ResearchTasksCritique Quality EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHuman Evaluation OverallRCO66Win Rate6Feb 26, 2026CodeRCO67.5Win Rate6Feb 26, 2026MathRCO57.5Win Rate6Feb 26, 2026QARCO75Win Rate6Feb 26, 2026SummarizationRCO75Win Rate6Feb 26, 2026DialogRCO80Win Rate6Feb 26, 2026