ResearchDatasetsUltraMedicalFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMT-BenchUltraMedical Preference6.9MT Score28AlpacaEval 2.0UltraMedical Preference17.7LC28Pairwise Preference RankingUltraMedical0.82Q-Score5Reward ModelingUltraMedical (test)95.8Easy Score5