ResearchDatasetsAIME, AMC, MATH, GSM8KAIME, AMC, MATH, GSM8KFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical Problem SolvingAIME, AMC, MATH, GSM8K (test)58.5AIME Accuracy3