wassname/moral-maps
1
0 Fork 0
mirror of https://github.com/wassname/moral-maps.git synced 2026-10-05 13:00:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

Regenerate WVS map from complete panels

Browse Source 
Co-Authored-By: PI[gpt-5.6-terra] <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
wassnameandPI[gpt-5.6-terra] committed 2026-09-17 04:28:14 +08:00
1 parent f2d6556af1
commit 8db3d3daa9
16 files changed
+33524 -4787
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/RESEARCH_JOURNAL.md
+27
View File
@@ -911,3 +911,30 @@ prove total spend remains below the authorized cap, so durable records must reta
and request phase before the next paid call. -- PI[gpt-5.6-terra]
The next result will replace these bounds with reconciled provider-reported usage.
## 2026-09-16 -- WVS measured OpenRouter usage
This entry records what the durable WVS request ledger reports after the API panels.
The source ledger is `slop/research/wvs/20260916_openrouter/wvs_iw_requests.jsonl`. It contains 48 complete
panels and eleven incomplete attempts. Summing the provider `usage.cost` field across every completed request
phase, including excluded attempts, gives USD 3.59086067. This is provider-reported per-request cost, not a
completion-token estimate. The first Qwen diagnostic cost USD 0.04310443 and produced 129 valid samples after
142 rescues. The corrected Qwen 3.7 Flash panel used `reasoning.enabled=false` plus strict JSON schema, cost
USD 0.00110376, and has 144 distinct item/sample keys, 144 valid parses, zero rescues, and zero request failures.
Source: `qwen3.7-flash_schema_audit.md` and the raw ledger in the same directory.
The provider usage records expose prompt tokens, completion tokens, total tokens, cost and generation IDs, but
some omit separate reasoning and cache fields. Those fields remain unknown rather than being counted as zero.
Each completed cache entry records its exact model, prompt-and-settings protocol hash, contributing run ID and
coordinate result. The execution matrix in `execution_matrix.md` separates optional reasoning disabled, mandatory
reasoning at a listed low effort, no advertised reasoning control, and catalog entries whose mandatory effort is
unknown. It is a catalog snapshot, not a billing statement.
My read: the strict schema plus disabled optional reasoning is probably the protocol change that made the Qwen
panel complete, because the prior same-model attempts stored partial JSON objects and spent their output allowance
on reasoning. Several provider/network or deterministic-format failures remain excluded from plotted coordinates.
The saved ledger permits a later exact-protocol completion calculation without reinterpreting an incomplete panel as
a valid point. -- PI[gpt-5.6-terra]
The durable records make the measured spend and exclusions available for the next decision.
docs/img/wvs/wvs_map_iw.png
BIN
View File
Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 350 KiB

After

Width:  |  Height:  |  Size: 408 KiB

docs/img/wvs/wvs_map_iw.svg
+6985 -4660
View File
File diff suppressed because it is too large. Load diff
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 434 KiB

After

Width:  |  Height:  |  Size: 514 KiB

docs/img/wvs/wvs_model_ci.md
+66 -19
View File
@@ -1,19 +1,66 @@
| model | x self-expr | y secular | x 95%CI | y 95%CI |
|:---------------------------|--------------:|------------:|----------:|----------:|
| qwen3.7-max (rated) | +0.37 | +0.69 | +0.16 | +0.17 |
| grok-4.20 (rated) | +0.59 | +0.62 | +0.11 | +0.17 |
| gemma-4-31b-it (rated) | +0.36 | +0.66 | +0.16 | +0.13 |
| gemini-2.5-pro (rated) | +0.47 | +0.70 | +0.13 | +0.14 |
| grok-4.3 (rated) | +0.44 | +0.73 | +0.14 | +0.13 |
| deepseek-v4-flash (rated) | +0.57 | +0.64 | +0.11 | +0.16 |
| gpt-5.4 (rated) | +0.45 | +0.68 | +0.13 | +0.14 |
| mistral-large-2512 (rated) | +0.65 | +0.64 | +0.08 | +0.18 |
| gemma-3-27b-it (rated) | +0.60 | +0.60 | +0.09 | +0.17 |
| llama-4-maverick (rated) | +0.64 | +0.64 | +0.08 | +0.18 |
| gpt-5.3-chat (rated) | +0.50 | +0.67 | +0.09 | +0.16 |
| deepseek-v4-pro (rated) | +0.55 | +0.73 | +0.15 | +0.10 |
| llama-4-scout (rated) | +0.62 | +0.53 | +0.05 | +0.20 |
| gpt-5.5 (rated) | +0.42 | +0.76 | +0.17 | +0.07 |
| claude-opus-4.7 (rated) | +0.59 | +0.60 | +0.07 | +0.09 |
| claude-opus-4.8 (rated) | +0.61 | +0.58 | +0.07 | +0.07 |
| claude-opus-4.6 (rated) | +0.63 | +0.63 | +0.04 | +0.05 |
| model | x self-expr | y secular | x 95%CI | y 95%CI |
|:-------------------------------------|--------------:|------------:|----------:|----------:|
| qwen3.6-27b (rated) | +0.46 | +0.68 | +0.18 | +0.14 |
| qwen3.5-35b-a3b (rated) | +0.54 | +0.55 | +0.14 | +0.18 |
| qwen3.6-max-preview (rated) | +0.48 | +0.69 | +0.16 | +0.14 |
| muse-spark-1.3 (rated) | +0.43 | +0.73 | +0.18 | +0.12 |
| qwen3.8-27b (rated) | +0.43 | +0.69 | +0.16 | +0.14 |
| qwen3.8-flash (rated) | +0.42 | +0.63 | +0.14 | +0.15 |
| gemma-4-31b-it (rated) | +0.36 | +0.66 | +0.16 | +0.13 |
| qwen3.5-122b-a10b (rated) | +0.48 | +0.62 | +0.15 | +0.14 |
| grok-4.20 (rated) | +0.59 | +0.62 | +0.11 | +0.17 |
| qwen3.5-plus-20260420 (rated) | +0.59 | +0.65 | +0.12 | +0.16 |
| gemini-2.5-pro (rated) | +0.47 | +0.70 | +0.13 | +0.14 |
| grok-4.3 (rated) | +0.44 | +0.73 | +0.14 | +0.13 |
| deepseek-v4-flash (rated) | +0.57 | +0.64 | +0.11 | +0.16 |
| gpt-5.4 (rated) | +0.45 | +0.68 | +0.13 | +0.14 |
| deepseek-v4.1-flash (rated) | +0.54 | +0.60 | +0.10 | +0.16 |
| qwen3-coder-30b-a3b-instruct (rated) | +0.50 | +0.58 | +0.09 | +0.17 |
| qwen3-30b-a3b (rated) | +0.67 | +0.61 | +0.07 | +0.19 |
| gpt-6-astra (rated) | +0.46 | +0.68 | +0.15 | +0.11 |
| mistral-large-2512 (rated) | +0.65 | +0.64 | +0.08 | +0.18 |
| gemma-3-27b-it (rated) | +0.60 | +0.60 | +0.09 | +0.17 |
| llama-4-maverick (rated) | +0.64 | +0.64 | +0.08 | +0.18 |
| qwen3-coder (rated) | +0.60 | +0.62 | +0.08 | +0.18 |
| qwen3.7-flash (rated) | +0.65 | +0.59 | +0.10 | +0.16 |
| qwen3-vl-235b-a22b-instruct (rated) | +0.60 | +0.55 | +0.05 | +0.21 |
| qwen-plus (rated) | +0.60 | +0.63 | +0.07 | +0.18 |
| gpt-5.3-chat (rated) | +0.50 | +0.67 | +0.09 | +0.16 |
| deepseek-v4-pro (rated) | +0.55 | +0.73 | +0.15 | +0.10 |
| llama-4-scout (rated) | +0.62 | +0.53 | +0.05 | +0.20 |
| qwen3-vl-30b-a3b-instruct (rated) | +0.53 | +0.53 | +0.06 | +0.19 |
| qwen3.5-397b-a17b (rated) | +0.54 | +0.65 | +0.08 | +0.17 |
| qwen3.5-plus-02-15 (rated) | +0.54 | +0.66 | +0.08 | +0.17 |
| glm-5.3 (rated) | +0.55 | +0.64 | +0.12 | +0.13 |
| qwen3.7-plus (rated) | +0.51 | +0.67 | +0.10 | +0.15 |
| qwen3-30b-a3b-instruct-2507 (rated) | +0.65 | +0.54 | +0.05 | +0.20 |
| gpt-5.5 (rated) | +0.42 | +0.76 | +0.17 | +0.07 |
| qwen3.6-35b-a3b (rated) | +0.61 | +0.59 | +0.10 | +0.14 |
| qwen3.6-flash (rated) | +0.65 | +0.58 | +0.09 | +0.15 |
| qwen3.6-plus (rated) | +0.52 | +0.67 | +0.08 | +0.15 |
| qwen3-235b-a22b (rated) | +0.64 | +0.56 | +0.07 | +0.17 |
| qwen-2.5-72b-instruct (rated) | +0.60 | +0.60 | +0.06 | +0.17 |
| qwen-plus-2025-07-28 (rated) | +0.64 | +0.51 | +0.07 | +0.16 |
| qwen3.7-max (rated) | +0.50 | +0.65 | +0.11 | +0.12 |
| qwen3-235b-a22b-2507 (rated) | +0.64 | +0.57 | +0.07 | +0.16 |
| qwen3.5-9b (rated) | +0.50 | +0.59 | +0.09 | +0.14 |
| qwen2.5-vl-72b-instruct (rated) | +0.58 | +0.60 | +0.07 | +0.15 |
| qwen3-vl-32b-instruct (rated) | +0.60 | +0.53 | +0.02 | +0.20 |
| gpt-5.6-sol (rated) | +0.53 | +0.67 | +0.09 | +0.13 |
| qwen3-max-thinking (rated) | +0.58 | +0.70 | +0.07 | +0.14 |
| qwen3-coder-plus (rated) | +0.62 | +0.60 | +0.07 | +0.14 |
| inkling (rated) | +0.56 | +0.69 | +0.10 | +0.11 |
| qwen3-vl-8b-instruct (rated) | +0.61 | +0.60 | +0.06 | +0.15 |
| qwen-2.5-7b-instruct (rated) | +0.55 | +0.59 | +0.05 | +0.16 |
| kimi-k3 (rated) | +0.62 | +0.67 | +0.07 | +0.14 |
| qwen3.5-27b (rated) | +0.60 | +0.65 | +0.05 | +0.16 |
| qwen3-32b (rated) | +0.61 | +0.54 | +0.06 | +0.14 |
| qwen3-14b (rated) | +0.61 | +0.58 | +0.03 | +0.16 |
| qwen3-coder-next (rated) | +0.64 | +0.58 | +0.05 | +0.13 |
| qwen3-next-80b-a3b-instruct (rated) | +0.67 | +0.70 | +0.05 | +0.12 |
| claude-opus-4.7 (rated) | +0.59 | +0.60 | +0.07 | +0.09 |
| qwen3-8b (rated) | +0.62 | +0.54 | +0.03 | +0.12 |
| claude-opus-4.8 (rated) | +0.61 | +0.58 | +0.07 | +0.07 |
| gemini-3.7-flash (rated) | +0.50 | +0.63 | +0.03 | +0.10 |
| claude-fable-5.1 (rated) | +0.58 | +0.61 | +0.07 | +0.05 |
| claude-opus-4.6 (rated) | +0.63 | +0.63 | +0.04 | +0.05 |
docs/img/wvs/wvs_model_outlier_sd.md
+322 -87
View File
@@ -1,87 +1,322 @@
| model | zone | n countries | z self-expr | z secular | Mahalanobis |
|:-------------------|:----------------|--------------:|--------------:|------------:|--------------:|
| gpt-5.5 | African-Islamic | 19 | +2.36 | +6.12 | +6.51 |
| gpt-5.5 | East Asia | 9 | +1.31 | +3.54 | +3.72 |
| gpt-5.5 | Latin America | 14 | +2.35 | +6.45 | +6.51 |
| gpt-5.5 | Orthodox | 14 | +2.94 | +8.06 | +8.52 |
| gpt-5.5 | West | 29 | -0.33 | +2.93 | +4.71 |
| deepseek-v4-pro | African-Islamic | 19 | +3.70 | +5.75 | +5.75 |
| deepseek-v4-pro | East Asia | 9 | +3.10 | +3.14 | +3.46 |
| deepseek-v4-pro | Latin America | 14 | +4.25 | +6.05 | +6.74 |
| deepseek-v4-pro | Orthodox | 14 | +5.25 | +7.48 | +9.04 |
| deepseek-v4-pro | West | 29 | +0.54 | +2.61 | +3.32 |
| grok-4.3 | African-Islamic | 19 | +2.57 | +5.75 | +5.98 |
| grok-4.3 | East Asia | 9 | +1.58 | +3.14 | +3.17 |
| grok-4.3 | Latin America | 14 | +2.64 | +6.05 | +6.19 |
| grok-4.3 | Orthodox | 14 | +3.29 | +7.48 | +8.11 |
| grok-4.3 | West | 29 | -0.19 | +2.61 | +4.08 |
| gemini-2.5-pro | African-Islamic | 19 | +2.88 | +5.39 | +5.46 |
| gemini-2.5-pro | East Asia | 9 | +2.00 | +2.73 | +2.76 |
| gemini-2.5-pro | Latin America | 14 | +3.08 | +5.66 | +5.95 |
| gemini-2.5-pro | Orthodox | 14 | +3.83 | +6.89 | +7.81 |
| gemini-2.5-pro | West | 29 | +0.01 | +2.29 | +3.38 |
| qwen3.7-max | African-Islamic | 19 | +1.85 | +5.27 | +5.69 |
| qwen3.7-max | East Asia | 9 | +0.62 | +2.59 | +2.89 |
| qwen3.7-max | Latin America | 14 | +1.62 | +5.52 | +5.54 |
| qwen3.7-max | Orthodox | 14 | +2.05 | +6.70 | +6.96 |
| qwen3.7-max | West | 29 | -0.66 | +2.18 | +4.01 |
| gpt-5.4 | African-Islamic | 19 | +2.67 | +5.14 | +5.23 |
| gpt-5.4 | East Asia | 9 | +1.72 | +2.46 | +2.47 |
| gpt-5.4 | Latin America | 14 | +2.79 | +5.39 | +5.63 |
| gpt-5.4 | Orthodox | 14 | +3.47 | +6.50 | +7.30 |
| gpt-5.4 | West | 29 | -0.13 | +2.07 | +3.21 |
| gpt-5.3-chat | African-Islamic | 19 | +3.19 | +5.02 | +5.03 |
| gpt-5.3-chat | East Asia | 9 | +2.41 | +2.32 | +2.63 |
| gpt-5.3-chat | Latin America | 14 | +3.52 | +5.26 | +5.78 |
| gpt-5.3-chat | Orthodox | 14 | +4.36 | +6.31 | +7.59 |
| gpt-5.3-chat | West | 29 | +0.21 | +1.96 | +2.69 |
| gemma-4-31b-it | African-Islamic | 19 | +1.74 | +4.90 | +5.29 |
| gemma-4-31b-it | East Asia | 9 | +0.48 | +2.19 | +2.46 |
| gemma-4-31b-it | Latin America | 14 | +1.47 | +5.13 | +5.14 |
| gemma-4-31b-it | Orthodox | 14 | +1.87 | +6.11 | +6.36 |
| gemma-4-31b-it | West | 29 | -0.73 | +1.86 | +3.62 |
| deepseek-v4-flash | African-Islamic | 19 | +3.91 | +4.66 | +4.79 |
| deepseek-v4-flash | East Asia | 9 | +3.38 | +1.91 | +3.39 |
| deepseek-v4-flash | Latin America | 14 | +4.54 | +4.87 | +6.02 |
| deepseek-v4-flash | Orthodox | 14 | +5.60 | +5.72 | +7.92 |
| deepseek-v4-flash | West | 29 | +0.68 | +1.64 | +1.83 |
| llama-4-maverick | African-Islamic | 19 | +4.63 | +4.66 | +5.10 |
| llama-4-maverick | East Asia | 9 | +4.34 | +1.91 | +4.46 |
| llama-4-maverick | Latin America | 14 | +5.56 | +4.87 | +6.69 |
| llama-4-maverick | Orthodox | 14 | +6.84 | +5.72 | +8.82 |
| llama-4-maverick | West | 29 | +1.14 | +1.64 | +1.65 |
| mistral-large-2512 | African-Islamic | 19 | +4.73 | +4.66 | +5.15 |
| mistral-large-2512 | East Asia | 9 | +4.48 | +1.91 | +4.62 |
| mistral-large-2512 | Latin America | 14 | +5.71 | +4.87 | +6.79 |
| mistral-large-2512 | Orthodox | 14 | +7.02 | +5.72 | +8.96 |
| mistral-large-2512 | West | 29 | +1.21 | +1.64 | +1.64 |
| claude-opus-4.6 | African-Islamic | 19 | +4.53 | +4.54 | +4.97 |
| claude-opus-4.6 | East Asia | 9 | +4.21 | +1.78 | +4.34 |
| claude-opus-4.6 | Latin America | 14 | +5.42 | +4.73 | +6.51 |
| claude-opus-4.6 | Orthodox | 14 | +6.67 | +5.53 | +8.57 |
| claude-opus-4.6 | West | 29 | +1.08 | +1.54 | +1.54 |
| grok-4.20 | African-Islamic | 19 | +4.11 | +4.42 | +4.70 |
| grok-4.20 | East Asia | 9 | +3.65 | +1.64 | +3.74 |
| grok-4.20 | Latin America | 14 | +4.83 | +4.60 | +6.03 |
| grok-4.20 | Orthodox | 14 | +5.96 | +5.33 | +7.91 |
| grok-4.20 | West | 29 | +0.81 | +1.43 | +1.47 |
| claude-opus-4.7 | African-Islamic | 19 | +4.11 | +4.17 | +4.55 |
| claude-opus-4.7 | East Asia | 9 | +3.65 | +1.37 | +3.83 |
| claude-opus-4.7 | Latin America | 14 | +4.83 | +4.34 | +5.87 |
| claude-opus-4.7 | Orthodox | 14 | +5.96 | +4.94 | +7.66 |
| claude-opus-4.7 | West | 29 | +0.81 | +1.21 | +1.22 |
| gemma-3-27b-it | African-Islamic | 19 | +4.22 | +4.17 | +4.60 |
| gemma-3-27b-it | East Asia | 9 | +3.79 | +1.37 | +4.00 |
| gemma-3-27b-it | Latin America | 14 | +4.98 | +4.34 | +5.97 |
| gemma-3-27b-it | Orthodox | 14 | +6.13 | +4.94 | +7.79 |
| gemma-3-27b-it | West | 29 | +0.88 | +1.21 | +1.21 |
| claude-opus-4.8 | African-Islamic | 19 | +4.32 | +3.93 | +4.55 |
| claude-opus-4.8 | East Asia | 9 | +3.93 | +1.10 | +4.29 |
| claude-opus-4.8 | Latin America | 14 | +5.13 | +4.08 | +5.94 |
| claude-opus-4.8 | Orthodox | 14 | +6.31 | +4.55 | +7.70 |
| claude-opus-4.8 | West | 29 | +0.94 | +1.00 | +1.04 |
| llama-4-scout | African-Islamic | 19 | +4.42 | +3.32 | +4.46 |
| llama-4-scout | East Asia | 9 | +4.07 | +0.42 | +4.88 |
| llama-4-scout | Latin America | 14 | +5.27 | +3.42 | +5.75 |
| llama-4-scout | Orthodox | 14 | +6.49 | +3.58 | +7.34 |
| llama-4-scout | West | 29 | +1.01 | +0.46 | +1.09 |
| model | zone | n countries | z self-expr | z secular | Mahalanobis |
|:-----------------------------|:----------------|--------------:|--------------:|------------:|--------------:|
| gpt-5.5 | African-Islamic | 19 | +2.36 | +6.12 | +6.51 |
| gpt-5.5 | East Asia | 9 | +1.31 | +3.54 | +3.72 |
| gpt-5.5 | Latin America | 14 | +2.35 | +6.45 | +6.51 |
| gpt-5.5 | Orthodox | 14 | +2.94 | +8.06 | +8.52 |
| gpt-5.5 | West | 29 | -0.33 | +2.93 | +4.71 |
| deepseek-v4-pro | African-Islamic | 19 | +3.70 | +5.75 | +5.75 |
| deepseek-v4-pro | East Asia | 9 | +3.10 | +3.14 | +3.46 |
| deepseek-v4-pro | Latin America | 14 | +4.25 | +6.05 | +6.74 |
| deepseek-v4-pro | Orthodox | 14 | +5.25 | +7.48 | +9.04 |
| deepseek-v4-pro | West | 29 | +0.54 | +2.61 | +3.32 |
| grok-4.3 | African-Islamic | 19 | +2.57 | +5.75 | +5.98 |
| grok-4.3 | East Asia | 9 | +1.58 | +3.14 | +3.17 |
| grok-4.3 | Latin America | 14 | +2.64 | +6.05 | +6.19 |
| grok-4.3 | Orthodox | 14 | +3.29 | +7.48 | +8.11 |
| grok-4.3 | West | 29 | -0.19 | +2.61 | +4.08 |
| muse-spark-1.3 | African-Islamic | 19 | +2.47 | +5.75 | +6.02 |
| muse-spark-1.3 | East Asia | 9 | +1.45 | +3.14 | +3.20 |
| muse-spark-1.3 | Latin America | 14 | +2.50 | +6.05 | +6.16 |
| muse-spark-1.3 | Orthodox | 14 | +3.12 | +7.48 | +8.04 |
| muse-spark-1.3 | West | 29 | -0.26 | +2.61 | +4.16 |
| gemini-2.5-pro | African-Islamic | 19 | +2.88 | +5.39 | +5.46 |
| gemini-2.5-pro | East Asia | 9 | +2.00 | +2.73 | +2.76 |
| gemini-2.5-pro | Latin America | 14 | +3.08 | +5.66 | +5.95 |
| gemini-2.5-pro | Orthodox | 14 | +3.83 | +6.89 | +7.81 |
| gemini-2.5-pro | West | 29 | +0.01 | +2.29 | +3.38 |
| qwen3-max-thinking | African-Islamic | 19 | +4.01 | +5.39 | +5.42 |
| qwen3-max-thinking | East Asia | 9 | +3.52 | +2.73 | +3.58 |
| qwen3-max-thinking | Latin America | 14 | +4.69 | +5.66 | +6.65 |
| qwen3-max-thinking | Orthodox | 14 | +5.78 | +6.89 | +8.90 |
| qwen3-max-thinking | West | 29 | +0.74 | +2.29 | +2.68 |
| qwen3-next-80b-a3b-instruct | African-Islamic | 19 | +4.94 | +5.39 | +5.69 |
| qwen3-next-80b-a3b-instruct | East Asia | 9 | +4.76 | +2.73 | +4.77 |
| qwen3-next-80b-a3b-instruct | Latin America | 14 | +6.00 | +5.66 | +7.45 |
| qwen3-next-80b-a3b-instruct | Orthodox | 14 | +7.38 | +6.89 | +9.98 |
| qwen3-next-80b-a3b-instruct | West | 29 | +1.34 | +2.29 | +2.34 |
| inkling | African-Islamic | 19 | +3.81 | +5.27 | +5.28 |
| inkling | East Asia | 9 | +3.24 | +2.59 | +3.32 |
| inkling | Latin America | 14 | +4.40 | +5.52 | +6.40 |
| inkling | Orthodox | 14 | +5.42 | +6.70 | +8.53 |
| inkling | West | 29 | +0.61 | +2.18 | +2.64 |
| qwen3.6-max-preview | African-Islamic | 19 | +2.98 | +5.27 | +5.31 |
| qwen3.6-max-preview | East Asia | 9 | +2.14 | +2.59 | +2.68 |
| qwen3.6-max-preview | Latin America | 14 | +3.23 | +5.52 | +5.89 |
| qwen3.6-max-preview | Orthodox | 14 | +4.00 | +6.70 | +7.73 |
| qwen3.6-max-preview | West | 29 | +0.07 | +2.18 | +3.15 |
| qwen3.8-27b | African-Islamic | 19 | +2.47 | +5.27 | +5.43 |
| qwen3.8-27b | East Asia | 9 | +1.45 | +2.59 | +2.60 |
| qwen3.8-27b | Latin America | 14 | +2.50 | +5.52 | +5.67 |
| qwen3.8-27b | Orthodox | 14 | +3.12 | +6.70 | +7.33 |
| qwen3.8-27b | West | 29 | -0.26 | +2.18 | +3.53 |
| gpt-5.4 | African-Islamic | 19 | +2.67 | +5.14 | +5.23 |
| gpt-5.4 | East Asia | 9 | +1.72 | +2.46 | +2.47 |
| gpt-5.4 | Latin America | 14 | +2.79 | +5.39 | +5.63 |
| gpt-5.4 | Orthodox | 14 | +3.47 | +6.50 | +7.30 |
| gpt-5.4 | West | 29 | -0.13 | +2.07 | +3.21 |
| gpt-6-astra | African-Islamic | 19 | +2.77 | +5.14 | +5.21 |
| gpt-6-astra | East Asia | 9 | +1.86 | +2.46 | +2.49 |
| gpt-6-astra | Latin America | 14 | +2.93 | +5.39 | +5.67 |
| gpt-6-astra | Orthodox | 14 | +3.65 | +6.50 | +7.39 |
| gpt-6-astra | West | 29 | -0.06 | +2.07 | +3.14 |
| qwen3.6-27b | African-Islamic | 19 | +2.77 | +5.14 | +5.21 |
| qwen3.6-27b | East Asia | 9 | +1.86 | +2.46 | +2.49 |
| qwen3.6-27b | Latin America | 14 | +2.93 | +5.39 | +5.67 |
| qwen3.6-27b | Orthodox | 14 | +3.65 | +6.50 | +7.39 |
| qwen3.6-27b | West | 29 | -0.06 | +2.07 | +3.14 |
| gpt-5.3-chat | African-Islamic | 19 | +3.19 | +5.02 | +5.03 |
| gpt-5.3-chat | East Asia | 9 | +2.41 | +2.32 | +2.63 |
| gpt-5.3-chat | Latin America | 14 | +3.52 | +5.26 | +5.78 |
| gpt-5.3-chat | Orthodox | 14 | +4.36 | +6.31 | +7.59 |
| gpt-5.3-chat | West | 29 | +0.21 | +1.96 | +2.69 |
| gpt-5.6-sol | African-Islamic | 19 | +3.50 | +5.02 | +5.03 |
| gpt-5.6-sol | East Asia | 9 | +2.83 | +2.32 | +2.92 |
| gpt-5.6-sol | Latin America | 14 | +3.96 | +5.26 | +5.98 |
| gpt-5.6-sol | Orthodox | 14 | +4.89 | +6.31 | +7.90 |
| gpt-5.6-sol | West | 29 | +0.41 | +1.96 | +2.50 |
| kimi-k3 | African-Islamic | 19 | +4.42 | +5.02 | +5.23 |
| kimi-k3 | East Asia | 9 | +4.07 | +2.32 | +4.08 |
| kimi-k3 | Latin America | 14 | +5.27 | +5.26 | +6.73 |
| kimi-k3 | Orthodox | 14 | +6.49 | +6.31 | +8.95 |
| kimi-k3 | West | 29 | +1.01 | +1.96 | +2.07 |
| qwen3.6-plus | African-Islamic | 19 | +3.39 | +5.02 | +5.02 |
| qwen3.6-plus | East Asia | 9 | +2.69 | +2.32 | +2.81 |
| qwen3.6-plus | Latin America | 14 | +3.81 | +5.26 | +5.91 |
| qwen3.6-plus | Orthodox | 14 | +4.71 | +6.31 | +7.79 |
| qwen3.6-plus | West | 29 | +0.34 | +1.96 | +2.56 |
| qwen3.7-plus | African-Islamic | 19 | +3.29 | +5.02 | +5.02 |
| qwen3.7-plus | East Asia | 9 | +2.55 | +2.32 | +2.72 |
| qwen3.7-plus | Latin America | 14 | +3.66 | +5.26 | +5.84 |
| qwen3.7-plus | Orthodox | 14 | +4.54 | +6.31 | +7.69 |
| qwen3.7-plus | West | 29 | +0.27 | +1.96 | +2.63 |
| gemma-4-31b-it | African-Islamic | 19 | +1.74 | +4.90 | +5.29 |
| gemma-4-31b-it | East Asia | 9 | +0.48 | +2.19 | +2.46 |
| gemma-4-31b-it | Latin America | 14 | +1.47 | +5.13 | +5.14 |
| gemma-4-31b-it | Orthodox | 14 | +1.87 | +6.11 | +6.36 |
| gemma-4-31b-it | West | 29 | -0.73 | +1.86 | +3.62 |
| qwen3.5-plus-02-15 | African-Islamic | 19 | +3.60 | +4.90 | +4.93 |
| qwen3.5-plus-02-15 | East Asia | 9 | +2.96 | +2.19 | +3.00 |
| qwen3.5-plus-02-15 | Latin America | 14 | +4.10 | +5.13 | +5.96 |
| qwen3.5-plus-02-15 | Orthodox | 14 | +5.07 | +6.11 | +7.85 |
| qwen3.5-plus-02-15 | West | 29 | +0.47 | +1.86 | +2.28 |
| qwen3.5-27b | African-Islamic | 19 | +4.22 | +4.78 | +4.98 |
| qwen3.5-27b | East Asia | 9 | +3.79 | +2.05 | +3.81 |
| qwen3.5-27b | Latin America | 14 | +4.98 | +5.00 | +6.37 |
| qwen3.5-27b | Orthodox | 14 | +6.13 | +5.92 | +8.43 |
| qwen3.5-27b | West | 29 | +0.88 | +1.75 | +1.86 |
| qwen3.5-397b-a17b | African-Islamic | 19 | +3.60 | +4.78 | +4.82 |
| qwen3.5-397b-a17b | East Asia | 9 | +2.96 | +2.05 | +2.98 |
| qwen3.5-397b-a17b | Latin America | 14 | +4.10 | +5.00 | +5.86 |
| qwen3.5-397b-a17b | Orthodox | 14 | +5.07 | +5.92 | +7.71 |
| qwen3.5-397b-a17b | West | 29 | +0.47 | +1.75 | +2.13 |
| qwen3.5-plus-20260420 | African-Islamic | 19 | +4.11 | +4.78 | +4.95 |
| qwen3.5-plus-20260420 | East Asia | 9 | +3.65 | +2.05 | +3.66 |
| qwen3.5-plus-20260420 | Latin America | 14 | +4.83 | +5.00 | +6.28 |
| qwen3.5-plus-20260420 | Orthodox | 14 | +5.96 | +5.92 | +8.30 |
| qwen3.5-plus-20260420 | West | 29 | +0.81 | +1.75 | +1.89 |
| qwen3.7-max | African-Islamic | 19 | +3.19 | +4.78 | +4.78 |
| qwen3.7-max | East Asia | 9 | +2.41 | +2.05 | +2.51 |
| qwen3.7-max | Latin America | 14 | +3.52 | +5.00 | +5.57 |
| qwen3.7-max | Orthodox | 14 | +4.36 | +5.92 | +7.27 |
| qwen3.7-max | West | 29 | +0.21 | +1.75 | +2.38 |
| deepseek-v4-flash | African-Islamic | 19 | +3.91 | +4.66 | +4.79 |
| deepseek-v4-flash | East Asia | 9 | +3.38 | +1.91 | +3.39 |
| deepseek-v4-flash | Latin America | 14 | +4.54 | +4.87 | +6.02 |
| deepseek-v4-flash | Orthodox | 14 | +5.60 | +5.72 | +7.92 |
| deepseek-v4-flash | West | 29 | +0.68 | +1.64 | +1.83 |
| glm-5.3 | African-Islamic | 19 | +3.70 | +4.66 | +4.73 |
| glm-5.3 | East Asia | 9 | +3.10 | +1.91 | +3.10 |
| glm-5.3 | Latin America | 14 | +4.25 | +4.87 | +5.84 |
| glm-5.3 | Orthodox | 14 | +5.25 | +5.72 | +7.68 |
| glm-5.3 | West | 29 | +0.54 | +1.64 | +1.92 |
| llama-4-maverick | African-Islamic | 19 | +4.63 | +4.66 | +5.10 |
| llama-4-maverick | East Asia | 9 | +4.34 | +1.91 | +4.46 |
| llama-4-maverick | Latin America | 14 | +5.56 | +4.87 | +6.69 |
| llama-4-maverick | Orthodox | 14 | +6.84 | +5.72 | +8.82 |
| llama-4-maverick | West | 29 | +1.14 | +1.64 | +1.65 |
| mistral-large-2512 | African-Islamic | 19 | +4.73 | +4.66 | +5.15 |
| mistral-large-2512 | East Asia | 9 | +4.48 | +1.91 | +4.62 |
| mistral-large-2512 | Latin America | 14 | +5.71 | +4.87 | +6.79 |
| mistral-large-2512 | Orthodox | 14 | +7.02 | +5.72 | +8.96 |
| mistral-large-2512 | West | 29 | +1.21 | +1.64 | +1.64 |
| claude-opus-4.6 | African-Islamic | 19 | +4.53 | +4.54 | +4.97 |
| claude-opus-4.6 | East Asia | 9 | +4.21 | +1.78 | +4.34 |
| claude-opus-4.6 | Latin America | 14 | +5.42 | +4.73 | +6.51 |
| claude-opus-4.6 | Orthodox | 14 | +6.67 | +5.53 | +8.57 |
| claude-opus-4.6 | West | 29 | +1.08 | +1.54 | +1.54 |
| gemini-3.7-flash | African-Islamic | 19 | +3.19 | +4.54 | +4.54 |
| gemini-3.7-flash | East Asia | 9 | +2.41 | +1.78 | +2.44 |
| gemini-3.7-flash | Latin America | 14 | +3.52 | +4.73 | +5.36 |
| gemini-3.7-flash | Orthodox | 14 | +4.36 | +5.53 | +6.96 |
| gemini-3.7-flash | West | 29 | +0.21 | +1.54 | +2.06 |
| qwen-plus | African-Islamic | 19 | +4.22 | +4.54 | +4.82 |
| qwen-plus | East Asia | 9 | +3.79 | +1.78 | +3.86 |
| qwen-plus | Latin America | 14 | +4.98 | +4.73 | +6.21 |
| qwen-plus | Orthodox | 14 | +6.13 | +5.53 | +8.17 |
| qwen-plus | West | 29 | +0.88 | +1.54 | +1.58 |
| qwen3.8-flash | African-Islamic | 19 | +2.36 | +4.54 | +4.61 |
| qwen3.8-flash | East Asia | 9 | +1.31 | +1.78 | +1.80 |
| qwen3.8-flash | Latin America | 14 | +2.35 | +4.73 | +4.91 |
| qwen3.8-flash | Orthodox | 14 | +2.94 | +5.53 | +6.20 |
| qwen3.8-flash | West | 29 | -0.33 | +1.54 | +2.65 |
| grok-4.20 | African-Islamic | 19 | +4.11 | +4.42 | +4.70 |
| grok-4.20 | East Asia | 9 | +3.65 | +1.64 | +3.74 |
| grok-4.20 | Latin America | 14 | +4.83 | +4.60 | +6.03 |
| grok-4.20 | Orthodox | 14 | +5.96 | +5.33 | +7.91 |
| grok-4.20 | West | 29 | +0.81 | +1.43 | +1.47 |
| qwen3-coder | African-Islamic | 19 | +4.22 | +4.42 | +4.74 |
| qwen3-coder | East Asia | 9 | +3.79 | +1.64 | +3.90 |
| qwen3-coder | Latin America | 14 | +4.98 | +4.60 | +6.13 |
| qwen3-coder | Orthodox | 14 | +6.13 | +5.33 | +8.04 |
| qwen3-coder | West | 29 | +0.88 | +1.43 | +1.45 |
| qwen3.5-122b-a10b | African-Islamic | 19 | +2.98 | +4.42 | +4.42 |
| qwen3.5-122b-a10b | East Asia | 9 | +2.14 | +1.64 | +2.17 |
| qwen3.5-122b-a10b | Latin America | 14 | +3.23 | +4.60 | +5.12 |
| qwen3.5-122b-a10b | Orthodox | 14 | +4.00 | +5.33 | +6.60 |
| qwen3.5-122b-a10b | West | 29 | +0.07 | +1.43 | +2.04 |
| claude-fable-5.1 | African-Islamic | 19 | +4.01 | +4.29 | +4.57 |
| claude-fable-5.1 | East Asia | 9 | +3.52 | +1.51 | +3.62 |
| claude-fable-5.1 | Latin America | 14 | +4.69 | +4.47 | +5.85 |
| claude-fable-5.1 | Orthodox | 14 | +5.78 | +5.14 | +7.65 |
| claude-fable-5.1 | West | 29 | +0.74 | +1.32 | +1.36 |
| qwen3-30b-a3b | African-Islamic | 19 | +4.94 | +4.29 | +5.13 |
| qwen3-30b-a3b | East Asia | 9 | +4.76 | +1.51 | +5.10 |
| qwen3-30b-a3b | Latin America | 14 | +6.00 | +4.47 | +6.80 |
| qwen3-30b-a3b | Orthodox | 14 | +7.38 | +5.14 | +8.90 |
| qwen3-30b-a3b | West | 29 | +1.34 | +1.32 | +1.43 |
| claude-opus-4.7 | African-Islamic | 19 | +4.11 | +4.17 | +4.55 |
| claude-opus-4.7 | East Asia | 9 | +3.65 | +1.37 | +3.83 |
| claude-opus-4.7 | Latin America | 14 | +4.83 | +4.34 | +5.87 |
| claude-opus-4.7 | Orthodox | 14 | +5.96 | +4.94 | +7.66 |
| claude-opus-4.7 | West | 29 | +0.81 | +1.21 | +1.22 |
| deepseek-v4.1-flash | African-Islamic | 19 | +3.60 | +4.17 | +4.32 |
| deepseek-v4.1-flash | East Asia | 9 | +2.96 | +1.37 | +3.02 |
| deepseek-v4.1-flash | Latin America | 14 | +4.10 | +4.34 | +5.40 |
| deepseek-v4.1-flash | Orthodox | 14 | +5.07 | +4.94 | +7.00 |
| deepseek-v4.1-flash | West | 29 | +0.47 | +1.21 | +1.36 |
| gemma-3-27b-it | African-Islamic | 19 | +4.22 | +4.17 | +4.60 |
| gemma-3-27b-it | East Asia | 9 | +3.79 | +1.37 | +4.00 |
| gemma-3-27b-it | Latin America | 14 | +4.98 | +4.34 | +5.97 |
| gemma-3-27b-it | Orthodox | 14 | +6.13 | +4.94 | +7.79 |
| gemma-3-27b-it | West | 29 | +0.88 | +1.21 | +1.21 |
| qwen-2.5-72b-instruct | African-Islamic | 19 | +4.22 | +4.17 | +4.60 |
| qwen-2.5-72b-instruct | East Asia | 9 | +3.79 | +1.37 | +4.00 |
| qwen-2.5-72b-instruct | Latin America | 14 | +4.98 | +4.34 | +5.97 |
| qwen-2.5-72b-instruct | Orthodox | 14 | +6.13 | +4.94 | +7.79 |
| qwen-2.5-72b-instruct | West | 29 | +0.88 | +1.21 | +1.21 |
| qwen2.5-vl-72b-instruct | African-Islamic | 19 | +4.01 | +4.17 | +4.50 |
| qwen2.5-vl-72b-instruct | East Asia | 9 | +3.52 | +1.37 | +3.67 |
| qwen2.5-vl-72b-instruct | Latin America | 14 | +4.69 | +4.34 | +5.77 |
| qwen2.5-vl-72b-instruct | Orthodox | 14 | +5.78 | +4.94 | +7.52 |
| qwen2.5-vl-72b-instruct | West | 29 | +0.74 | +1.21 | +1.23 |
| qwen3-coder-plus | African-Islamic | 19 | +4.42 | +4.17 | +4.73 |
| qwen3-coder-plus | East Asia | 9 | +4.07 | +1.37 | +4.33 |
| qwen3-coder-plus | Latin America | 14 | +5.27 | +4.34 | +6.18 |
| qwen3-coder-plus | Orthodox | 14 | +6.49 | +4.94 | +8.07 |
| qwen3-coder-plus | West | 29 | +1.01 | +1.21 | +1.22 |
| qwen3-vl-8b-instruct | African-Islamic | 19 | +4.32 | +4.17 | +4.66 |
| qwen3-vl-8b-instruct | East Asia | 9 | +3.93 | +1.37 | +4.16 |
| qwen3-vl-8b-instruct | Latin America | 14 | +5.13 | +4.34 | +6.08 |
| qwen3-vl-8b-instruct | Orthodox | 14 | +6.31 | +4.94 | +7.93 |
| qwen3-vl-8b-instruct | West | 29 | +0.94 | +1.21 | +1.22 |
| qwen-2.5-7b-instruct | African-Islamic | 19 | +3.70 | +4.05 | +4.28 |
| qwen-2.5-7b-instruct | East Asia | 9 | +3.10 | +1.24 | +3.23 |
| qwen-2.5-7b-instruct | Latin America | 14 | +4.25 | +4.21 | +5.40 |
| qwen-2.5-7b-instruct | Orthodox | 14 | +5.25 | +4.75 | +7.00 |
| qwen-2.5-7b-instruct | West | 29 | +0.54 | +1.11 | +1.18 |
| qwen3.5-9b | African-Islamic | 19 | +3.19 | +4.05 | +4.11 |
| qwen3.5-9b | East Asia | 9 | +2.41 | +1.24 | +2.44 |
| qwen3.5-9b | Latin America | 14 | +3.52 | +4.21 | +4.97 |
| qwen3.5-9b | Orthodox | 14 | +4.36 | +4.75 | +6.37 |
| qwen3.5-9b | West | 29 | +0.21 | +1.11 | +1.43 |
| qwen3.6-35b-a3b | African-Islamic | 19 | +4.32 | +4.05 | +4.61 |
| qwen3.6-35b-a3b | East Asia | 9 | +3.93 | +1.24 | +4.22 |
| qwen3.6-35b-a3b | Latin America | 14 | +5.13 | +4.21 | +6.01 |
| qwen3.6-35b-a3b | Orthodox | 14 | +6.31 | +4.75 | +7.81 |
| qwen3.6-35b-a3b | West | 29 | +0.94 | +1.11 | +1.12 |
| qwen3.7-flash | African-Islamic | 19 | +4.73 | +4.05 | +4.89 |
| qwen3.7-flash | East Asia | 9 | +4.48 | +1.24 | +4.90 |
| qwen3.7-flash | Latin America | 14 | +5.71 | +4.21 | +6.45 |
| qwen3.7-flash | Orthodox | 14 | +7.02 | +4.75 | +8.39 |
| qwen3.7-flash | West | 29 | +1.21 | +1.11 | +1.25 |
| claude-opus-4.8 | African-Islamic | 19 | +4.32 | +3.93 | +4.55 |
| claude-opus-4.8 | East Asia | 9 | +3.93 | +1.10 | +4.29 |
| claude-opus-4.8 | Latin America | 14 | +5.13 | +4.08 | +5.94 |
| claude-opus-4.8 | Orthodox | 14 | +6.31 | +4.55 | +7.70 |
| claude-opus-4.8 | West | 29 | +0.94 | +1.00 | +1.04 |
| qwen3-14b | African-Islamic | 19 | +4.32 | +3.93 | +4.55 |
| qwen3-14b | East Asia | 9 | +3.93 | +1.10 | +4.29 |
| qwen3-14b | Latin America | 14 | +5.13 | +4.08 | +5.94 |
| qwen3-14b | Orthodox | 14 | +6.31 | +4.55 | +7.70 |
| qwen3-14b | West | 29 | +0.94 | +1.00 | +1.04 |
| qwen3-coder-30b-a3b-instruct | African-Islamic | 19 | +3.19 | +3.93 | +4.01 |
| qwen3-coder-30b-a3b-instruct | East Asia | 9 | +2.41 | +1.10 | +2.47 |
| qwen3-coder-30b-a3b-instruct | Latin America | 14 | +3.52 | +4.08 | +4.87 |
| qwen3-coder-30b-a3b-instruct | Orthodox | 14 | +4.36 | +4.55 | +6.23 |
| qwen3-coder-30b-a3b-instruct | West | 29 | +0.21 | +1.00 | +1.27 |
| qwen3-coder-next | African-Islamic | 19 | +4.63 | +3.93 | +4.77 |
| qwen3-coder-next | East Asia | 9 | +4.34 | +1.10 | +4.80 |
| qwen3-coder-next | Latin America | 14 | +5.56 | +4.08 | +6.27 |
| qwen3-coder-next | Orthodox | 14 | +6.84 | +4.55 | +8.14 |
| qwen3-coder-next | West | 29 | +1.14 | +1.00 | +1.17 |
| qwen3.6-flash | African-Islamic | 19 | +4.73 | +3.93 | +4.85 |
| qwen3.6-flash | East Asia | 9 | +4.48 | +1.10 | +4.97 |
| qwen3.6-flash | Latin America | 14 | +5.71 | +4.08 | +6.39 |
| qwen3.6-flash | Orthodox | 14 | +7.02 | +4.55 | +8.28 |
| qwen3.6-flash | West | 29 | +1.21 | +1.00 | +1.22 |
| qwen3-235b-a22b-2507 | African-Islamic | 19 | +4.63 | +3.81 | +4.74 |
| qwen3-235b-a22b-2507 | East Asia | 9 | +4.34 | +0.96 | +4.88 |
| qwen3-235b-a22b-2507 | Latin America | 14 | +5.56 | +3.94 | +6.21 |
| qwen3-235b-a22b-2507 | Orthodox | 14 | +6.84 | +4.36 | +8.03 |
| qwen3-235b-a22b-2507 | West | 29 | +1.14 | +0.89 | +1.15 |
| qwen3-235b-a22b | African-Islamic | 19 | +4.63 | +3.69 | +4.71 |
| qwen3-235b-a22b | East Asia | 9 | +4.34 | +0.83 | +4.96 |
| qwen3-235b-a22b | Latin America | 14 | +5.56 | +3.81 | +6.15 |
| qwen3-235b-a22b | Orthodox | 14 | +6.84 | +4.16 | +7.93 |
| qwen3-235b-a22b | West | 29 | +1.14 | +0.78 | +1.15 |
| qwen3-vl-235b-a22b-instruct | African-Islamic | 19 | +4.22 | +3.56 | +4.34 |
| qwen3-vl-235b-a22b-instruct | East Asia | 9 | +3.79 | +0.69 | +4.35 |
| qwen3-vl-235b-a22b-instruct | Latin America | 14 | +4.98 | +3.68 | +5.63 |
| qwen3-vl-235b-a22b-instruct | Orthodox | 14 | +6.13 | +3.97 | +7.23 |
| qwen3-vl-235b-a22b-instruct | West | 29 | +0.88 | +0.68 | +0.88 |
| qwen3.5-35b-a3b | African-Islamic | 19 | +3.60 | +3.56 | +3.93 |
| qwen3.5-35b-a3b | East Asia | 9 | +2.96 | +0.69 | +3.31 |
| qwen3.5-35b-a3b | Latin America | 14 | +4.10 | +3.68 | +4.98 |
| qwen3.5-35b-a3b | Orthodox | 14 | +5.07 | +3.97 | +6.37 |
| qwen3.5-35b-a3b | West | 29 | +0.47 | +0.68 | +0.68 |
| qwen3-30b-a3b-instruct-2507 | African-Islamic | 19 | +4.73 | +3.44 | +4.75 |
| qwen3-30b-a3b-instruct-2507 | East Asia | 9 | +4.48 | +0.56 | +5.31 |
| qwen3-30b-a3b-instruct-2507 | Latin America | 14 | +5.71 | +3.55 | +6.16 |
| qwen3-30b-a3b-instruct-2507 | Orthodox | 14 | +7.02 | +3.77 | +7.90 |
| qwen3-30b-a3b-instruct-2507 | West | 29 | +1.21 | +0.57 | +1.30 |
| qwen3-32b | African-Islamic | 19 | +4.32 | +3.44 | +4.39 |
| qwen3-32b | East Asia | 9 | +3.93 | +0.56 | +4.61 |
| qwen3-32b | Latin America | 14 | +5.13 | +3.55 | +5.68 |
| qwen3-32b | Orthodox | 14 | +6.31 | +3.77 | +7.28 |
| qwen3-32b | West | 29 | +0.94 | +0.57 | +0.96 |
| qwen3-8b | African-Islamic | 19 | +4.42 | +3.44 | +4.48 |
| qwen3-8b | East Asia | 9 | +4.07 | +0.56 | +4.78 |
| qwen3-8b | Latin America | 14 | +5.27 | +3.55 | +5.80 |
| qwen3-8b | Orthodox | 14 | +6.49 | +3.77 | +7.43 |
| qwen3-8b | West | 29 | +1.01 | +0.57 | +1.04 |
| llama-4-scout | African-Islamic | 19 | +4.42 | +3.32 | +4.46 |
| llama-4-scout | East Asia | 9 | +4.07 | +0.42 | +4.88 |
| llama-4-scout | Latin America | 14 | +5.27 | +3.42 | +5.75 |
| llama-4-scout | Orthodox | 14 | +6.49 | +3.58 | +7.34 |
| llama-4-scout | West | 29 | +1.01 | +0.46 | +1.09 |
| qwen3-vl-30b-a3b-instruct | African-Islamic | 19 | +3.50 | +3.32 | +3.75 |
| qwen3-vl-30b-a3b-instruct | East Asia | 9 | +2.83 | +0.42 | +3.30 |
| qwen3-vl-30b-a3b-instruct | Latin America | 14 | +3.96 | +3.42 | +4.73 |
| qwen3-vl-30b-a3b-instruct | Orthodox | 14 | +4.89 | +3.58 | +6.00 |
| qwen3-vl-30b-a3b-instruct | West | 29 | +0.41 | +0.46 | +0.47 |
| qwen3-vl-32b-instruct | African-Islamic | 19 | +4.22 | +3.32 | +4.28 |
| qwen3-vl-32b-instruct | East Asia | 9 | +3.79 | +0.42 | +4.53 |
| qwen3-vl-32b-instruct | Latin America | 14 | +4.98 | +3.42 | +5.51 |
| qwen3-vl-32b-instruct | Orthodox | 14 | +6.13 | +3.58 | +7.03 |
| qwen3-vl-32b-instruct | West | 29 | +0.88 | +0.46 | +0.92 |
| qwen-plus-2025-07-28 | African-Islamic | 19 | +4.63 | +3.08 | +4.63 |
| qwen-plus-2025-07-28 | East Asia | 9 | +4.34 | +0.15 | +5.43 |
| qwen-plus-2025-07-28 | Latin America | 14 | +5.56 | +3.15 | +5.90 |
| qwen-plus-2025-07-28 | Orthodox | 14 | +6.84 | +3.19 | +7.49 |
| qwen-plus-2025-07-28 | West | 29 | +1.14 | +0.25 | +1.45 |