ResearchDatasetsMMLU, GSM8K, HEval, IFEval, MTBenchMMLU, GSM8K, HEval, IFEval, MTBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral Language CapabilityMMLU, GSM8K, HEval, IFEval, MTBench76.4MMLU Accuracy16