Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mobile GUI Agent Navigation on MobileWorld
Loading...
58
Success Rate (SR)
Task-State Representation (Kimi-k2.5)
42.4
46.45
50.5
54.55
Jul 1, 2026
Success Rate (SR)
Average Steps
Delta SR
Updated 24d ago
Evaluation Results
Method
Method
Links
Success Rate (SR)
Average Steps
Delta SR
Task-State Representation (Kimi-k2.5)
Base Model=Kimi-k2.5,...
2026.07
58
28.3
9
Task-State Representation (Qwen3.5-plus)
Base Model=Qwen3.5-plu...
2026.07
55
27
12
Kimi-k2.5
Context=Baseline
2026.07
49
29.6
-
Qwen3.5-plus
Context=Baseline
2026.07
43
25.1
-
Feedback
Search any
task
Search any
task