ResearchDatasetsMMLU, GSM8K, HEval, BBH, MedQAMMLU, GSM8K, HEval, BBH, MedQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-domain EvaluationMMLU, GSM8K, HEval, BBH, MedQA68Average Score18