News
ResearchOpenAI pens AI safety agreement with four firmsReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierOpenAI鈥檚 New Hacking Model Found Dozens Of Holes In Apple TechFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIResearchOpenAI pens AI safety agreement with four firmsReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierOpenAI鈥檚 New Hacking Model Found Dozens Of Holes In Apple TechFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAI
EveryLLM

Images in

Reads photos, charts and documents. 118 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

imgPhi 馃嚭馃嚫 United StatesPhi Microsoft's small open-weights language models that run on a single deviceSmall 路 Open weights 路 2023 imgwavvidQwen 馃嚚馃嚦 ChinaQwen A family of large and small language models developed by Alibaba Cloud.General 路 Open weights 路 2023 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 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 imgHuawei PanGu 馃嚚馃嚦 ChinaHuawei PanGu Huawei's multimodal large model family for industry, from 1B to trillion-scaleMultimodal 路 Open weights 路 2023 imgfnMuse 馃嚭馃嚫 United StatesMuse Meta's multimodal LLM family, successor to Llama, with open and closed variantsGeneral 路 API only 路 2026 imgwavvidGemini 馃嚭馃嚫 United StatesGemini Google DeepMind's multimodal LLM family, from Nano to UltraGeneral 路 API only 路 2023 imgGPT-4.1 馃嚭馃嚫 United StatesGPT-4.1 Multimodal large language model released by OpenAI in April 2025.General 路 API only 路 2025 imgwavfnGato 馃嚞馃嚙 United KingdomGato A single DeepMind network handling dialogue, games and robot controlGeneral 路 2022 imgwavKimi 馃嚚馃嚦 ChinaKimi A Chinese chatbot and large language model family by Moonshot AI.Assistant 路 API only 路 2023 imgwavvidGemma 馃嚭馃嚫 United StatesGemma Google DeepMind's open family of Gemini-derived language modelsGeneral 路 Open weights 路 2024 imgfnGPT-5.3-Codex 馃嚭馃嚫 United StatesGPT-5.3-Codex OpenAI's code-focused large language model with repository and terminal accessCode 路 API only 路 2026 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 imgfnApple Intelligence 馃嚭馃嚫 United StatesApple Intelligence Apple's on-device and cloud AI features built into iOS, iPadOS and macOSGeneral 路 API only 路 2024 imgfnGPT-5 馃嚭馃嚫 United StatesGPT-5 Multimodal large language model released by OpenAI in August 2025.Multimodal 路 API only 路 2025 imgwavGPT-4 馃嚭馃嚫 United StatesGPT-4 Multimodal large language model by OpenAIGeneral 路 API only 路 2023 imgOpenAI o4-mini 馃嚭馃嚫 United StatesOpenAI o4-mini Multimodal reasoning model by OpenAI, now retired.Reasoning 路 API only 路 2025 imgDALL-E 馃嚭馃嚫 United StatesDALL-E Text-to-image model series by OpenAIMultimodal 路 API only 路 2021 imgMistral Medium 3 馃嚝馃嚪 FranceMistral Medium 3 A mid-size language model aimed at enterprise coding and multimodal workGeneral 路 API only 路 2025 imgfnGLM-4 馃嚚馃嚦 ChinaGLM-4 Multilingual large language model series by Zhipu AIGeneral 路 Open weights 路 2024 imgMistral Medium 3.5 馃嚝馃嚪 FranceMistral Medium 3.5 A 128B multimodal model with a 256k window for chat, reasoning and codingGeneral 路 Open weights imgJanus-Pro 馃嚚馃嚦 ChinaJanus-Pro Unified multimodal model for understanding and generating imagesMultimodal 路 Open weights 路 2025 imgMolmo 馃嚭馃嚫 United StatesMolmo Open vision-language model family by Allen Institute for AIMultimodal 路 Fully open 路 2024 imgvidfnQwen2.5-VL 馃嚚馃嚦 ChinaQwen2.5-VL Vision-language model for images, documents and long videosMultimodal 路 Open weights 路 2025 imgvidfnQwen3-VL 馃嚚馃嚦 ChinaQwen3-VL Vision-language model with deep visual reasoning and long video context.Multimodal 路 Open weights imgvidHyperCLOVA X SEED Think 馃嚢馃嚪 South KoreaHyperCLOVA X SEED Think Efficient reasoning model for Korean and multimodal tasksReasoning 路 Open weights imgEXAONE 4.5 馃嚢馃嚪 South KoreaEXAONE 4.5 Open-weight vision-language model from LG AI ResearchMultimodal 路 Open weights imgwavfnFanar 馃嚩馃嚘 QatarFanar Arabic-centric multimodal generative AI platform and modelsMultimodal 路 API only 路 2025 imgChitrarth 馃嚠馃嚦 IndiaChitrarth Multilingual vision-language model for ten Indian languages and English.Multimodal 路 Conditional licence imgCogVLM 馃嚚馃嚦 ChinaCogVLM Open-source visual language model with deep feature fusionMultimodal 路 Open weights 路 2023 imgvidfnInternVL3 馃嚚馃嚦 ChinaInternVL3 Open-source multimodal large language model seriesMultimodal 路 Open weights 路 2025 imgfnUI-TARS 馃嚚馃嚦 ChinaUI-TARS Open-source multimodal agent for GUI tasksMultimodal 路 Open weights 路 2025 imgNVLM 1.0 馃嚭馃嚫 United StatesNVLM 1.0 Open multimodal language models from NVIDIA for vision and language tasksMultimodal 路 Open weights 路 2024 imgvidGLM-4.1V-Thinking 馃嚚馃嚦 ChinaGLM-4.1V-Thinking Open-source vision-language model with reasoning focusMultimodal 路 Open weights 路 2025 imgPixtral 12B 馃嚝馃嚪 FrancePixtral 12B A 12B multimodal model that reads images and text without losing text skillsMultimodal 路 Open weights 路 2024 imgwavvidReka Core 馃嚫馃嚞 SingaporeReka Core Multimodal language model by RekaMultimodal 路 API only 路 2024 imgSalamandra 馃嚜馃嚫 SpainSalamandra Open multilingual language models for European languagesGeneral 路 Open weights 路 2025 imgwavvidQwen2.5-Omni 馃嚚馃嚦 ChinaQwen2.5-Omni End-to-end multimodal model for real-time speech and video chat.Multimodal 路 Open weights 路 2025 imgLLaVA 馃嚭馃嚫 United StatesLLaVA Open-source multimodal chatbot connecting vision encoders to language models.Multimodal 路 Fully open 路 2023 imgwavGemini 2.0 Flash 馃嚭馃嚫 United StatesGemini 2.0 Flash Google DeepMind's fast multimodal workhorse model for agentic appsGeneral 路 API only 路 2024 imgAmazon Nova 馃嚭馃嚫 United StatesAmazon Nova Amazon's family of foundation models on AWS BedrockGeneral 路 API only 路 2024 imgMM1 WorldMM1 A family of multimodal language models up to 30B parameters, dense and MoE.Multimodal 路 Research only 路 2024 imgGrok-2 馃嚭馃嚫 United StatesGrok-2 xAI's 2024 chat and reasoning model, with a smaller sibling, Grok-2 miniGeneral 路 Conditional licence 路 2024 imgClaude 3 Opus 馃嚭馃嚫 United StatesClaude 3 Opus Anthropic's largest Claude 3 model, aimed at complex reasoning and analysisGeneral 路 API only imgClaude 3 Haiku 馃嚭馃嚫 United StatesClaude 3 Haiku Anthropic's fastest and lowest-cost model in the Claude 3 familyGeneral 路 API only 路 2024 imgwavvidGemini 1.0 馃嚭馃嚫 United StatesGemini 1.0 Google's first Gemini models: multimodal AI in Ultra, Pro and Nano sizesMultimodal 路 API only 路 2023 imgwavvidGemini 3.1 Flash-Lite 馃嚭馃嚫 United StatesGemini 3.1 Flash-Lite A fast, low-cost multimodal reasoning model for high-volume tasksMultimodal 路 API only 路 2026 imgvidfnGemma 3 馃嚭馃嚫 United StatesGemma 3 Lightweight multimodal open models from 1B to 27B parametersGeneral 路 Open weights 路 2025

The weekly digest

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