Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-Image Understanding on MMIU 106 (test)
Loading...
72.1
Score
Gemini 3 Pro
25.612
37.681
49.75
61.819
Jan 15, 2026
Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Score
Gemini 3 Pro
Model Category=API cal...
2026.01
72.1
GPT-5
Model Category=API cal...
2026.01
71
Gemini 2.5 Pro
Model Category=API cal...
2026.01
68.9
GPT-5 mini
Model Category=API cal...
2026.01
64.5
GLM-4.1V-9B
Model Category=Open we...
2026.01
62.4
Gemini 2.5 Flash
Model Category=API cal...
2026.01
61.2
Molmo2-4B
Model Category=Molmo2...
2026.01
55.5
Molmo2-8B
Model Category=Molmo2...
2026.01
54.2
Claude Sonnet 4.5
Model Category=API cal...
2026.01
54.1
Molmo2-O-7B
Model Category=Molmo2...
2026.01
51.7
Keye-VL-1.5-8B
Model Category=Open we...
2026.01
50.3
InternVL3.5-8B
Model Category=Open we...
2026.01
49.4
InternVL3.5-4B
Model Category=Open we...
2026.01
49.2
Eagle2.5-8B
Model Category=Open we...
2026.01
48.4
MiniCPM-V-4.5-8B
Model Category=Open we...
2026.01
46.5
Qwen3-VL-4B
Model Category=Open we...
2026.01
43.2
PLM-3B
Model Category=Open mo...
2026.01
40.6
Qwen3-VL-8B
Model Category=Open we...
2026.01
35.3
PLM-8B
Model Category=Open mo...
2026.01
27.4
Feedback
Search any
task
Search any
task