// MODEL CATEGORY

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.

271 models
JS

KataGo

🇺🇸 Jane Street

Feb 2019 2.5M
Multimodal Open (Restricted)
DE

Hanabi 4 player

🇬🇧 DeepMind

Feb 2019 764K
Multimodal Proprietary
DE

FTW (For The Win)

🇬🇧 DeepMind

Jul 2018 126M
Multimodal Proprietary
DE

IMPALA

🇬🇧 DeepMind

Feb 2018 1.6M
Multimodal Proprietary
DE

AlphaZero

🇬🇧 DeepMind

Dec 2017
Multimodal Proprietary
DE

AlphaGo Master

🇬🇧 DeepMind

Oct 2017
Multimodal Proprietary
DE

AlphaGo Zero

🇬🇧 DeepMind

Oct 2017 46.4M
Multimodal Proprietary
DE

Rainbow DQN

🇬🇧 DeepMind

Oct 2017
Multimodal Proprietary
CM

Libratus

🇺🇸 Carnegie Mellon University (CMU)

Aug 2017
Multimodal Proprietary
OpenAI

OpenAI TI7 DOTA 1v1

🇺🇸 OpenAI

Aug 2017
Multimodal Proprietary
DE

NoisyNet-Dueling

🇬🇧 DeepMind

Jun 2017
Multimodal Proprietary
MA

HRA

🇺🇸 Maluuba

Jun 2017
Multimodal Proprietary
UO

DeepStack

🇺🇸 University of Alberta

Jan 2017 2.5M
Multimodal Proprietary
Google DeepMind

Dueling DQN

🇺🇸 Google DeepMind

Apr 2016 1.7M
Multimodal Proprietary
Google DeepMind

Double DQN

🇺🇸 Google DeepMind

Mar 2016 1.5M
Multimodal Proprietary
GO

A3C FF hs

🇺🇸 Google

Feb 2016
Multimodal Proprietary
DE

AlphaGo Lee

🇬🇧 DeepMind

Jan 2016
Multimodal Proprietary
Google DeepMind

Advantage Learning

🇺🇸 Google DeepMind

Dec 2015
Multimodal Proprietary
DE

AlphaGo Fan

🇬🇧 DeepMind

Oct 2015 8.2M
Multimodal Proprietary
UO

TRPO

🇺🇸 University of California (UC) Berkeley

Feb 2015 33.5K
Multimodal Proprietary
UO

SC-NLM

🇺🇸 University of Toronto

Nov 2014
Multimodal Proprietary
UC

SmooCT

🇨🇳 University College London (UCL)

Jul 2014
Multimodal Proprietary
DE

DQN

🇬🇧 DeepMind

Dec 2013 836.1K
Multimodal Proprietary
IN

Crazy Stone

🇺🇸 INRIA

May 2006
Multimodal Proprietary
IB

Deep Blue

🇺🇸 IBM

May 1997 8K
Multimodal Proprietary
AI

NeuroChess

Unknown

Dec 1994 72.3K
Multimodal Proprietary
IB

TD-Gammon

🇺🇸 IBM

May 1992 25K
Multimodal Proprietary
UO

Boxes (pole)

🇺🇸 University of Edinburgh

Jul 1968
Multimodal Proprietary
UO

GLEE

🇺🇸 University of Edinburgh

Jul 1968
Multimodal Proprietary
UO

MENACE

🇺🇸 University of Edinburgh

Nov 1963
Multimodal Proprietary
IB

Samuel Neural Checkers

🇺🇸 IBM

Jul 1959 16
Multimodal Proprietary

About Multimodal AI models

Multimodal AI models — often called vision-language models (VLMs) — 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.