Model

Baichuan-2-13B-Base

Baichuan

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BBH49.0averageN/AIndependentmediumarxiv.org
BBH48.8averageN/ASelf-reportedmediumarxiv.org
BoolQ67.0scoreN/AIndependentmediumarxiv.org
HellaSwag70.8overall_accuracyN/AIndependentmediumarxiv.org
LAMBADA74.0scoreN/AIndependentmediumarxiv.org
MMLU59.2exact_matchN/AIndependentmediumarxiv.org
MMLU59.2exact_matchN/ASelf-reportedmediumarxiv.org
PIQA78.1scoreN/AIndependentmediumarxiv.org

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K52.8exact_matchN/ASelf-reportedmediumarxiv.org
GSM8K52.8exact_matchN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…