ResearchTasksMove to AimFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedPhysical Simulator Out-of-Domain evaluationRL w. World Model82.1Success Rate6Feb 26, 2026Physical Simulator In-Domain evaluationRL w. World Model94.6Success Rate6Feb 26, 2026