Social Reasoning on SimpleToM
99.24Accuracy
GPT-5
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 99.24 | |
2026.03 | 96.75 | |
2026.03 | 96.72 | |
2026.03 | 96.19 | |
2026.03 | 94.94 | |
2026.03 | 94.33 | |
2026.03 | 93.52 | |
2026.03 | 92.85 | |
2026.03 | 91.98 | |
2026.03 | 90.41 | |
2026.03 | 89.63 | |
2026.03 | 89.6 | |
2026.03 | 76.4 | |
2026.03 | 76.34 | |
2026.03 | 76.29 | |
2026.03 | 75.01 | |
2026.03 | 73.58 | |
2026.03 | 73.55 | |
2026.03 | 71.9 | |
2026.03 | 71.87 | |
2026.03 | 71.11 | |
2026.03 | 66.61 | |
2026.03 | 64.78 | |
2026.03 | 61.76 | |
2026.03 | 61.26 | |
2026.03 | 59.08 | |
2026.03 | 54.11 | |
2026.03 | 51.09 | |
2026.03 | 51.09 |