Theory of Mind reasoning on MMToM-QA
98.5Overall Accuracy
UserHarness
Updated 6d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.05 | 98.5 | - | - | |
2026.05 | 98.33 | - | - | |
2026.05 | 98.17 | - | - | |
2026.05 | 98.17 | - | - | |
2026.05 | 98 | - | - | |
2026.05 | 97.83 | - | - | |
2026.05 | 97.83 | - | - | |
2026.05 | 97.67 | - | - | |
2026.05 | 97.5 | - | - | |
2026.05 | 97.33 | - | - | |
2026.05 | 97 | - | - | |
2026.05 | 96.67 | - | - | |
2026.05 | 83 | - | - | |
2026.05 | 69.83 | - | - | |
2026.05 | 67.5 | - | - | |
| 66.3 | 70.7 | 62 | ||
2026.05 | 64.17 | - | - | |
2026.05 | 63.33 | - | - | |
2026.05 | 62.83 | - | - | |
2026.03 | 61.2 | 64 | 58.3 | |
| 60.5 | 64.3 | 56.7 | ||
2026.05 | 56.17 | - | - | |
2026.05 | 55.33 | - | - | |
2026.05 | 51 | - | - | |
2026.05 | 48.83 | - | - | |
2026.05 | 48.67 | - | - | |
2026.05 | 48 | - | - | |
2026.05 | 47.33 | - | - | |
2026.05 | 47.33 | - | - | |
2026.05 | 47 | - | - | |
2026.05 | 47 | - | - | |
2026.05 | 46.67 | - | - | |
2026.05 | 45.67 | - | - | |
2026.05 | 45.17 | - | - | |
2026.05 | 44.33 | - | - | |
2026.05 | 43.5 | - | - | |
2026.05 | 43.33 | - | - | |
2026.05 | 39.67 | - | - | |
2026.03 | 38.2 | 47 | 29.3 | |
2026.05 | 37.5 | - | - | |
2026.05 | 37.17 | - | - | |
2026.05 | 37.17 | - | - | |
2026.05 | 35 | - | - | |
2026.05 | 34 | - | - |