Model

FLAN-T5-Large 783M

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
HellaSwag48.7accuracyN/AIndependentmediumarxiv.org
OpenBookQA31.2accuracyN/AIndependentmediumarxiv.org
PIQA72.2accuracyN/AIndependentmediumarxiv.org
WiC64.7accuracyN/AIndependentmediumarxiv.org
WinoGrande59.9accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…