Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Reasoning on MVision
Loading...
61.5
Accuracy
GPT-5
15.844
27.697
39.55
51.403
Jun 29, 2026
Accuracy
Updated 25d ago
Evaluation Results
Method
Method
Links
Accuracy
GPT-5
Model Category=Closed-...
2026.06
61.5
Qwen3-VL-8B
Model Category=Open-so...
2026.06
53.9
Gemini-2.5-Pro
Model Category=Closed-...
2026.06
39.8
GPT-4o
Model Category=Closed-...
2026.06
36.5
TACO (Ours-7B)
Model Category=Code-to...
2026.06
35.8
Qwen2.5-VL-32B
Model Category=Open-so...
2026.06
35.2
CodeV-RL-7B
Model Category=Code-to...
2026.06
33.6
DeepEyes-v2-7B
Model Category=Code-to...
2026.06
28.9
PyVision-RL-7B
Model Category=Code-to...
2026.06
28.7
Thyme-7B
Model Category=Code-to...
2026.06
27.6
Qwen2.5-VL-7B
Model Category=Open-so...
2026.06
27
DeepEyes-7B
Model Category=Code-to...
2026.06
26.6
InternVL3-8B
Model Category=Open-so...
2026.06
26.3
Pixel-Reasoner-7B
Model Category=Code-to...
2026.06
26.3
MathCoder-VL-8B
Model Category=Code-to...
2026.06
26.1
Mini-o3-7B
Model Category=Code-to...
2026.06
25.7
LLaVA-OneVision-7B
Model Category=Open-so...
2026.06
17.6
Feedback
Search any
task
Search any
task