ResearchDatasetsCountdown, GSM8K, MATH, and SVAMPCountdown, GSM8K, MATH, and SVAMPFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningCountdown, GSM8K, MATH500, and SVAMP54.92Accuracy6