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.
ERNIE 4.0
๐จ๐ณ Baidu
Fuyu-8B
๐บ๐ธ Adept
PaLI-3
๐บ๐ธ Google DeepMind
Ferret (13B)
๐บ๐ธ Columbia University
InternLM-XComposer
๐จ๐ณ Shanghai AI Lab
GPT-4V
๐บ๐ธ OpenAI
DreamLLM
๐จ๐ณ Xiโan Jiaotong University
360 Smart Brain
๐จ๐ณ 360 Security Technology
Qwen-VL
๐จ๐ณ Qwen
IDEFICS-80B
๐บ๐ธ Hugging Face
IDEFICS-9B
๐บ๐ธ Hugging Face
EXAONE 2.0
๐ฐ๐ท LG AI Research
West Lake (โXฤซhรบ / ่ฅฟๆนๅคงๆจกๅโ)
๐จ๐ณ West Lake Xinchen / Xinchen AI / ่ฅฟๆนๅฟ่พฐ๏ผๆญๅท๏ผ็งๆๆ้ๅ ฌๅธ
Pangu 3.0
๐จ๐ณ Huawei
PaLI-X
๐บ๐ธ Google Research
ONE-PEACE
๐จ๐ณ Alibaba
InstructBLIP
๐บ๐ธ Salesforce Research
ImageBind
๐บ๐ธ Meta AI
Otter
๐จ๐ณ Nanyang Technological University
AiLMe-100B v3
๐จ๐ณ "Qilin Hesheng Network Technology Co.
LLaVA
๐บ๐ธ University of Wisconsin Madison
Yiye Qingzhou
๐จ๐ณ EFFYIC (่ฏๅ ๆบ่ฝ)
GPT-4 (Jun 2023)
๐บ๐ธ OpenAI
GPT-4 (Mar 2023)
๐บ๐ธ OpenAI
Kosmos-1
๐บ๐ธ Microsoft
Flan T5-XXL + BLIP-2
๐บ๐ธ Salesforce Research
Adaptive Agent
๐ฌ๐ง DeepMind
DreamerV3
๐ฌ๐ง DeepMind
DeepNash
๐ฌ๐ง DeepMind
CICERO
๐บ๐ธ Meta AI
AltCLIP_M9
๐จ๐ณ Beijing Academy of Artificial Intelligence / BAAI
Diplodocus
๐บ๐ธ Meta AI
BEIT-3
๐บ๐ธ Microsoft
Unified-IO (XL)
๐บ๐ธ Allen Institute for AI
MetaLM
๐บ๐ธ Microsoft Research
LIMoE-H/14
๐บ๐ธ Google
Gato
๐ฌ๐ง DeepMind
Flamingo
๐ฌ๐ง DeepMind
EXAONE 1.0
๐ฐ๐ท LG
Student of Games
๐ฌ๐ง DeepMind
NรWA
๐บ๐ธ Microsoft Research
EfficientZero
๐จ๐ณ Tsinghua University
M6-10T
๐จ๐ณ Alibaba
Zidong Taichu
๐จ๐ณ Chinese Academy of Sciences
GOAT
๐ฌ๐ง DeepMind
ALIGN
๐บ๐ธ Google Research
Wu Dao 2.0
๐จ๐ณ Beijing Academy of Artificial Intelligence / BAAI
M6-T
๐จ๐ณ Alibaba
Wu Dao - Wen Lan
๐จ๐ณ Beijing Academy of Artificial Intelligence / BAAI
CLIP (ResNet-50)
๐บ๐ธ OpenAI
CLIP (ViT L/14@336px)
๐บ๐ธ OpenAI
Go-explore
๐บ๐ธ Uber AI
Agent57
๐ฌ๐ง DeepMind
Perceiver IO (optical flow)
๐ฌ๐ง DeepMind
OpenAI Five
๐บ๐ธ OpenAI
OpenAI Five Rerun
๐บ๐ธ OpenAI
MuZero
๐ฌ๐ง DeepMind
AlphaStar
๐ฌ๐ง DeepMind
Hide and Seek
๐บ๐ธ OpenAI
Pluribus
๐บ๐ธ Facebook AI Research
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.