ResearchDatasetsBoolQ, COPA, WinoG., SVAMP, MAWPSBoolQ, COPA, WinoG., SVAMP, MAWPSFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReasoning and Math Problem SolvingBoolQ, COPA, WinoG., SVAMP, MAWPS (test)88.2BoolQ Accuracy19