List your company
ResearchFormerly WizWand

General Reasoning Efficiency on Aggregate Math, Code, Science

1,267Response Length (Tokens)SuCo
1,088.242,294.873,501.54,708.13Jun 16, 2026
Updated 4mo ago

Evaluation results

MethodLinks
SuCoModel Scale=7B, Base Model=Qwen2.5-Math2026.061,267
SuCoModel Scale=1.5B, Base Model=Qwen2.5-Math2026.061,483
LHRMsModel Scale=7B, Base Model=Qwen2.5-Math2026.061,891
LHRMsModel Scale=1.5B, Base Model=Qwen2.5-Math2026.062,055
S-GRPOModel Scale=7B, Base Model=Qwen2.5-Math2026.062,478
S-GRPOModel Scale=1.5B, Base Model=Qwen2.5-Math2026.062,726
AdaptThinkModel Scale=1.5B, Base Model=Qwen2.5-Math2026.062,897
AdaCoTModel Scale=1.5B, Base Model=Qwen2.5-Math2026.062,952
AdaptThinkModel Scale=7B, Base Model=Qwen2.5-Math2026.063,400
AdaCoTModel Scale=7B, Base Model=Qwen2.5-Math2026.063,419
DeepSeek-R1-DistillModel Scale=7B, Base Model=Qwen2.5-Math2026.065,239
DeepSeek-R1-DistillModel Scale=1.5B, Base Model=Qwen2.5-Math2026.065,736