Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-image Understanding on MMIU (test)
Loading...
52.6
Accuracy
Qwen2VL-7B
12.04
22.57
33.1
43.63
Jan 12, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2VL-7B
2026.01
52.6
attention-masking strategy
backbone=LLaVA-OV-7B,...
2026.01
45.5
LLaVA-OV-7B
2026.01
45
InternVL2-Llama3-76B
2026.01
44.2
Qwen2VL-2B
2026.01
38.7
procedural data-generation strategy
backbone=LLaVA-OV-0.5B...
2026.01
37.2
InternVL2-8B
2026.01
36.8
attention-masking strategy
backbone=LLaVA-OV-0.5B...
2026.01
36.3
LLaVA-OV-0.5B
2026.01
34.2
LLaVA-v1.5-7B
2026.01
19.2
InternVL2-2B
2026.01
13.6
Feedback
Search any
task
Search any
task