Mathematical Reasoning on Minerva Math (Accuracy, Length)
47.9AccuracyDAPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DAPOBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 47.9 | 2,546 | |
| R1-7BBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 47.1 | 3,063 | |
| Entropy ShapeBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 46.7 | 2,274 | |
| CESBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 42.1 | 1,921 |