ResearchDatasetsAIME MATHFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMemorization DetectionAIME Math500 Translated distribution84.4Contaminated Score20Memorization DetectionAIME Math500 Rephrased distribution93.1Contaminated Score20Mathematical ReasoningAIME24, AIME25, MATH500 Combined77.62Average Score13