Model

Stablelm Tuned Alpha 7B

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ59.0scoreN/AIndependentmediumarxiv.org
HellaSwag40.7overall_accuracyN/AIndependentmediumarxiv.org
OpenBookQA32.4accuracyN/AIndependentmediumarxiv.org
PIQA65.8scoreN/AIndependentmediumarxiv.org
WinoGrande51.5accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…