ResearchDatasetsPairwise Preference ComparisonsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsPairwise Preference ComparisonPairwise Preference Comparisons 1.5B Scale (test)0.834Avg Preference Score30
Pairwise Preference ComparisonPairwise Preference Comparisons 1.5B Scale (test)0.834Avg Preference Score30