Response Length on MMLU STEM Science Reasoning
1,956Response Length (Tokens)DeepSeek-R1-Distill
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-R1-DistillModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 1,956 | |
| DeepSeek-R1-DistillModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 1,572 | |
| AdaCoTModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 1,214 | |
| AdaCoTModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 1,029 | |
| AdaptThinkModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 1,023 | |
| AdaptThinkModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 995 | |
| LHRMsModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 955 | |
| S-GRPOModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 812 | |
| SuCoModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 745 | |
| S-GRPOModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 717 | |
| LHRMsModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 628 | |
| SuCoModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 505 |