Response Length (Tokens) on GSM8K
501Response Length (Tokens)DeepSeek-R1-Distill
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-R1-DistillModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 501 | |
| DeepSeek-R1-DistillModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 465 | |
| AdaCoTModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 443 | |
| AdaCoTModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 422 | |
| AdaptThinkModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 337 | |
| SuCoModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 304 | |
| S-GRPOModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 297 | |
| LHRMsModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 274 | |
| S-GRPOModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 267 | |
| AdaptThinkModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 247 | |
| SuCoModel Scale=7B, Base Model=Qwen2.5-Math2026.06 | 243 | |
| LHRMsModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06 | 242 |