ResearchDatasetsReal-phone Human EvaluationFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAgentic Phone Use150-task Real-phone Human Evaluation Single-App62Task Success Rate14Agentic Phone Use150-task Real-phone Human Evaluation Cross-App48Task Success Rate7