Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
GUI Agent task on DroidTask
Loading...
88.6
Success Rate
AppAgentX
10.288
30.619
50.95
71.281
May 12, 2026
Success Rate
Updated 21d ago
Evaluation Results
Method
Method
Links
Success Rate
AppAgentX
Type=GPT-4o, Input=SoM
2026.05
88.6
GUI-Explorer
Type=GPT-4o, Input=SoM
2026.05
88
EAM
Type=GPT-4o, Qwen2.5-3...
2026.05
86.1
M3A
Type=GPT-4o, Input=SoM
2026.05
72.2
GPT-4o
Type=GPT-4o, Input=SoM
2026.05
57
UI-TARS-7B
Type=UI-TARS-7B, Input...
2026.05
55
AutoDroid-V2
Type=Llama-3-8B-ft, In...
2026.05
54.4
UI-TARS-2B
Type=UI-TARS-2B, Input...
2026.05
34.8
Qwen 2.5-VL-3B
Type=Qwen 2.5-VL-3B, I...
2026.05
13.3
Feedback
Search any
task
Search any
task