ResearchDatasetsAMC, AIME, HMMT, and OlympiadBenchAMC, AIME, HMMT, and OlympiadBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningAMC, AIME, HMMT, and OlympiadBench Aggregate54.11Accuracy15