Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Perception on MMStar
Loading...
68.8
Score
Claude-3.7-Sonnet
49.04
54.17
59.3
64.43
Mar 4, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Claude-3.7-Sonnet
Model Category=Closed-...
2026.03
68.8
MM-Eureka-7B
Model Category=Multimo...
2026.03
65.2
GPT-4o
Model Category=Closed-...
2026.03
65.1
ThinkLite-VL
Model Category=Multimo...
2026.03
65
Vision-R1
Model Category=Multimo...
2026.03
64.8
VLAA-Thinker-7B
Model Category=Multimo...
2026.03
64.2
Vision-SR1
Model Category=Multimo...
2026.03
64.1
AVAR-Thinker
Model Category=Our model
2026.03
64.1
InternVL2.5-8B
Model Category=Open-So...
2026.03
63.2
Qwen2.5-VL-7B
Model Category=Open-So...
2026.03
62.1
LLaVA-OneVision-7B
Model Category=Open-So...
2026.03
61.7
Mulberry-7B
Model Category=Multimo...
2026.03
61.3
OpenVLThinker
Model Category=Multimo...
2026.03
59.5
R1-OneVision
Model Category=Multimo...
2026.03
52.2
Llama-3.2-11B-Vision-Instruct
Model Category=Open-So...
2026.03
49.8
Feedback
Search any
task
Search any
task