ResearchDatasetsAQuA, GSM8K, MAWPS, SVAMPAQuA, GSM8K, MAWPS, SVAMPFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsArithmetic ReasoningAQuA, GSM8K, MAWPS, SVAMP62.2AQuA Accuracy31