ResearchTasksCode Safety EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAPPS 1.0 (test)Self-Rec (No Elicitation)0.988Safety Score30Feb 26, 2026BigCodeBench 1.0 (test)Self-Rec (No Elicitation)99.9Safety Score24Feb 26, 2026