ResearchTasksRO reformulationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedRandomAutoREM96.9Accuracy6May 13, 2026Large Out-of-DistributionAutoREM85.4Accuracy6May 13, 2026Hard (Out-of-Distribution)AutoREM94.8Accuracy6May 13, 2026Random In-DistributionAutoREM97.4Accuracy6May 13, 2026