Mathematical Reasoning on Olympiad Bench (Acc, Len)
55.8AccuracyCES
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CESBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 55.8 | 4,297 | |
| DAPOBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 53.6 | 5,136 | |
| Entropy ShapeBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 53.5 | 4,821 | |
| R1-7BBackbone=DeepSeek-R1-Distill-Qwen-7B2026.05 | 52.3 | 5,599 |