Model

OPT-13b

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ65.0scoreN/AIndependentmediumarxiv.org
HellaSwag69.9overall_accuracyN/AIndependentmediumarxiv.org
KAMEL17.6average_f1N/AIndependentmediumakbc.ws
MMLU25.1exact_matchN/AIndependentmediumarxiv.org
OpenBookQA39.8accuracyN/AIndependentmediumarxiv.org
PIQA75.7scoreN/AIndependentmediumarxiv.org
WinoGrande64.7accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…