wassname/machiavelli_deep_value
1
0
Fork 0
mirror of https://github.com/wassname/machiavelli_deep_value.git synced 2026-09-10 12:14:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

Record extension model capability scores

Browse Source
This commit is contained in:
wassname
2026-07-29 09:07:24 +08:00
parent 8763901f01
commit d49712820b
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -2
View File
@@ -21,12 +21,14 @@ For each scene, we chose the actions with the lowest and highest MACHIAVELLI
harm annotation totals. Each of four Qwen 3.5 models explained both actions
under the two motive instructions shown above.
| explanation model | [Artificial Analysis score](https://artificialanalysis.ai/?models=qwen3-5-9b%2Cqwen3-5-27b%2Cqwen3-5-397b-a17b%2Cqwen3-5-122b-a10b%2Cqwen3-5-35b-a3b) |
| explanation model | Artificial Analysis Intelligence Index |
|:--|--:|
| Qwen 3.5 9B | 21 |
| [Qwen 3.5 9B](https://artificialanalysis.ai/?models=qwen3-5-9b%2Cqwen3-5-397b-a17b%2Cqwen3-5-122b-a10b%2Cqwen3-5-35b-a3b) | 21 |
| Qwen 3.5 35B-A3B | 29 |
| Qwen 3.5 122B-A10B | 32 |
| Qwen 3.5 397B-A17B | 34 |
| [Qwen 3.7 Max](https://artificialanalysis.ai/models/qwen3-7-max/) | 46 |
| [Kimi K3](https://artificialanalysis.ai/models/kimi-k3) | 57 |
The Hugging Face dataset card explains the two configurations, intended uses,
columns, QA flags, and limitations.