ResearchTasksHousehold ManipulationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedALFWorld (Seen)SkillReranker84.65Average Reward12Jul 8, 2026Mobile UMI Household TasksMobile UMI70Success Rate7May 21, 2026