Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
GUI Task Execution on SPA-Bench single-app English Level 3
Loading...
53.7
Task Success Rate
GUI-explorer
-2.148
12.351
26.85
41.349
May 22, 2025
Task Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Task Success Rate
GUI-explorer
Input=SOM, Base Model=...
2025.05
53.7
M3A
Input=SOM, Base Model=...
2025.05
42
MobileAgentV2
Input=SoM, Base Model=...
2025.05
20
AppAgent
Input=SOM, Base Model=...
2025.05
14
AutoDroid
Input=a11y tree, Base...
2025.05
12
SeeAct
Input=SOM, Base Model=...
2025.05
12
CogAgent
Input=screen, Base Mod...
2025.05
0
DigiRL
Input=screen, Base Mod...
2025.05
0
Feedback
Search any
task
Search any
task