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.
Cambrian-1-34B
๐บ๐ธ New York University (NYU)
Cambrian-1-8B
๐บ๐ธ New York University (NYU)
Claude 3.5 Sonnet
๐บ๐ธ Anthropic
Ovis-7B
๐จ๐ณ Alibaba
Megrez-3B-Omni
๐จ๐ณ Infinigence AI
Diamond
๐บ๐ธ University of Geneva
Chameleon-34B
๐บ๐ธ Facebook AI Research
FragLlama: Next-fragment prediction for molecular design
๐บ๐ธ Facebook AI Research
VILA-7B
๐บ๐ธ NVIDIA
VILA1.5-40B
๐บ๐ธ NVIDIA
GPT-4o (May 2024)
๐บ๐ธ OpenAI
Gemini 1.5 Flash (May 2024)
๐บ๐ธ Google DeepMind
Gemini 1.5 Flash 8B
๐บ๐ธ Google DeepMind
Emu2
๐จ๐ณ Beijing Academy of Artificial Intelligence / BAAI
Idefics2
๐บ๐ธ Hugging Face
VILA1.5-13B
๐บ๐ธ NVIDIA
InternVL1.5
๐จ๐ณ Shanghai AI Lab
Insights into Human Harmony (ๆด่งไบบๅ)
๐จ๐ณ "Zhejiang Lianxin Digital Co.
Reka Edge
๐บ๐ธ Reka AI
SIMA
๐บ๐ธ Google DeepMind
Reka Core
๐บ๐ธ Reka AI
Reka Flash
๐บ๐ธ Reka AI
NOMI GPT
๐จ๐ณ NIO
GPT-4 Turbo (Apr 2024)
๐บ๐ธ OpenAI
WeituAI 1.0
๐จ๐ณ Weitu AI
APUS-xDAN-4.0(MoE)
๐จ๐ณ "Qilin Hesheng Network Technology Co.
POKEยดLLMON
๐บ๐ธ Georgia Institute of Technology
Grok-1.5V
๐บ๐ธ xAI
Xinghai (ๆๆตท)
๐จ๐ณ Hisense
MM1-30B
๐บ๐ธ Apple
DeepSeek-VL-1.3B
๐จ๐ณ DeepSeek
DeepSeek-VL-7B
๐จ๐ณ DeepSeek
GroundingGPT
๐จ๐ณ ByteDance
Claude 3 Opus
๐บ๐ธ Anthropic
Claude 3 Sonnet
๐บ๐ธ Anthropic
Ovis2 16B
๐จ๐ณ Alibaba
Ovis2 34B
๐จ๐ณ Alibaba
Distilled Grandmaster
๐ฌ๐ง DeepMind
RecGPT / Xingchen LLM (ๆทๅฎ๏ผไธญๅฝ๏ผ่ฝฏไปถๆ้ๅ ฌๅธ)
๐จ๐ณ Alibaba
Hanhai (็ๆตท)
๐จ๐ณ "Shuchi Information Technology ( Shanghai ) Co.
LLaVA-NeXT-34B (LLaVA-1.6)
๐บ๐ธ University of Wisconsin Madison
Qwen-VL-Max
๐จ๐ณ Qwen
Fuyu-Heavy
๐บ๐ธ Adept
Yiye Qingzhou-0.7B
๐จ๐ณ EFFYIC (่ฏๅ ๆบ่ฝ)
Yiye Qingzhou-45B
๐จ๐ณ EFFYIC (่ฏๅ ๆบ่ฝ)
Gemini Nano-1
๐บ๐ธ Google DeepMind
Gemini Nano-2
๐บ๐ธ Google DeepMind
VILA-13B
๐บ๐ธ NVIDIA
Gemini 1.0 Pro
๐บ๐ธ Google DeepMind
Gemini 1.0 Ultra
๐บ๐ธ Google DeepMind
OneLLM
๐บ๐ธ Chinese University of Hong Kong (CUHK)
OmniFusion-7B (InternViT-6B-448px V1-2)
๐ท๐บ AIRI Artificial Intelligence Research Institute
LLaVA + LVIS-INSTRUCT4V
๐จ๐ณ Fudan University
OmniVec
๐บ๐ธ TensorTour
OtterHD-8B
๐จ๐ณ Nanyang Technological University
CogVLM-17B
๐จ๐ณ Tsinghua University
GPT-4 Turbo (Nov 2023)
๐บ๐ธ OpenAI
LLaVA 1.5
๐บ๐ธ University of Wisconsin Madison
ChatGLM3-6B
๐จ๐ณ Zhipu AI
Xinghan Foundation Model
๐จ๐ณ Dahua Technology
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.