GUI Agent
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
62Accuracy
70
Feb 26, 2026
69.4SR
20
Feb 26, 2026
51.84Success Rate
16
May 19, 2026
72.9SR
16
Feb 26, 2026
93.5Success Rate
16
Feb 26, 2026
88.8TP
11
Feb 26, 2026
-0.38Avg Z-Score
7
Feb 26, 2026
90.74Type Accuracy
7
Feb 26, 2026
85.25Type
7
Feb 26, 2026