Model

Dolly V2 12B

Databricks

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ56.3scoreN/AIndependentmediumarxiv.org
HellaSwag70.8overall_accuracyN/AIndependentmediumarxiv.org
MMLU26.2exact_matchN/AIndependentmediumarxiv.org
OpenBookQA39.2accuracyN/AIndependentmediumarxiv.org
PIQA75.4scoreN/AIndependentmediumarxiv.org
WinoGrande61.8accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…