ResearchTasksMobile Agent EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAndroidControl Low (test)Qwen2.5-VL-72B93.7Task Success Rate22Mar 16, 2026GUI-Odyssey (test)Aria-UIIH87.02Grounding8Feb 26, 2026AndroidControl High (test)Aria-UITH43.16Grounding8Feb 26, 2026