Model

OPT 1.3B

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ62.5test_accuracyN/AIndependentmediumarxiv.org
BoolQ60.5accuracyN/AIndependentmediumarxiv.org
BoolQ59.6scoreN/AIndependentmediumarxiv.org
HellaSwag41.5overall_accuracyN/AIndependentmediumarxiv.org
OpenBookQA24.0accuracyN/AIndependentmediumarxiv.org
PIQA69.0scoreN/AIndependentmediumarxiv.org
RTE60.9test_accuracyN/AIndependentmediumarxiv.org
RTE54.2accuracyN/AIndependentmediumarxiv.org
WiC56.1test_accuracyN/AIndependentmediumarxiv.org
WinoGrande61.0accuracyN/AIndependentmediumarxiv.org
WSC64.2test_accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…