Strategic Reasoning on stra
74.9Pass RateSRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| SRPOModel=Qwen2.5-14B-Instruct2026.05 | 74.9 | |
| Cr-GRPOModel=Qwen2.5-14B-Instruct2026.05 | 72.1 | |
| SCoReModel=Qwen2.5-14B-Instruct2026.05 | 72 | |
| SPO-TreeModel=Qwen2.5-14B-Instruct2026.05 | 71.7 | |
| BaseModel=Qwen2.5-14B-Instruct2026.05 | 71.4 | |
| RRPOModel=Qwen2.5-14B-Instruct2026.05 | 69.6 | |
| GRPOModel=Qwen2.5-14B-Instruct2026.05 | 69.5 | |
| RRPOModel=OLMo-3-7B-Instruct2026.05 | 68.1 | |
| SRPOModel=OLMo-3-7B-Instruct2026.05 | 66.6 | |
| GRPOModel=OLMo-3-7B-Instruct2026.05 | 62 | |
| SCoReModel=OLMo-3-7B-Instruct2026.05 | 60.2 | |
| BaseModel=OLMo-3-7B-Instruct2026.05 | 55 | |
| SPO-TreeModel=OLMo-3-7B-Instruct2026.05 | 54.3 | |
| Cr-GRPOModel=OLMo-3-7B-Instruct2026.05 | 53.1 |