ResearchDatasetsMobile-Eval-RAGFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMobile agent task completionMobile-Eval-RAG79.6Completion Rate9Mobile App Task ExecutionMobile-Eval-RAG Multi-App75.7Completion Rate (CR)5Mobile App Task ExecutionMobile-Eval-RAG Single-App29.2Completion Rate (CR)3