FAQs.

Intelligence

Updated
Claude Fable 5.1 (max with fallback) logo Claude Fable 5.1 (max with fallback) and Claude Fable 5.1 (xhigh with fallback) logo Claude Fable 5.1 (xhigh with fallback) are the highest intelligence models, followed by GPT-6 Astra (max) logo GPT-6 Astra (max) and GPT-6 Astra (xhigh) logo GPT-6 Astra (xhigh).

Output Speed (tokens/s)

Celeris-1 logo Celeris-1 (1463 t/s) and Mercury 2 logo Mercury 2 (610 t/s) are the fastest models, followed by Gemini 2.5 Flash-Lite logo Gemini 2.5 Flash-Lite and Gemini 3.5 Flash-Lite logo Gemini 3.5 Flash-Lite.

Latency (seconds)

Gemini 2.5 Flash-Lite (Non-reasoning) logo Gemini 2.5 Flash-Lite (Non-reasoning) (0.31s) and North Mini Code logo North Mini Code (0.39s) are the lowest latency models, followed by Command A+ logo Command A+ and Granite 4.2 3B logo Granite 4.2 3B.

Price ($ per M tokens)

Devstral 2 logo Devstral 2 ($0.00) and North Mini Code logo North Mini Code ($0.00) are the cheapest models, followed by Gemma 3 4B logo Gemma 3 4B and Gemma 3 27B logo Gemma 3 27B.

Context Window

Llama 4 Scout logo Llama 4 Scout (10M) and Grok 4.20 0309 logo Grok 4.20 0309 (2M) are the largest context window models, followed by Gemini 1.5 Pro (May) logo Gemini 1.5 Pro (May) and Grok 4.1 Fast logo Grok 4.1 Fast.

Highlights

Updated

Intelligence

Artificial Analysis Intelligence Index · Higher is better

Speed

Output tokens per second · Higher is better

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better

IntelligenceUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.3 incorporates 10 evaluations: AA-Briefcase, GDPval-AA v2, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1

Capability IndexesUpdated

Measures the performance of models on specific capabilities and industries

Artificial Analysis Finance & Accounting Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Benchmarks

Intelligence Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
See more
AA-Briefcase

Agentic knowledge work, (Elo-500)/2000

GDPval-AA v2

Agentic real-world work tasks, (Elo-500)/2000

AutomationBench-AAUpdated

Agentic SaaS workflows

Terminal-Bench 4.0New

Agentic coding & terminal use

SciCode

Coding

Humanity's Last Exam

Reasoning & knowledge

GDP.pdfNew

Professional document reasoning, All-pass

CritPt

Physics reasoning

AA-Omniscience Accuracy

Knowledge

AA-Omniscience Non-Hallucination Rate

1 - hallucination rate

AA-LCR v1.1

Long context reasoning

Harvey LAB-AA

Legal agentic work, criterion pass rate

EnterpriseOps-Gym-AA

Agentic business operations

AA-AnalystAgent

Quantitative analysis on spreadsheets & documents

𝜏³-Banking

Agentic tool use

ITBench-AA

Kubernetes incident root-cause analysis

MMMU-Pro

Visual reasoning

MLCR-AANew

Medical long context reasoning

AA-Briefcase

AA-Briefcase Elo

AA-Briefcase is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better

AA-Omniscience

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct.

Openness Index

Artificial Analysis Openness Index: Score

Openness Index assesses model openness on a 0 to 100 normalized scale (higher is more open)

Intelligence Index Comparisons

Intelligence Index vs. Cost per Intelligence Index Task

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
Pareto line

Token Use

Output Tokens per Intelligence Index Task

Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index

Cost

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens)

Context Window

Context Window

Context window: tokens limit · Higher is better

Speed

Measured by Output Speed (tokens per second)

Output Speed

Output tokens per second · Higher is better

Time per Intelligence Index Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better

Latency

Measured by Time (seconds) to First Token

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time

End-to-End Response Time

Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better

Model Size (Open Weights Models Only)

Model Size: Total and Active Parameters

Comparison between total model parameters and parameters active during inference

Frequently Asked Questions

\ No newline at end of file diff --git a/slop/research/wvs/20260917_artificialanalysis/wvs_hle_mapping.json b/slop/research/wvs/20260917_artificialanalysis/wvs_hle_mapping.json new file mode 100644 index 0000000..8e40e1f --- /dev/null +++ b/slop/research/wvs/20260917_artificialanalysis/wvs_hle_mapping.json @@ -0,0 +1,649 @@ +{ + "schema": 2, + "source": { + "models_url": "https://artificialanalysis.ai/models", + "hle_url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam", + "fetched_utc": "2026-09-17T10:13:20Z", + "manifest_html": "artificialanalysis_models_hle_manifest_2026-09-17T101320Z.html", + "manifest_html_sha256": "2477a135dbba9beb804e1a5d4e1b7b6885b4db3370e5cadd5c75b941c17a603f", + "encrypted_models": "artificialanalysis_hle_models_2026-09-17T101320Z.txt", + "encrypted_models_sha256": "92c745e965335282fdfc1482a5ccae04c6ff424f0c5cf13a94e55dfdbf3d161d", + "decoded_models": "artificialanalysis_hle_models_decoded_2026-09-17T101320Z.json", + "decoded_models_sha256": "d0b33c6d5d5a76fb65eeea9893b646c991342ca4b93996910520e02404df1818", + "decoded_collection": "models", + "canonical_configuration_rows": 652, + "non_null_hle_rows": 615, + "metric": "Humanity's Last Exam score", + "protocol": "Artificial Analysis HLE evaluation as supplied per model configuration; HLE score is a fraction correct." + }, + "selection_rule": "For each exact canonical release mapping, select the highest non-null HLE score among saved AA configurations for that release. The selected configuration and effort remain in each mapping. This is a capability ceiling, not the score of the WVS request configuration.", + "mappings": [ + { + "plotted_model": "qwen3.6-27b", + "source_release_slug": "qwen3-6-27b", + "source_release_name": "Qwen3.6 27B", + "source_configuration_slug": "qwen3-6-27b", + "source_name": "Qwen3.6 27B (Reasoning)", + "source_effort": null, + "source_release_date": "2026-04-22", + "hle_score": 0.230769230769231, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3.5-35b-a3b", + "source_release_slug": "qwen3-5-35b-a3b", + "source_release_name": "Qwen3.5 35B A3B", + "source_configuration_slug": "qwen3-5-35b-a3b", + "source_name": "Qwen3.5 35B A3B (Reasoning)", + "source_effort": null, + "source_release_date": "2026-02-24", + "hle_score": 0.210379981464319, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3.6-max-preview", + "source_release_slug": "qwen3-6-max", + "source_release_name": "Qwen3.6 Max Preview", + "source_configuration_slug": "qwen3-6-max", + "source_name": "Qwen3.6 Max Preview", + "source_effort": null, + "source_release_date": "2026-04-20", + "hle_score": 0.308155699721965, + "match_basis": "AA release name and saved OpenRouter display name are both Qwen3.6 Max Preview; AA release date 2026-04-20 predates catalog indexing on 2026-04-27.", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "muse-spark-1.3", + "source_release_slug": "muse-spark-1-3", + "source_release_name": "Muse Spark 1.3", + "source_configuration_slug": "muse-spark-1-3", + "source_name": "Muse Spark 1.3 (max)", + "source_effort": "max", + "source_release_date": "2026-09-02", + "hle_score": 0.487025023169602, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3.8-27b", + "source_release_slug": "qwen3-8-27b", + "source_release_name": "Qwen3.8 27B", + "source_configuration_slug": "qwen3-8-27b", + "source_name": "Qwen3.8 27B (xhigh)", + "source_effort": "xhigh", + "source_release_date": "2026-08-14", + "hle_score": 0.33920296570899, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 4 + }, + { + "plotted_model": "gemma-4-31b-it", + "source_release_slug": "gemma-4-31b", + "source_release_name": "Gemma 4 31B", + "source_configuration_slug": "gemma-4-31b", + "source_name": "Gemma 4 31B (Reasoning)", + "source_effort": null, + "source_release_date": "2026-04-02", + "hle_score": 0.236329935125116, + "match_basis": "AA release and saved OpenRouter catalog both identify Google Gemma 4 31B on 2026-04-02; catalog suffix -it is not printed in either display name.", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3.5-122b-a10b", + "source_release_slug": "qwen3-5-122b-a10b", + "source_release_name": "Qwen3.5 122B A10B", + "source_configuration_slug": "qwen3-5-122b-a10b", + "source_name": "Qwen3.5 122B A10B (Reasoning)", + "source_effort": null, + "source_release_date": "2026-02-24", + "hle_score": 0.252085264133457, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "grok-4.20", + "source_release_slug": "grok-4-20", + "source_release_name": "Grok 4.20 0309 v2", + "source_configuration_slug": "grok-4-20", + "source_name": "Grok 4.20 0309 v2 (Reasoning)", + "source_effort": null, + "source_release_date": "2026-04-07", + "hle_score": 0.345227062094532, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "gemini-2.5-pro", + "source_release_slug": "gemini-2-5-pro", + "source_release_name": "Gemini 2.5 Pro", + "source_configuration_slug": "gemini-2-5-pro", + "source_name": "Gemini 2.5 Pro", + "source_effort": null, + "source_release_date": "2025-06-05", + "hle_score": 0.225208526413346, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "grok-4.3", + "source_release_slug": "grok-4-3", + "source_release_name": "Grok 4.3", + "source_configuration_slug": "grok-4-3", + "source_name": "Grok 4.3 (high)", + "source_effort": "high", + "source_release_date": "2026-04-30", + "hle_score": 0.372103799814643, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 4 + }, + { + "plotted_model": "deepseek-v4-flash", + "source_release_slug": "deepseek-v4-flash", + "source_release_name": "DeepSeek V4 Flash 0731", + "source_configuration_slug": "deepseek-v4-flash", + "source_name": "DeepSeek V4 Flash 0731 (Reasoning, Max Effort)", + "source_effort": "max", + "source_release_date": "2026-07-31", + "hle_score": 0.385542168674699, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "gpt-5.4", + "source_release_slug": "gpt-5-4", + "source_release_name": "GPT-5.4", + "source_configuration_slug": "gpt-5-4", + "source_name": "GPT-5.4 (xhigh)", + "source_effort": "xhigh", + "source_release_date": "2026-03-05", + "hle_score": 0.437442075996293, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 3 + }, + { + "plotted_model": "deepseek-v4.1-flash", + "source_release_slug": "deepseek-v4-1-flash", + "source_release_name": "DeepSeek V4.1 Flash", + "source_configuration_slug": "deepseek-v4-1-flash", + "source_name": "DeepSeek V4.1 Flash (Reasoning, Max Effort)", + "source_effort": "max", + "source_release_date": "2026-09-10", + "hle_score": 0.392493049119555, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "qwen3-coder-30b-a3b-instruct", + "source_release_slug": "qwen3-coder-30b-a3b-instruct", + "source_release_name": "Qwen3 Coder 30B A3B Instruct", + "source_configuration_slug": "qwen3-coder-30b-a3b-instruct", + "source_name": "Qwen3 Coder 30B A3B Instruct", + "source_effort": null, + "source_release_date": "2025-07-31", + "hle_score": 0.0384615384615385, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "gpt-6-astra", + "source_release_slug": "gpt-6-astra", + "source_release_name": "GPT-6 Astra", + "source_configuration_slug": "gpt-6-astra", + "source_name": "GPT-6 Astra (max)", + "source_effort": "max", + "source_release_date": "2026-09-03", + "hle_score": 0.546802594995366, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 5 + }, + { + "plotted_model": "gemma-3-27b-it", + "source_release_slug": "gemma-3-27b-instruct", + "source_release_name": "Gemma 3 27B Instruct", + "source_configuration_slug": "gemma-3-27b", + "source_name": "Gemma 3 27B Instruct", + "source_effort": null, + "source_release_date": "2025-03-12", + "hle_score": 0.044, + "match_basis": "AA names Gemma 3 27B Instruct; saved OpenRouter ID suffix -it and display name Gemma 3 27B identify the same 2025-03-12 Google release.", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "llama-4-maverick", + "source_release_slug": "llama-4-maverick", + "source_release_name": "Llama 4 Maverick", + "source_configuration_slug": "llama-4-maverick", + "source_name": "Llama 4 Maverick", + "source_effort": null, + "source_release_date": "2025-04-05", + "hle_score": 0.0491195551436515, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "qwen3-vl-235b-a22b-instruct", + "source_release_slug": "qwen3-vl-235b-a22b-instruct", + "source_release_name": "Qwen3 VL 235B A22B Instruct", + "source_configuration_slug": "qwen3-vl-235b-a22b-instruct", + "source_name": "Qwen3 VL 235B A22B Instruct", + "source_effort": null, + "source_release_date": "2025-09-23", + "hle_score": 0.0662650602409639, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "deepseek-v4-pro", + "source_release_slug": "deepseek-v4-pro", + "source_release_name": "DeepSeek V4 Pro 0813", + "source_configuration_slug": "deepseek-v4-pro", + "source_name": "DeepSeek V4 Pro 0813 (Reasoning, Max Effort)", + "source_effort": "max", + "source_release_date": "2026-08-13", + "hle_score": 0.410101946246525, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "llama-4-scout", + "source_release_slug": "llama-4-scout", + "source_release_name": "Llama 4 Scout", + "source_configuration_slug": "llama-4-scout", + "source_name": "Llama 4 Scout", + "source_effort": null, + "source_release_date": "2025-04-05", + "hle_score": 0.0378, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "qwen3-vl-30b-a3b-instruct", + "source_release_slug": "qwen3-vl-30b-a3b-instruct", + "source_release_name": "Qwen3 VL 30B A3B Instruct", + "source_configuration_slug": "qwen3-vl-30b-a3b-instruct", + "source_name": "Qwen3 VL 30B A3B Instruct", + "source_effort": null, + "source_release_date": "2025-10-03", + "hle_score": 0.0630213160333642, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "qwen3.5-397b-a17b", + "source_release_slug": "qwen3-5-397b-a17b", + "source_release_name": "Qwen3.5 397B A17B", + "source_configuration_slug": "qwen3-5-397b-a17b", + "source_name": "Qwen3.5 397B A17B (Reasoning)", + "source_effort": null, + "source_release_date": "2026-02-16", + "hle_score": 0.289620018535681, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "glm-5.3", + "source_release_slug": "glm-5-3", + "source_release_name": "GLM-5.3", + "source_configuration_slug": "glm-5-3", + "source_name": "GLM-5.3 (max)", + "source_effort": "max", + "source_release_date": "2026-08-18", + "hle_score": 0.422613531047266, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "qwen3.7-plus", + "source_release_slug": "qwen3-7-plus", + "source_release_name": "Qwen3.7 Plus", + "source_configuration_slug": "qwen3-7-plus", + "source_name": "Qwen3.7 Plus", + "source_effort": null, + "source_release_date": "2026-06-01", + "hle_score": 0.356348470806302, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "gpt-5.5", + "source_release_slug": "gpt-5-5", + "source_release_name": "GPT-5.5", + "source_configuration_slug": "gpt-5-5", + "source_name": "GPT-5.5 (xhigh)", + "source_effort": "xhigh", + "source_release_date": "2026-04-23", + "hle_score": 0.457831325301205, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 5 + }, + { + "plotted_model": "qwen3.6-35b-a3b", + "source_release_slug": "qwen3-6-35b-a3b", + "source_release_name": "Qwen3.6 35B A3B", + "source_configuration_slug": "qwen3-6-35b-a3b", + "source_name": "Qwen3.6 35B A3B (Reasoning)", + "source_effort": null, + "source_release_date": "2026-04-16", + "hle_score": 0.222428174235403, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3.6-plus", + "source_release_slug": "qwen3-6-plus", + "source_release_name": "Qwen3.6 Plus", + "source_configuration_slug": "qwen3-6-plus", + "source_name": "Qwen3.6 Plus", + "source_effort": null, + "source_release_date": "2026-04-02", + "hle_score": 0.278498609823911, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "qwen3-235b-a22b", + "source_release_slug": "qwen3-235b-a22b-instruct", + "source_release_name": "Qwen3 235B A22B", + "source_configuration_slug": "qwen3-235b-a22b-instruct-reasoning", + "source_name": "Qwen3 235B A22B (Reasoning)", + "source_effort": null, + "source_release_date": "2025-04-28", + "hle_score": 0.1098, + "match_basis": "AA release name and saved OpenRouter display name are both Qwen3 235B A22B on 2025-04-28; AA release slug adds its Instruct configuration label.", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3.7-max", + "source_release_slug": "qwen3-7-max", + "source_release_name": "Qwen3.7 Max", + "source_configuration_slug": "qwen3-7-max", + "source_name": "Qwen3.7 Max", + "source_effort": null, + "source_release_date": "2026-05-19", + "hle_score": 0.405004633920297, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "qwen3.5-9b", + "source_release_slug": "qwen3-5-9b", + "source_release_name": "Qwen3.5 9B", + "source_configuration_slug": "qwen3-5-9b", + "source_name": "Qwen3.5 9B (Reasoning)", + "source_effort": null, + "source_release_date": "2026-03-02", + "hle_score": 0.149212233549583, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3-vl-32b-instruct", + "source_release_slug": "qwen3-vl-32b-instruct", + "source_release_name": "Qwen3 VL 32B Instruct", + "source_configuration_slug": "qwen3-vl-32b-instruct", + "source_name": "Qwen3 VL 32B Instruct", + "source_effort": null, + "source_release_date": "2025-10-21", + "hle_score": 0.0681186283595922, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "gpt-5.6-sol", + "source_release_slug": "gpt-5-6-sol", + "source_release_name": "GPT-5.6 Sol", + "source_configuration_slug": "gpt-5-6-sol", + "source_name": "GPT-5.6 Sol (max)", + "source_effort": "max", + "source_release_date": "2026-07-09", + "hle_score": 0.494902687673772, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 6 + }, + { + "plotted_model": "qwen3-max-thinking", + "source_release_slug": "qwen3-max-thinking", + "source_release_name": "Qwen3 Max Thinking", + "source_configuration_slug": "qwen3-max-thinking", + "source_name": "Qwen3 Max Thinking", + "source_effort": null, + "source_release_date": "2026-01-26", + "hle_score": 0.279888785912882, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "inkling", + "source_release_slug": "inkling", + "source_release_name": "Inkling", + "source_configuration_slug": "inkling", + "source_name": "Inkling (xhigh)", + "source_effort": "xhigh", + "source_release_date": "2026-07-15", + "hle_score": 0.318813716404078, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "qwen3-vl-8b-instruct", + "source_release_slug": "qwen3-vl-8b-instruct", + "source_release_name": "Qwen3 VL 8B Instruct", + "source_configuration_slug": "qwen3-vl-8b-instruct", + "source_name": "Qwen3 VL 8B Instruct", + "source_effort": null, + "source_release_date": "2025-10-14", + "hle_score": 0.0268767377201112, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "kimi-k3", + "source_release_slug": "kimi-k3", + "source_release_name": "Kimi K3", + "source_configuration_slug": "kimi-k3", + "source_name": "Kimi K3 (max)", + "source_effort": "max", + "source_release_date": "2026-07-16", + "hle_score": 0.468952734012975, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3.5-27b", + "source_release_slug": "qwen3-5-27b", + "source_release_name": "Qwen3.5 27B", + "source_configuration_slug": "qwen3-5-27b", + "source_name": "Qwen3.5 27B (Reasoning)", + "source_effort": null, + "source_release_date": "2026-02-24", + "hle_score": 0.239110287303058, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3-32b", + "source_release_slug": "qwen3-32b-instruct", + "source_release_name": "Qwen3 32B", + "source_configuration_slug": "qwen3-32b-instruct-reasoning", + "source_name": "Qwen3 32B (Reasoning)", + "source_effort": null, + "source_release_date": "2025-04-28", + "hle_score": 0.0741, + "match_basis": "AA release name and saved OpenRouter display name are both Qwen3 32B on 2025-04-28; AA release slug adds its Instruct configuration label.", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3-coder-next", + "source_release_slug": "qwen3-coder-next", + "source_release_name": "Qwen3 Coder Next", + "source_configuration_slug": "qwen3-coder-next", + "source_name": "Qwen3 Coder Next", + "source_effort": null, + "source_release_date": "2026-02-03", + "hle_score": 0.101482854494903, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "qwen3-next-80b-a3b-instruct", + "source_release_slug": "qwen3-next-80b-a3b-instruct", + "source_release_name": "Qwen3 Next 80B A3B Instruct", + "source_configuration_slug": "qwen3-next-80b-a3b-instruct", + "source_name": "Qwen3 Next 80B A3B Instruct", + "source_effort": null, + "source_release_date": "2025-09-11", + "hle_score": 0.0764596848934198, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "claude-opus-4.7", + "source_release_slug": "claude-opus-4-7", + "source_release_name": "Claude Opus 4.7", + "source_configuration_slug": "claude-opus-4-7", + "source_name": "Claude Opus 4.7 (Adaptive Reasoning, Max Effort)", + "source_effort": "max", + "source_release_date": "2026-04-16", + "hle_score": 0.423076923076923, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "qwen3-8b", + "source_release_slug": "qwen3-8b-instruct", + "source_release_name": "Qwen3 8B", + "source_configuration_slug": "qwen3-8b-instruct-reasoning", + "source_name": "Qwen3 8B (Reasoning)", + "source_effort": null, + "source_release_date": "2025-04-28", + "hle_score": 0.0389, + "match_basis": "AA release name and saved OpenRouter display name are both Qwen3 8B on 2025-04-28; AA release slug adds its Instruct configuration label.", + "candidate_configurations_with_hle": 2 + }, + { + "plotted_model": "claude-opus-4.8", + "source_release_slug": "claude-opus-4-8", + "source_release_name": "Claude Opus 4.8", + "source_configuration_slug": "claude-opus-4-8", + "source_name": "Claude Opus 4.8 (Adaptive Reasoning, Max Effort)", + "source_effort": "max", + "source_release_date": "2026-05-28", + "hle_score": 0.486561631139944, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 1 + }, + { + "plotted_model": "gemini-3.7-flash", + "source_release_slug": "gemini-3-7-flash", + "source_release_name": "Gemini 3.7 Flash", + "source_configuration_slug": "gemini-3-7-flash", + "source_name": "Gemini 3.7 Flash (high)", + "source_effort": "high", + "source_release_date": "2026-08-13", + "hle_score": 0.478683966635774, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 3 + }, + { + "plotted_model": "claude-fable-5.1", + "source_release_slug": "claude-fable-5-1", + "source_release_name": "Claude Fable 5.1", + "source_configuration_slug": "claude-fable-5-1", + "source_name": "Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)", + "source_effort": "max", + "source_release_date": "2026-09-01", + "hle_score": 0.591288229842447, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 5 + }, + { + "plotted_model": "claude-opus-4.6", + "source_release_slug": "claude-opus-4-6", + "source_release_name": "Claude Opus 4.6", + "source_configuration_slug": "claude-opus-4-6-adaptive", + "source_name": "Claude Opus 4.6 (Adaptive Reasoning, Max Effort)", + "source_effort": "max", + "source_release_date": "2026-02-05", + "hle_score": 0.399443929564411, + "match_basis": "exact canonical release slug after replacing dots in the plotted ID with hyphens", + "candidate_configurations_with_hle": 2 + } + ], + "omitted": [ + { + "plotted_model": "qwen3.8-flash", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen3.5-plus-20260420", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen3-30b-a3b", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "mistral-large-2512", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen3-coder", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen3.7-flash", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen-plus", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "gpt-5.3-chat", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen3.5-plus-02-15", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen3-30b-a3b-instruct-2507", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen3.6-flash", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen-2.5-72b-instruct", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen-plus-2025-07-28", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen3-235b-a22b-2507", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen2.5-vl-72b-instruct", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen3-coder-plus", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen-2.5-7b-instruct", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + }, + { + "plotted_model": "qwen3-14b", + "reason": "no exact canonical release or reviewed same-release alias in saved AA HLE table" + } + ], + "unmatched_policy": "A plotted model is omitted unless it has an exact canonical release mapping or a separately reviewed alias with direct evidence for identical weights and release." +}