ResearchDatasetsIn-Domain Reasoning BenchmarksIn-Domain Reasoning BenchmarksFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReasoningIn-Domain Reasoning Benchmarks AIME, AMC, MATH-500, Minerva, Olympiad40AIME 24 Score7