Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual perception and grounding on InfoVQA
Loading...
88.3
Accuracy
Llava-OV
73.74
77.52
81.3
85.08
May 13, 2026
Accuracy
Updated 19d ago
Evaluation Results
Method
Method
Links
Accuracy
Llava-OV
Size=7B
2026.05
88.3
DeepEyes
Size=7B
2026.05
87.7
MoCA
Size=7B
2026.05
87
Pixel Reasoner
Size=7B
2026.05
86.4
Qwen2.5-VL-Instruct
Size=72B
2026.05
84.3
GPT-4o-mini
Size=-
2026.05
83.3
GPT-4o
Size=-
2026.05
80.7
Qwen2.5-VL-Instruct
Size=7B
2026.05
80.7
VL-Rethinker
Size=7B
2026.05
79.5
R1-VL
Size=7B
2026.05
78
mPLUG-Owl3
Size=7B
2026.05
76.3
Docopilot
Size=8B
2026.05
75
Claude-3.5
Size=-
2026.05
74.3
Feedback
Search any
task
Search any
task