Model

Step 5 Preview

StepFun

stepfun.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CritPt20.9accuracyN/AIndependentlowepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
SciCode58.9scoreN/AIndependentmediumartificialanalysis.ai

Reproduced by the community

Loading community runs…