New: connect Claude & other AIs to GenAIList over MCP โ research the catalog and contribute to the shared knowledge base. Learn how โ
Multimodal AI models
Explore multimodal AI models that understand images, text, audio and video together. Compare vision-language models (VLMs) by multimodal benchmark scores and capabilities.
Mistral OCR 4
๐ซ๐ท Mistral AI
Hy-Embodied-0.5-VLA
๐จ๐ณ Tencent Hunyuan
Claude Fable 5
๐บ๐ธ Anthropic
Claude Mythos 5
๐บ๐ธ Anthropic
Apple Foundation Models 3
๐บ๐ธ Apple
ChatMinerva
๐ฎ๐น Sapienza NLP
Gemma 4 12B
๐บ๐ธ Google DeepMind
NVIDIA Nemotron 3.5 Content Safety
๐บ๐ธ NVIDIA
MiniMax M3
๐จ๐ณ MiniMax
NVIDIA Cosmos 3
๐บ๐ธ NVIDIA
Qwen3.7-Plus
๐จ๐ณ Qwen
Qwen-VLA
๐จ๐ณ Qwen
Step 3.7 Flash
๐จ๐ณ StepFun
CubePart
๐บ๐ธ Roblox
Rodin Gen-2.5
Deemos
Command A+
๐จ๐ฆ Cohere
Gemini 3.5 Flash
๐บ๐ธ Google DeepMind
OlmoEarth v1.1
๐บ๐ธ Allen Institute for AI
Intern-S2-Preview
๐จ๐ณ Shanghai AI Laboratory
Falcon Perception
๐ฆ๐ช Technology Innovation Institute
Falcon-OCR
๐ฆ๐ช Technology Innovation Institute
MolmoAct 2
๐บ๐ธ Allen Institute for AI
Grok 4.3
๐บ๐ธ xAI
Mistral Medium 3.5
๐ซ๐ท Mistral AI
SenseNova U1
๐จ๐ณ SenseTime
NVIDIA Nemotron 3 Nano Omni
๐บ๐ธ NVIDIA
Qwen3-Omni-Flash (2025-12-01)
๐จ๐ณ Alibaba
Amazon Nova 2 Omni (Preview)
๐บ๐ธ Amazon
Gemini 3 Pro
๐บ๐ธ Google DeepMind
GPT-5.1
๐บ๐ธ OpenAI
GPT-5 Pro
๐บ๐ธ OpenAI
Qwen3-Omni-30B-A3B
๐จ๐ณ Qwen
Qwen3-Omni-Flash
๐จ๐ณ Qwen
Qwen3-Omni
๐จ๐ณ Alibaba
Gemma-SEA-LION-v4-27B-IT
๐ธ๐ฌ AI Singapore
GLM-4.1V-Thinking
๐จ๐ณ Zhipu AI
GLM-4.5V
๐จ๐ณ Zhipu AI
Ovis2.5 2B
๐จ๐ณ Alibaba
Ovis2.5 9B
๐จ๐ณ Alibaba
GPT-5
๐บ๐ธ OpenAI
GPT-5 mini
๐บ๐ธ OpenAI
GPT-5 nano
๐บ๐ธ OpenAI
Genie 3
๐บ๐ธ Google DeepMind
ANITA-NEXT 24B Vision
๐ฎ๐น University of Bari
ERNIE-4.5-VL-28B-A3B
๐จ๐ณ Baidu
BlueOcean LLM 2.0 (่ค็ณ่ๆตท)
๐จ๐ณ "Hangzhou EZVIZ Software Co.
Kimi-VL
๐จ๐ณ Moonshot
Seed 1.6
๐จ๐ณ ByteDance
Seed-1.6-Thinking
๐จ๐ณ ByteDance
OpenOmni
๐จ๐ณ Chinese Academy of Sciences
Cosmos-Reason1 56B
๐บ๐ธ NVIDIA
Cosmos-Reason1 7B
๐บ๐ธ NVIDIA
Mistral Medium 3
๐ซ๐ท Mistral AI
Amazon Nova Premier
๐บ๐ธ Amazon
o4-mini
๐บ๐ธ OpenAI
GPT-4.1
๐บ๐ธ OpenAI
GPT-4.1 mini
๐บ๐ธ OpenAI
GPT-4.1 nano
๐บ๐ธ OpenAI
SenseNova V6
๐จ๐ณ SenseTime
Llama 4 Behemoth (preview)
๐บ๐ธ Meta AI
About Multimodal AI models
Multimodal AI models โ often called vision-language models (VLMs) โ understand more than text: they reason over images, documents, charts, audio and sometimes video alongside language. The best multimodal model depends on your inputs: document understanding rewards strong OCR and layout reasoning, while visual question answering rewards fine-grained image understanding. When comparing VLMs, look at multimodal benchmark scores, supported input types, resolution limits and context window, then weigh quality against cost and latency. Browse the list below to compare multimodal models by provider and availability, check rankings on our benchmarks page, and use compare to put two vision-language models side by side.
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.