ResearchTasksGUI planning semantic consistencyFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGUIGuard-Bench Overall 1.0 (Mixed)UI-Tars-1.5-7B1.16Black Mask Score7Feb 26, 2026GUIGuard-Bench PC 1.0GPT-5.2328PC Avg.7Feb 26, 2026GUIGuard-Bench Android 1.0Gemini-3-Pro3.45Android Avg.7Feb 26, 2026