ResearchTasksImageNavFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGOAT-Bench seen (val)RL Skill Chain42.2Success Rate (SR)4Jun 15, 2026FloVerse-1.6K (test)ThreeDiff28.9Success Rate (SR)3Jun 15, 2026