Theory-of-Mind Reasoning on medieval castle
85.6Belief Inference Accuracy
8B ↬ 405B
Updated 22d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.06 | 85.6 | 75.2 | 79.7 | |
2025.06 | 84.6 | 73 | 78 | |
2025.06 | 83.6 | 75 | 78.7 | |
2025.06 | 83.3 | 64 | 72.2 | |
2025.06 | 82.6 | 57.6 | 68.3 | |
2025.06 | 81 | 65 | 71.8 |