Social Reasoning on ToMBench Hard (val)
62.79Accuracy
SocialR1-8B
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.03 | 62.79 | |
2026.03 | 61.28 | |
2026.03 | 55.09 | |
2026.03 | 52.64 | |
2026.03 | 50.42 | |
2026.03 | 48.46 | |
2026.03 | 48.2 | |
2026.03 | 47.28 | |
2026.03 | 44.78 | |
2026.03 | 44.71 | |
2026.03 | 44.36 | |
2026.03 | 44.23 | |
2026.03 | 44.23 | |
2026.03 | 43.64 | |
2026.03 | 43.35 | |
2026.03 | 42.72 | |
2026.03 | 41.19 | |
2026.03 | 40.92 | |
2026.03 | 40.33 | |
2026.03 | 40.12 | |
2026.03 | 39.82 | |
2026.03 | 39.46 | |
2026.03 | 38.62 | |
2026.03 | 37.33 | |
2026.03 | 34.03 | |
2026.03 | 31.87 |