ResearchDatasetsIn-Domain Reasoning BenchmarksFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsReasoningIn-Domain Reasoning Benchmarks AIME, AMC, MATH-500, Minerva, Olympiad40AIME 24 Score7