ResearchDatasetsMMLU, GSM8K, HEval, IFEval, MTBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGeneral Language CapabilityMMLU, GSM8K, HEval, IFEval, MTBench76.4MMLU Accuracy16