Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-image Understanding on MIRB (test)
Loading...
60.8
Accuracy
Qwen2VL-7B
23.568
33.234
42.9
52.566
Jan 12, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2VL-7B
2026.01
60.8
InternVL2-Llama3-76B
2026.01
58.2
GPT-4V
2026.01
53.1
attention-masking strategy
backbone=LLaVA-OV-7B,...
2026.01
51
InternVL2-8B
2026.01
48.6
LLaVA-OV-7B
2026.01
47.2
Qwen2VL-2B
2026.01
45.9
procedural data-generation strategy
backbone=LLaVA-OV-0.5B...
2026.01
32.8
LLaVA-OV-0.5B
2026.01
31.8
LLaVA-v1.5-7B
2026.01
28.5
attention-masking strategy
backbone=LLaVA-OV-0.5B...
2026.01
28.5
InternVL2-2B
2026.01
25
Feedback
Search any
task
Search any
task