Model

CodeQwen1.5-7B

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
MMLU40.5exact_matchN/AIndependentmediumarxiv.org
WinoGrande59.8accuracyN/AIndependentmediumarxiv.org

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K37.7exact_matchN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…