ResearchDatasetsWinoGrande, PiQA, HellaSwag, ARC, BoolQFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsZero-shot ClassificationWinoGrande, PiQA, HellaSwag, ARC-easy, ARC-challenge, BoolQ Zero-shot76.88Avg Zero-shot Acc31
Zero-shot ClassificationWinoGrande, PiQA, HellaSwag, ARC-easy, ARC-challenge, BoolQ Zero-shot76.88Avg Zero-shot Acc31