Benchmark

BigCodeBench-Hard

BigCodeBench-Hard is a subset of 148 challenging programming tasks from BigCodeBench, designed to evaluate large language models' ability to solve…

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

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Qwen2.5-Coder 32B InstructQwen0.272024-09-19evidence

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.