Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
GUI Agent Planning on GUIAct-Web 2024a (test)
Loading...
50.5
Step Success Rate
GPT-4o + GoClick-L (Intent)
15.452
24.551
33.65
42.749
Apr 27, 2026
Step Success Rate
Click Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Step Success Rate
Click Accuracy
GPT-4o + GoClick-L (Intent)
Planner=GPT-4o, Ground...
2026.04
50.5
62
GPT-4o + GoClick-L (Func)
Planner=GPT-4o, Ground...
2026.04
47.8
57.2
GPT-4o + SoM
Planner=GPT-4o + SoM,...
2026.04
42.3
55.6
Gemini-2-Flash-Exp + GoClick-L (Intent)
Planner=Gemini-2-Flash...
2026.04
41.7
51.6
Gemini-2-Flash-Exp + GoClick-L (Func)
Planner=Gemini-2-Flash...
2026.04
39.9
48.5
Gemini-2-Flash-Exp + SoM
Planner=Gemini-2-Flash...
2026.04
32.9
44.7
GPT-4o
Planner=GPT-4o, Ground...
2026.04
18.2
5.1
Gemini-2-Flash-Exp
Planner=Gemini-2-Flash...
2026.04
16.8
8
Feedback
Search any
task
Search any
task