Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Unseen UI Generalization on OSExpert Eval
Loading...
25
Tableau Success Rate
OSExpert (Explore w/ Qwen-3-VL-8B)
-1
5.75
12.5
19.25
Mar 9, 2026
Tableau Success Rate
MiniWord Success Rate
Updated 4mo ago
Evaluation Results
Method
Method
Links
Tableau Success Rate
MiniWord Success Rate
OSExpert (Explore w/ Qwen-3-VL-8B)
Agent Type=Agentic Fra...
2026.03
25
37
OSExpert (Explore w/ GPT-5 & UI-TARS)
Agent Type=Agentic Fra...
2026.03
25
37
OSExpert (Explore w/ Qwen-3-VL-8B, wo/ Fine Skills)
Agent Type=Agentic Fra...
2026.03
23
30
CoAct-1
Agent Type=Agentic Fra...
2026.03
5
6
Agent-S3 w/ GPT-5
Agent Type=Agentic Fra...
2026.03
3
2
OpenCUA-7B
Agent Type=Specialized...
2026.03
2
0
Computer-Use-Preview
Agent Type=Specialized...
2026.03
0
0
Qwen-3-VL-8B
Agent Type=General Model
2026.03
0
0
Feedback
Search any
task
Search any
task