News
EveryLLM

Images in

Reads photos, charts and documents. 117 models on EveryLLM so far.

Models with image input can read photographs, screenshots, charts, diagrams, handwriting and scanned documents, and answer questions about them. An image encoder, often a vision transformer, cuts the picture into small patches and turns each into a vector that the language model treats like a token. Vision is now standard in frontier models and common in open ones.

How vision was added

Early vision-language models joined a pre-trained image encoder to a pre-trained language model. DeepMind's Flamingo (2022) did this with special cross-attention layers, and LLaVA (2023) used a simple projection trained on instruction data written by GPT-4. GPT-4 accepted images from March 2023, a feature that reached ChatGPT users in September 2023. Claude 3 (March 2024), Llama 3.2 (September 2024) and Gemma 3 (March 2025) brought vision to more users.

Uses and limits

Document understanding is the largest practical use: reading invoices, forms, tables and slides, and turning scanned pages into text. Models also describe images for blind and low-vision people, starting with a partnership between OpenAI and the Be My Eyes app in 2023. Weak spots include counting objects, reading small print, precise spatial reasoning and spotting edited photographs, and models can be misled by instructions hidden in images.

Famous images in models

Still to be written: GPT-4o.

Further reading

imgwavvidVideoPoet 馃嚭馃嚫 United StatesVideoPoet A Google Research language model that turns text and images into video and audioMultimodal 路 Research only 路 2023 imgfnGemini Robotics 馃嚭馃嚫 United StatesGemini Robotics A vision-language-action model from Google DeepMind built for robotsMultimodal 路 API only 路 2025 imgWu Dao 馃嚚馃嚦 ChinaWu Dao BAAI's trillion-parameter multimodal model family, announced 2021Multimodal 路 Research only 路 2021 imgLlama 馃嚭馃嚫 United StatesLlama Meta AI's family of open-weight language models, from 1B to 2T parametersGeneral 路 Conditional licence 路 2023 imgChameleon WorldChameleon Early-fusion models that read and write images and text in one streamMultimodal 路 Research only 路 2024 imgKimi k1.5 馃嚚馃嚦 ChinaKimi k1.5 Multimodal LLM trained with reinforcement learning for reasoningReasoning 路 Research only 路 2025 imgBLIP-2 WorldBLIP-2 Efficient vision-language model using frozen encodersMultimodal 路 Research only 路 2023 imgfnUI-TARS 馃嚚馃嚦 ChinaUI-TARS Open-source multimodal agent for GUI tasksMultimodal 路 Open weights 路 2025 imgMM1 WorldMM1 A family of multimodal language models up to 30B parameters, dense and MoE.Multimodal 路 Research only 路 2024 imgPaLM-E WorldPaLM-E An embodied multimodal language model that grounds words in robot sensor inputMultimodal 路 Research only 路 2023 imgwavvidGemini 1.5 Pro 馃嚭馃嚫 United StatesGemini 1.5 Pro Google DeepMind's mid-size multimodal model with up to a 1 million token context windowGeneral 路 API only 路 2024 imgwavvidGemma 3n 馃嚭馃嚫 United StatesGemma 3n Mobile-first open model family for on-device text, image and audio workMultimodal 路 Open weights 路 2025 imgvidFlamingo 馃嚞馃嚙 United KingdomFlamingo A visual language model family that learns new image and video tasks from a few examples.Multimodal 路 Research only 路 2022

The weekly digest

Every Monday: the model of the day, new pages on EveryLLM, and the conferences and anniversaries of the week ahead.