Model

Xgen 7B 8K Base

Salesforce

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ74.3scoreN/ASelf-reportedmediumarxiv.org
HellaSwag74.2overall_accuracyN/ASelf-reportedmediumarxiv.org
MMLU36.3exact_matchN/ASelf-reportedmediumarxiv.org
OpenBookQA40.2accuracyN/ASelf-reportedmediumarxiv.org
PIQA75.5scoreN/ASelf-reportedmediumarxiv.org
WinoGrande64.9accuracyN/ASelf-reportedmediumarxiv.org

Reproduced by the community

Loading community runs…