Code Generation on LiveCodeBench V6 (Response Length)
11,073Response Length (Tokens)DeepSeek-R1-Distill
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-R1-DistillModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 11,073 | |
| DeepSeek-R1-DistillModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 10,407 | |
| AdaptThinkModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 8,911 | |
| AdaCoTModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 8,153 | |
| AdaptThinkModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 6,689 | |
| S-GRPOModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 6,534 | |
| AdaCoTModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 6,455 | |
| S-GRPOModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 5,293 | |
| LHRMsModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 4,716 | |
| LHRMsModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 4,294 | |
| SuCoModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 2,809 | |
| SuCoModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 2,629 |