ResearchTasksCode Reasoning (Output Prediction)FollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCruxEval-OCodeEnhance+CodeQA36.4CX-O Score10Jun 11, 2026CRUXEval-O 1-shotERNIE 5.0-Base84.01Accuracy3Feb 26, 2026