Model

OPT-125M

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ61.6test_accuracyN/AIndependentmediumarxiv.org
RTE57.0test_accuracyN/AIndependentmediumarxiv.org
WiC53.4test_accuracyN/AIndependentmediumarxiv.org
WSC59.6test_accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…