ResearchDatasetsPIQA, WinoGrande, HellaSwag, ARC, LAMBADAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsZero-shot EvaluationPIQA, WinoGrande, HellaSwag, ARC (Easy and Challenge), LAMBADA (test)77.07Average Accuracy102
Zero-shot EvaluationPIQA, WinoGrande, HellaSwag, ARC (Easy and Challenge), LAMBADA (test)77.07Average Accuracy102