Model

OPT-175B

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
ARC-Challenge43.9accuracyN/AIndependentmediumarxiv.org
ARC-Easy71.0accuracyN/AIndependentmediumarxiv.org
BoolQ79.3scoreN/AIndependentmediumcrfm.stanford.edu
BoolQ60.1accuracyN/AIndependentmediumarxiv.org
HellaSwag79.1overall_accuracyN/AIndependentmediumcrfm.stanford.edu
LAMBADA75.6accuracyN/AIndependentmediumarxiv.org
PIQA81.1accuracyN/AIndependentmediumarxiv.org
RTE60.3accuracyN/AIndependentmediumarxiv.org
TruthfulQA21.0mc1N/AIndependentmediumarxiv.org

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K4.0exact_matchN/AIndependentmediumcrfm.stanford.edu

Reproduced by the community

Loading community runs…