ResearchDatasetsAIME, AMC, and MATHAIME, AMC, and MATHFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningAIME’25, AIME’24, AMC’23, and MATH500 Average (test)92.3Acc@466