Benchmark

HumanEval Plus

Enhanced version of HumanEval that extends the original test cases by 80x using EvalPlus framework for rigorous evaluation of LLM-synthesized code…

Modality
text
Categories
reasoning, code
Openness
unknown
Source
llm_stats
Reported scores
1

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Mistral Small 3.2 24B InstructMistral0.9292025-06-20evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.