ResearchDatasetsCompetition-level MathematicsCompetition-level MathematicsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningCompetition-level Mathematics AIME24, AIME25, AMC23 (test)86.67AIME24 pass@325