ResearchDatasetsEDUFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsPreference AlignmentEDU39.1Human Win Rate8Question AnsweringEdu75.22Avg@87Worst-slab coverage (WSC)EDU80WSC Coverage6Node RegressionEDU (test)93.7Marginal Coverage6