ResearchDatasetsVicuna BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsLLM-as-a-judge evaluationVicuna Bench0.605Pearson Correlation (r)16Feedback Evaluation AlignmentVicuna Bench0.423Kendall's Tau6Feedback evaluationVicuna Bench (test)0.468Kendall's Tau5