ResearchDatasetsArcC, ArcE, HS, PiQA, WGArcC, ArcE, HS, PiQA, WGFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsZero-shot EvaluationArcC, ArcE, HS, PiQA, WG (test val)76Average Accuracy61