Theory of Mind Reasoning on FanToM
96.131st-Order AccuracyRECTOM
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| RECTOMModel=GPT-5.42026.06 | 96.13 | 99.3 | 97.53 | |
| RECTOMModel=Qwen3.52026.06 | 92.82 | 86.01 | 89.81 | |
| TIMETOMModel=GPT-5.42026.06 | 92.27 | 92.31 | 92.28 | |
| SIMTOMModel=GPT-5.42026.06 | 91.16 | 95.8 | 93.21 | |
| RECTOMModel=Gemini-32026.06 | 91.16 | 91.61 | 91.36 | |
| SIMTOMModel=Qwen3.52026.06 | 89.5 | 81.82 | 86.11 | |
| CoTModel=GPT-5.42026.06 | 88.95 | 86.71 | 87.96 | |
| RECTOMModel=Gemma-42026.06 | 87.29 | 84.62 | 86.11 | |
| TIMETOMModel=Qwen3.52026.06 | 86.74 | 85.31 | 86.11 | |
| SIMTOMModel=Gemini-32026.06 | 82.32 | 89.51 | 85.49 | |
| CoTModel=Qwen3.52026.06 | 78.45 | 85.31 | 81.48 | |
| CoTModel=Gemini-32026.06 | 77.35 | 90.21 | 83.02 | |
| TIMETOMModel=Gemma-42026.06 | 76.24 | 79.72 | 77.78 | |
| TIMETOMModel=Gemini-32026.06 | 74.59 | 91.61 | 82.1 | |
| SIMTOMModel=Gemma-42026.06 | 71.27 | 80.42 | 75.31 | |
| CoTModel=Gemma-42026.06 | 63.54 | 75.52 | 68.83 |