Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mobile Task Execution on OS-Kairos real-world Android devices (test)
Loading...
93.09
RE Rate
Mobile-Aptus
56.2636
65.8243
75.385
84.9457
May 27, 2026
RE Rate
TSR Rate
AIF
Updated 6d ago
Evaluation Results
Method
Method
Links
RE Rate
TSR Rate
AIF
Mobile-Aptus
Execution Steps=246
2026.05
93.09
62
0.64
OS-Kairos
Execution Steps=265
2026.05
86.42
70
0.96
GPT-4o
Execution Steps=302
2026.05
75.83
36
-
OS-Atlas-Pro-7B
Execution Steps=359
2026.05
63.79
26
-
Qwen2-VL-7B
Execution Steps=397
2026.05
57.68
4
-
Feedback
Search any
task
Search any
task