Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Native Windows operating system task execution on WindowsAgentArena (WAA)
Loading...
9.5
AUV
Qwen3-VL-235B-A22B-Instruct
-0.38
2.185
4.75
7.315
Feb 2, 2026
AUV
LR
Updated 4d ago
Evaluation Results
Method
Method
Links
AUV
LR
Qwen3-VL-235B-A22B-Instruct
Active Parameters=22B,...
2026.02
9.5
19.1
InternVL3.5-30B-A3B
Active Parameters=3B,...
2026.02
6.7
4.4
Qwen2.5-VL-72B-Instruct
Parameters=72B, Type=I...
2026.02
6
8.1
Claude3.7-Sonnet-20250219
Proprietary=true
2026.02
0
21.6
Feedback
Search any
task
Search any
task