Theory-of-Mind Reasoning on apartment seen
87Belief Inference Accuracy
8B ↬ 405B
Updated 22d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.06 | 87 | 77 | 81.3 | |
2025.06 | 85.6 | 74.6 | 79.3 | |
2025.06 | 85 | 62 | 71.8 | |
2025.06 | 84.6 | 73.6 | 78.3 | |
2025.06 | 83.6 | 74.6 | 78.5 | |
2025.06 | 80.3 | 56.3 | 66.6 |