ResearchDatasetsMATH, AMC, AIMEFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMath ReasoningMATH-500, AMC-23, AIME-25 Average53.5Mean@3212Mathematical ReasoningMATH500, AMC23, AIME24, AIME2554.2Majority Score6