Model

GLaM

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
HellaSwag77.2overall_accuracyN/ASelf-reportedmediumarxiv.org
OpenBookQA63.0accuracyN/ASelf-reportedmediumarxiv.org
Trivia QA75.8exact_matchN/ASelf-reportedmediumarxiv.org
WinoGrande79.2accuracyN/ASelf-reportedmediumarxiv.org

Reproduced by the community

Loading community runs…