ResearchDatasetsCWEvalFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSecure Code GenerationCWEval48.2pass@129Secure Code GenerationCWEval92.27Functionality22Vulnerability injectionCWEval Python66.67Attack Success Rate (ASR)14