ResearchDatasetsMATH, GSM, AIME, AMC, OlympiadBench, Minerva MathMATH, GSM, AIME, AMC, OlympiadBench, Minerva MathFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMathematical ReasoningMATH 500, GSM8K, AIME 24, AMC 23, OlympiadBench, and Minerva Math (test)46.92Final Accuracy24
Mathematical ReasoningMATH 500, GSM8K, AIME 24, AMC 23, OlympiadBench, and Minerva Math (test)46.92Final Accuracy24