Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Computer Use on OSWorld (Verified)
Loading...
75
Score
GPT-5.4
5.944
23.872
41.8
59.728
Feb 2, 2026
Feb 19, 2026
Mar 9, 2026
Mar 27, 2026
Apr 13, 2026
May 1, 2026
May 19, 2026
Score
Updated 14d ago
Evaluation Results
Method
Method
Links
Score
GPT-5.4
2026.05
75
Kimi-K2.6
2026.05
73.1
Claude-Sonnet-4.6
2026.05
72.5
Claude Opus 4.5
Evaluation Source=Exte...
2026.02
66.3
Kimi K2.5
Evaluation Source=Exte...
2026.02
63.3
Qwen-3.5-27B
2026.05
56.2
GUI-OWL-1.5-8B
2026.05
52.3
EvoCUA-8B
2026.05
46.1
Qwen-3.5-9B
2026.05
41.8
Qwen3-VL-235B-A22B
Evaluation Source=Exte...
2026.02
38.1
Gemini 3 Pro
Evaluation Source=Inte...
2026.02
20.7
GPT-5.2 (xhigh)
Evaluation Source=Inte...
2026.02
8.6
Feedback
Search any
task
Search any
task