Mathematical Reasoning on MATH (test) (accuracy (r*), self-reward (r_self))
70.6Accuracy (r*)
Qwen / Base
Updated 27d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 70.6 | 0.093 | |
2026.05 | 68.2 | 0.064 | |
2026.05 | 67.7 | 0.08 | |
2026.05 | 67.6 | 0.06 | |
2026.05 | 66.1 | 0.073 | |
2026.05 | 63.1 | 0.094 | |
2026.05 | 57.9 | 0.185 | |
2026.05 | 51.3 | 0.175 | |
2026.05 | 49.3 | 0.155 | |
2026.05 | 48.1 | 0.088 | |
2026.05 | 47.6 | 0.173 | |
2026.05 | 47 | 0.118 | |
2026.05 | 46.1 | 0.086 | |
2026.05 | 45.7 | 0.106 | |
2026.05 | 44.9 | 0.234 | |
2026.05 | 41 | 0.405 |