ResearchDatasetsMATH and AIMEFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMathematical ReasoningMATH-500 and AIME202480.8Micro Avg. Accuracy5Mathematical ReasoningMATH500, AIME24, and AIME25 Average combined (test)2.5Delta Accuracy (pp)2