Social Intelligence Evaluation on SENTIPOLIS v1 (test)
7.217Empathy (EMP)Qwen3-235B-A22B
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Qwen3-235B-A22BEvaluator=Sonnet-4.52026.01 | 7.217 | 7.906 | 8.318 | 5.92 | 7.738 | -1.57 | |
| GPT-5.2Evaluator=Sonnet-4.52026.01 | 7.072 | 8.799 | 6.732 | 8.051 | 9.201 | -0.581 | |
| Qwen3-235B-A22BEvaluator=DeepSeek-V3.22026.01 | 6.898 | 9.049 | 8.825 | 8.023 | 9.203 | -0.458 | |
| GPT-5.2Evaluator=GPT-5.12026.01 | 6.765 | 8.583 | 6.662 | 7.972 | 9.25 | 0 | |
| Kimi-K2-0905Evaluator=Sonnet-4.52026.01 | 6.75 | 8.804 | 7.822 | 7.01 | 7.067 | -2.74 | |
| Qwen3-235B-A22BEvaluator=GPT-5.12026.01 | 6.569 | 8.631 | 8.195 | 7.38 | 8.749 | -0.23 | |
| Kimi-K2-0905Evaluator=GPT-5.12026.01 | 6.524 | 8.974 | 7.622 | 8.139 | 8.619 | -1.511 | |
| MiMo-v2-FlashEvaluator=Sonnet-4.52026.01 | 6.495 | 6.857 | 5.711 | 6.748 | 8.117 | -0.26 | |
| GPT-4o-miniEvaluator=GPT-5.12026.01 | 6.418 | 6.7 | 5.378 | 4.924 | 7.903 | 0 | |
| GPT-4o-miniEvaluator=Sonnet-4.52026.01 | 6.387 | 5.059 | 3.938 | 3.54 | 6.973 | -0.023 | |
| MiMo-v2-FlashEvaluator=GPT-5.12026.01 | 6.286 | 7.805 | 5.424 | 6.908 | 8.393 | -0.09 | |
| Kimi-K2-0905Evaluator=DeepSeek-V3.22026.01 | 6.193 | 9.277 | 8.198 | 7.768 | 7.398 | -1.765 | |
| MiMo-v2-FlashEvaluator=DeepSeek-V3.22026.01 | 6.193 | 7.468 | 5.705 | 7.093 | 8.208 | -0.143 | |
| GPT-5.2Evaluator=DeepSeek-V3.22026.01 | 6.17 | 8.838 | 6.458 | 8.593 | 9.573 | -0.122 | |
| GPT-4o-miniEvaluator=DeepSeek-V3.22026.01 | 5.953 | 7.138 | 5.377 | 4.843 | 8.363 | -0.043 | |
| Grok-4Evaluator=Sonnet-4.52026.01 | 5.696 | 7.348 | 5.666 | 7.285 | 8.574 | -0.416 | |
| Grok-4Evaluator=GPT-5.12026.01 | 5.625 | 8.074 | 5.603 | 7.47 | 8.765 | -0.015 | |
| Grok-4Evaluator=DeepSeek-V3.22026.01 | 5.415 | 8.355 | 6.522 | 8.13 | 8.925 | -0.097 |