Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Perception on MME-RW
Loading...
68.6
Accuracy
GPT-5
52.272
56.511
60.75
64.989
Jun 29, 2026
Accuracy
Updated 25d ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-5
Model Category=Closed-...
2026.06
68.6
TACO (Ours-7B)
Model Category=Code-to...
2026.06
66.2
Mini-o3-7B
Model Category=Code-to...
2026.06
65.5
DeepEyes-v2-7B
Model Category=Code-to...
2026.06
64.9
Thyme-7B
Model Category=Code-to...
2026.06
64.8
CodeV-RL-7B
Model Category=Code-to...
2026.06
64.5
Pixel-Reasoner-7B
Model Category=Code-to...
2026.06
64.4
DeepEyes-7B
Model Category=Code-to...
2026.06
64.1
GPT-4o
Model Category=Closed-...
2026.06
62.8
InternVL3-8B
Model Category=Open-so...
2026.06
61.3
Qwen2.5-VL-32B
Model Category=Open-so...
2026.06
61
Qwen3-VL-8B
Model Category=Open-so...
2026.06
60.3
PyVision-RL-7B
Model Category=Code-to...
2026.06
59.6
Gemini-2.5-Pro
Model Category=Closed-...
2026.06
58.3
Qwen2.5-VL-7B
Model Category=Open-so...
2026.06
58.3
LLaVA-OneVision-7B
Model Category=Open-so...
2026.06
57.4
MathCoder-VL-8B
Model Category=Code-to...
2026.06
52.9
Feedback
Search any
task
Search any
task