Model

Vicuna 13B V1.1

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BBH43.0averageN/AIndependentmediumarxiv.org
BoolQ83.5scoreN/AIndependentmediumarxiv.org
HellaSwag57.8overall_accuracyN/AIndependentmediumarxiv.org
OpenBookQA33.0accuracyN/AIndependentmediumarxiv.org
PIQA77.4scoreN/AIndependentmediumarxiv.org
WinoGrande70.8accuracyN/AIndependentmediumarxiv.org

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K28.1exact_matchN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…