New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Vision AI models
Browse the complete list of Vision AI models. Compare specifications, benchmark scores and provider pricing on GenAIList.
GLM-4.6V
🇨🇳 Zhipu AI
Ministral 3 14B
🇫🇷 Mistral AI
Ministral 3 3B
🇫🇷 Mistral AI
Ministral 3 8B
🇫🇷 Mistral AI
Mistral Large 3
🇫🇷 Mistral AI
OCR 3
🇫🇷 Mistral AI
ERNIE-4.5-VL-28B-A3B-Thinking
🇨🇳 Baidu
Deepseek OCR
🇨🇳 DeepSeek
PaddleOCR-VL
🇨🇳 Baidu
Gemini Robotics-ER 1.5
🇺🇸 Google DeepMind
Qwen3-VL (series)
🇨🇳 Alibaba
Granite-Docling
🇺🇸 IBM
MultiverSeg
🇺🇸 Massachusetts Institute of Technology (MIT)
Mistral Medium 3.1
🇫🇷 Mistral AI
Command A Vision
🇨🇦 Cohere
Aeneas
🇺🇸 Google DeepMind
EXAONE Path 2.0
🇰🇷 LG AI Research
MedSigLIP
V-JEPA 2
🇺🇸 Facebook AI Research
Skywork-R1V3
🇨🇳 Kunlun Inc.
MiMo-VL-7B-SFT
🇨🇳 Xiaomi Corp
MiMo‑VL‑7B‑RL
🇨🇳 Xiaomi Corp
Seed1.5-VL
🇨🇳 ByteDance
OCR 2
🇫🇷 Mistral AI
Eagle 2.5
🇺🇸 NVIDIA
Midjourney V7
🇺🇸 Midjourney
FASHN v1.5
🇬🇧 FASHN AI
Stable Video 4D 2.0 (SV4D 2.0)
🇺🇸 Stability AI
Aya Vision
🇨🇦 Cohere
SigLIP 2
🇺🇸 Google DeepMind
PaliGemma 2 3B Mix 224
PaliGemma 2 3B Mix 448
Computer-Using Agent (CUA)
🇺🇸 OpenAI
Eagle 2
🇺🇸 NVIDIA
MiniMax-VL-01
🇨🇳 MiniMax
Typhoon2-Vision
🇹🇭 Typhoon / SCB 10X
NVILA 15B
🇺🇸 NVIDIA
NVILA 8B
🇺🇸 NVIDIA
TokenFlow-XL
🇨🇳 ByteDance
SeedEdit
🇨🇳 ByteDance
KwooVa
🇨🇳 Harbin Institute of Technology
YOLOv11
🇬🇧 Huddersfield University
NVLM-D 72B
🇺🇸 NVIDIA
NVLM-H 72B
🇺🇸 NVIDIA
NVLM-X 72B
🇺🇸 NVIDIA
Pixtral 12B
🇫🇷 Mistral AI
YOLOv8 (reCAPTCHA fine-tuned)
🇨🇭 ETH Zurich
Harrison.rad.1
🇦🇺 Harrison.ai
3-ensemble of Self-ensembles on CIFAR-100
🇺🇸 Google DeepMind
MiniCPM-V 2.6
🇨🇳 OpenBMB (Open Lab for Big Model Base)
CXR Foundation
H-optimus-0
Unknown
OmniParser: Icon Description Model
🇺🇸 Microsoft Research
OmniParser: Interactable Region Detection Model
🇺🇸 Microsoft Research
Florence-2-B (base)
🇺🇸 Microsoft
Florence-2-L (large)
🇺🇸 Microsoft
Segment Anything Model 2
🇺🇸 Meta AI
Yi Vision
🇨🇳 01.AI
Stable Video 4D (SV4D)
🇺🇸 Stability AI
OV-DINO
🇨🇳 Guangzhou AI Public Computing Center
About Vision AI models
This page lists every Vision AI models tracked on GenAIList. When choosing a model, weigh raw capability against practical constraints like context window, latency, licensing and price. Open-weights and open-source models can be self-hosted and fine-tuned, while proprietary models often lead on raw quality. Compare benchmark scores on our benchmarks page and put two candidates head to head with compare.
Frequently asked questions
How do I choose the right model?
Weigh raw capability against practical constraints like context window, latency, licensing and price. Use the benchmarks page to compare rankings and the compare tool to evaluate two candidates side by side.
Where can I see benchmark scores?
Visit the benchmarks page to compare these models on standardised tests, then use the compare tool for a detailed side-by-side of any two models.