Code Generation on MBPP (Response Length Tokens)
3,511Response Length (Tokens)DeepSeek-R1-Distill
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-R1-DistillModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 3,511 | |
| DeepSeek-R1-DistillModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 3,182 | |
| AdaCoTModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 1,720 | |
| LHRMsModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 1,487 | |
| S-GRPOModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 1,481 | |
| AdaCoTModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 1,423 | |
| AdaptThinkModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 1,422 | |
| S-GRPOModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 1,356 | |
| AdaptThinkModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 1,242 | |
| LHRMsModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 1,158 | |
| SuCoModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 1,149 | |
| SuCoModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 930 |