ResearchDatasetsAIME, HMMT, BeyondAIME, AMO-Bench, IMO-AnswerBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMathematicsAIME-25, HMMT25(Feb), BeyondAIME, AMO-Bench, IMO-AnswerBench97.5Pass@125