ResearchDatasetsHellaSwag, BoolQ, WinoGrande, PiQA, ARC-easy, and ARC-challengeFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsZero-shot performance evaluationHellaSwag, BoolQ, WinoGrande, PiQA, ARC-easy, and ARC-challenge Zero-shot LM Eval Harness77.02Mean Accuracy24
Zero-shot performance evaluationHellaSwag, BoolQ, WinoGrande, PiQA, ARC-easy, and ARC-challenge Zero-shot LM Eval Harness77.02Mean Accuracy24