Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
GUI Agent Task Completion on DataScope V2
Loading...
6.2
Success Rate (SR)
GPT-5.2+ UIIns
-0.248
1.426
3.1
4.774
Jun 30, 2026
Success Rate (SR)
Progress Score (Sprog)
Scope Score (Sscope)
Updated 25d ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Progress Score (Sprog)
Scope Score (Sscope)
GPT-5.2+ UIIns
Params=–
2026.06
6.2
16.1
21.3
ATMem-UI
Params=8B
2026.06
6.2
9.4
9.8
MAI-UI
Params=8B
2026.06
3.1
4.2
3.9
GELab-Zero
Params=4B
2026.06
0
3.6
6.4
UI-TARS-1.5
Params=7B
2026.06
0
1.6
1.8
GUI-Owl
Params=7B
2026.06
0
1.6
1.1
UI-Venus
Params=7B
2026.06
0
1.6
0.6
GUI-Owl-1.5
Params=8B
2026.06
0
2.6
7.4
GUI-Owl
Params=32B
2026.06
0
1.6
1.1
UI-Venus-1.5-A3B
Params=30B
2026.06
0
1.6
1.8
Feedback
Search any
task
Search any
task