ResearchDatasetsMMLU, PIQA, HellaSwag, WinoGrande, ARC-ChallengeMMLU, PIQA, HellaSwag, WinoGrande, ARC-ChallengeFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsLanguage Understanding and ReasoningMMLU, PIQA, HellaSwag, WinoGrande, ARC-Challenge46.45MMLU (5s)13