Model

Qwen-14B

Alibaba · open weights

qwenlm.github.io

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BBH55.0averageN/AIndependentmediumarxiv.org
BBH53.4averageN/ASelf-reportedmediumarxiv.org
BoolQ86.2scoreN/ASelf-reportedmediumarxiv.org
LAMBADA71.1scoreN/ASelf-reportedmediumarxiv.org
MMLU66.3exact_matchN/AIndependentmediumarxiv.org
MMLU53.4exact_matchN/ASelf-reportedmediumarxiv.org
PIQA79.9scoreN/AIndependentmediumarxiv.org
PIQA79.9scoreN/ASelf-reportedmediumarxiv.org

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K61.3exact_matchN/AIndependentmediumarxiv.org
GSM8K61.3exact_matchN/ASelf-reportedmediumarxiv.org

Reproduced by the community

Loading community runs…