Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Web Navigation on MMInA Shop
Loading...
48.5
Success Rate
Mem-W-8B
0.66
13.08
25.5
37.92
May 10, 2026
Success Rate
Updated 22d ago
Evaluation Results
Method
Method
Links
Success Rate
Mem-W-8B
Backbone=UI-Venus-1.5-8B
2026.05
48.5
Mem-W-4B
Backbone=Qwen3-VL-4B
2026.05
40.5
Qwen3-VL-32B
Model Class=Open-sourc...
2026.05
36
Mem-W-7B
Backbone=UI-TARS-1.5-7B
2026.05
32.5
GLM-4.1V-9B-Thinking
Model Class=Open-sourc...
2026.05
28.5
Qwen3-VL-8B
Model Class=Open-sourc...
2026.05
19.5
Step-GUI-4B
Model Class=Open-sourc...
2026.05
19.5
UI-Venus-1.5-8B
Model Class=Mem-W Models
2026.05
18.5
Qwen2.5-VL-7B
Model Class=Open-sourc...
2026.05
16
UI-Venus-1.5-30B-A3B
Model Class=Open-sourc...
2026.05
13.5
Qwen3-VL-4B
Model Class=Mem-W Models
2026.05
11.5
Qwen3-VL-2B
Model Class=Open-sourc...
2026.05
9.5
UI-TARS-1.5-7B
Model Class=Mem-W Models
2026.05
5.5
GUI-Owl-1.5-8B
Model Class=Open-sourc...
2026.05
5
MAI-UI-2B
Model Class=Open-sourc...
2026.05
2.5
Feedback
Search any
task
Search any
task