Scientific Reasoning on bio
33.9Pass RateSRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| SRPOModel=Qwen2.5-14B-Instruct2026.05 | 33.9 | |
| RRPOModel=Qwen2.5-14B-Instruct2026.05 | 33.1 | |
| SPO-TreeModel=Qwen2.5-14B-Instruct2026.05 | 31.4 | |
| Cr-GRPOModel=Qwen2.5-14B-Instruct2026.05 | 30.9 | |
| SCoReModel=Qwen2.5-14B-Instruct2026.05 | 30.2 | |
| GRPOModel=Qwen2.5-14B-Instruct2026.05 | 30.1 | |
| BaseModel=Qwen2.5-14B-Instruct2026.05 | 30 | |
| SCoReModel=OLMo-3-7B-Instruct2026.05 | 29.6 | |
| SRPOModel=OLMo-3-7B-Instruct2026.05 | 28.7 | |
| RRPOModel=OLMo-3-7B-Instruct2026.05 | 28 | |
| SPO-TreeModel=OLMo-3-7B-Instruct2026.05 | 27.3 | |
| Cr-GRPOModel=OLMo-3-7B-Instruct2026.05 | 26.7 | |
| GRPOModel=OLMo-3-7B-Instruct2026.05 | 26.3 | |
| BaseModel=OLMo-3-7B-Instruct2026.05 | 25.8 |