Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

GUI Agent Task on AndroidWorld

80Success Rate

Human

28.93642.19355.4568.707Oct 7, 2024Jan 7, 2025Apr 10, 2025Jul 11, 2025Oct 12, 2025Jan 12, 2026Apr 15, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2025.05
80
2025.12
78
2026.04
77.6
2026.04
74.1
2025.12
73.3
2026.03
73.3
2026.04
73.3
2025.12
68.1
2026.04
67.2
2026.01
66.4
2025.12
66.4
2026.01
65.9
2025.12
65.9
2026.04
65.9
2026.03
64.8
2025.12
64.2
2026.03
64.2
2026.04
63.7
2026.01
62.9
2025.12
62.9
2026.01
62.1
2026.03
62.1
2026.03
61.4
2026.04
60.3
2026.01
59.5
2025.12
59.5
2026.01
56
2026.01
54.3
2026.01
54.3
2026.03
54.3
2026.04
54.3
2026.03
52.5
2026.04
52.5
2026.01
51.7
2026.01
50.4
2026.03
50
2025.05
47.4
2026.01
46.8
2026.01
46.6
2026.01
46.6
2026.01
46.6
2026.04
46.6
2026.01
45.7
2024.12
44.8
2025.05
44.8
2026.01
44.8
2026.04
44.8
2024.10
44
2026.01
44
2026.01
44
2026.02
44
2026.01
42.62
2026.01
42.2
2025.12
41.7
2026.02
41.7
2026.01
41.4
2026.01
41
2026.01
41
2026.02
41
2026.01
40.98
2025.05
40.5
2026.01
40.5
2026.02
40.5
2024.12
39.7
2026.01
39.7
2025.12
39.7
2026.01
38
2026.01
37.9
2025.05
37.1
2026.01
37.1
2026.03
36.6
2026.01
35.3
2026.03
35.3
2025.02
35
2026.01
35
2026.02
35
2026.03
35
2025.02
34.5
2025.05
34.5
2026.01
34.5
2026.02
34.5
2026.01
34.43
2026.01
33.6
2025.12
33
2024.10
32.8
2024.12
32.8
2025.05
32.8
2026.02
32.8
2026.01
32.78
2026.01
31.9
2026.01
31.9
2026.03
31.7
2026.04
31.5
2024.10
31
2024.12
31
2026.01
31
2025.12
31
2026.02
31
2026.04
31
2026.03
30.9
Showing 100 of 136 rows