ResearchDatasetsMMLU, GSM8K, MATH, MedQA, MedMCQAMMLU, GSM8K, MATH, MedQA, MedMCQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-domain EvaluationMMLU, GSM8K, MATH, MedQA, MedMCQA56.9Math Accuracy15