ResearchDatasetsMMLU, GSM8K, MultiArith, SVAMP, AQuA, HumanEvalFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCross-domain LLM EvaluationMMLU, GSM8K, MultiArith, SVAMP, AQuA, HumanEval90.32Average Score21