ResearchDatasetsGSM8K, MATH, HumanEval, MBPPGSM8K, MATH, HumanEval, MBPPFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral Reasoning and GenerationGSM8K, MATH500, HumanEval, MBPP51.34Mean Accuracy5