ResearchDatasetsGSM8K, MATH500, OlympiadBench, AIMEGSM8K, MATH500, OlympiadBench, AIMEFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningGSM8K, MATH500, OlympiadBench, AIME (test)71.4Pass@112