ResearchDatasetsMMLU, GSM, HellaSwag, TruthfulQA, ARC, CodeXMMLU, GSM, HellaSwag, TruthfulQA, ARC, CodeXFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAggregate Performance EvaluationMMLU, GSM, HellaSwag, TruthfulQA, ARC-C, CodeX5.32Improvement18