Mathematical Reasoning on lvl5
67.5Pass RateSRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| SRPOModel=OLMo-3-7B-Instruct2026.05 | 67.5 | |
| GRPOModel=OLMo-3-7B-Instruct2026.05 | 67.1 | |
| RRPOModel=OLMo-3-7B-Instruct2026.05 | 66.2 | |
| Cr-GRPOModel=OLMo-3-7B-Instruct2026.05 | 58.5 | |
| SPO-TreeModel=OLMo-3-7B-Instruct2026.05 | 57.4 | |
| BaseModel=OLMo-3-7B-Instruct2026.05 | 56.8 | |
| SRPOModel=Qwen2.5-14B-Instruct2026.05 | 55.2 | |
| SCoReModel=Qwen2.5-14B-Instruct2026.05 | 54.1 | |
| RRPOModel=Qwen2.5-14B-Instruct2026.05 | 52.7 | |
| GRPOModel=Qwen2.5-14B-Instruct2026.05 | 52.1 | |
| SPO-TreeModel=Qwen2.5-14B-Instruct2026.05 | 51.5 | |
| Cr-GRPOModel=Qwen2.5-14B-Instruct2026.05 | 51.1 | |
| BaseModel=Qwen2.5-14B-Instruct2026.05 | 51 | |
| SCoReModel=OLMo-3-7B-Instruct2026.05 | 43.4 |