Theory-of-Mind Reasoning on outer space
87.2Belief Inference Accuracy
8B ↬ 405B
Updated 22d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.06 | 87.2 | 75.5 | 80.5 | |
2025.06 | 84 | 58 | 69.1 | |
2025.06 | 84 | 75 | 78.8 | |
2025.06 | 83 | 66 | 73.2 | |
2025.06 | 82.6 | 75.3 | 78.4 | |
2025.06 | 81.6 | 71 | 75.5 |