ResearchDatasetsHumanEval, MBPP, and BigCodeBenchHumanEval, MBPP, and BigCodeBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsCode GenerationHumanEval+, MBPP+, and BigCodeBench Aggregate70.72Average Score12