ResearchDatasetsDyCoBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsPairwise Preference PredictionDyCoBench-1K Overall Preference78.3Preference Rate (A > B)17Pairwise Preference PredictionDyCoBench-1K Multiple Criteria65.6Preference Rate (A > B)17Pairwise Preference PredictionDyCoBench-1K Single Criterion70.2P(A > B)17