ResearchDatasetsMMLU, CMMLU, GSM8k, XSum, and StrategyQAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsReasoning and Generative TasksMMLU, CMMLU, GSM8k, XSum, and StrategyQA (test)30.77MMLU Accuracy4Reasoning and Generative TasksMMLU, CMMLU, GSM8k, XSum, and StrategyQA—MMLU0