ResearchDatasetsMMLU, GSM8K, MultiArith, SVAMP, AQuA, HumanEvalMMLU, GSM8K, MultiArith, SVAMP, AQuA, HumanEvalFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsCross-domain LLM EvaluationMMLU, GSM8K, MultiArith, SVAMP, AQuA, HumanEval90.32Average Score21