ResearchDatasetsMNLI, SCIQ, LAMBADA, HellaSwag, ARC, MMLUFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsDownstream Task EvaluationMNLI, SCIQ, LAMBADA, HellaSwag, ARC, MMLU0.385MNLI Acc2