List your company

Code Generation on MBPP (Response Length Tokens)

3,511Response Length (Tokens)DeepSeek-R1-Distill
826.761,523.632,220.52,917.37Jun 16, 2026

Evaluation results

MethodLinks
DeepSeek-R1-DistillModel Scale=1.5B, Base Model=Qwen2.5-Math2026.063,511
DeepSeek-R1-DistillModel Scale=7B, Base Model=Qwen2.5-Math2026.063,182
AdaCoTModel Scale=1.5B, Base Model=Qwen2.5-Math2026.061,720
LHRMsModel Scale=7B, Base Model=Qwen2.5-Math2026.061,487
S-GRPOModel Scale=1.5B, Base Model=Qwen2.5-Math2026.061,481
AdaCoTModel Scale=7B, Base Model=Qwen2.5-Math2026.061,423
AdaptThinkModel Scale=1.5B, Base Model=Qwen2.5-Math2026.061,422
S-GRPOModel Scale=7B, Base Model=Qwen2.5-Math2026.061,356
AdaptThinkModel Scale=7B, Base Model=Qwen2.5-Math2026.061,242
LHRMsModel Scale=1.5B, Base Model=Qwen2.5-Math2026.061,158
SuCoModel Scale=7B, Base Model=Qwen2.5-Math2026.061,149
SuCoModel Scale=1.5B, Base Model=Qwen2.5-Math2026.06930