ResearchDatasetsMMLU, GSM8K, MATH, MedQA, MedMCQAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMulti-domain EvaluationMMLU, GSM8K, MATH, MedQA, MedMCQA56.9Math Accuracy15