Mathematical Reasoning on MATH (Accuracy Mean, Std, and CI)
66.69Accuracy (Mean)
KTO
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 66.69 | 0.27 | 66.35 | |
2026.06 | 63.95 | 0.55 | 63.26 | |
2026.06 | 63.82 | 0.43 | 63.28 | |
2026.06 | 60.54 | 0.42 | 60.02 | |
2026.06 | 59.6 | 0.67 | 58.77 | |
2026.06 | 59.2 | 0.19 | 58.96 | |
2026.06 | 56.31 | 0.23 | 56.02 | |
2026.06 | 53.98 | 0.37 | 53.52 | |
2026.06 | 52.59 | 0.45 | 52.03 | |
2026.06 | 52.25 | 0.67 | 51.41 | |
2026.06 | 50.72 | 0.72 | 49.82 | |
2026.06 | 48.92 | 0.36 | 48.47 | |
2026.06 | 48.02 | 0.48 | 47.42 | |
2026.06 | 47.06 | 0.21 | 46.79 |