ResearchTasksCode Correctness PredictionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMultiPL-E JavaMin. Prob.0.705AUROC60May 28, 2026MultiPL-E JavaCodeBLEU0.231Brier Score60May 28, 2026LiveCodeBench PythonFunc. Equiv.86.7AUROC60May 28, 2026MultiPL-E JavaMin. Tok. Neg.0.075ECE60May 28, 2026LiveCodeBench PythonVerb. Conf.0.067Brier Score60May 28, 2026