Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
WebQA on WebMMU
Loading...
91.06
Agentic Action Success Rate
Qwen 2.5 VL 72B
53.0064
62.8857
72.765
82.6443
Jan 26, 2026
Agentic Action Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Agentic Action Success Rate
Qwen 2.5 VL 72B
Model Category=Open-So...
2026.01
91.06
GPT 5 + Tools
Model Category=Tool-Pl...
2026.01
88.82
Qwen 2.5 VL 32B
Model Category=Open-So...
2026.01
85.98
Claude 4 sonnet
Model Category=Closed-...
2026.01
83.54
GPT 5
Model Category=Closed-...
2026.01
80.49
Qwen 2.5 VL 72B + Tools
Model Category=Tool-Pl...
2026.01
76.83
DeepEyes
Model Category=Tool-Pl...
2026.01
72.76
AdaReasoner 7B
Model Category=Tool-Pl...
2026.01
72.15
InternVL3 78B
Model Category=Open-So...
2026.01
71.34
Qwen 2.5 VL 7B + Tools
Model Category=Tool-Pl...
2026.01
69.51
PixelReasoner
Model Category=Tool-Pl...
2026.01
69.51
Qwen 2.5 VL 7B
Model Category=Open-So...
2026.01
67.48
Gemini 2.5 flash
Model Category=Closed-...
2026.01
66.26
Qwen 2.5 VL 3B
Model Category=Open-So...
2026.01
54.47
Feedback
Search any
task
Search any
task