ResearchDatasetsArcC, ArcE, HS, PiQA, WGFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsZero-shot EvaluationArcC, ArcE, HS, PiQA, WG (test val)76Average Accuracy61