ResearchDatasetsLangRFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSkill EvaluationLangR0.866Object Perception (Grounding) Accuracy13Embodied Instruction FollowingLangR71Average Success Rate6Language ReasoningLangR unseen tasks (test)60.8Pass@13PlanningLangR51Success Rate2