Mathematical Reasoning on SVAMP (Acc, Len)
90.3AccuracyDAPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DAPOBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 90.3 | 290 | |
| Entropy ShapeBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 90.3 | 290 | |
| CESBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 90.2 | 276 | |
| R1-7BBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 89.4 | 293 |