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

imgwavInkling WorldInkling An open-weights mixture-of-experts model handling text, images and audio inputGeneral 路 Open weights 路 2026 imgWu Dao 馃嚚馃嚦 ChinaWu Dao BAAI's trillion-parameter multimodal model family, announced 2021Multimodal 路 Research only 路 2021 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 imgwavvidQwen 馃嚚馃嚦 ChinaQwen A family of large and small language models developed by Alibaba Cloud.General 路 Open weights 路 2023 imgwavvidNemotron 馃嚭馃嚫 United StatesNemotron Nvidia family of language and multimodal models for enterprise and reasoningGeneral 路 Conditional licence 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 imgAlice AI 馃嚪馃嚭 RussiaAlice AI Yandex's family of language, vision and image models behind the Alice assistantGeneral 路 API 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 imgfnQwen3.5-397B-A17B 馃嚚馃嚦 ChinaQwen3.5-397B-A17B A large multimodal language model with sparse activation.General 路 Open weights imgfnQwen3.6-35B-A3B 馃嚚馃嚦 ChinaQwen3.6-35B-A3B Open-weight multimodal coding model with hybrid architectureCode 路 Open weights 路 2026 imgfnKimi K3.1 Pro 馃嚚馃嚦 ChinaKimi K3.1 Pro Open-weight multimodal agentic model with 1M token contextMultimodal 路 Open weights imgLongCat-2.5 馃嚚馃嚦 ChinaLongCat-2.5 Multimodal MoE model for long-horizon agentic tasksMultimodal 路 Open weights imgERNIE 4.5 馃嚚馃嚦 ChinaERNIE 4.5 Baidu's multimodal mixture-of-experts language model series.General 路 Open weights 路 2025 imgStep3 馃嚚馃嚦 ChinaStep3 Multimodal reasoning model with 321 billion parametersMultimodal 路 Open weights 路 2025 imgvidIntern-S1 馃嚚馃嚦 ChinaIntern-S1 Open-source multimodal reasoning model for scienceReasoning 路 Open weights 路 2025 imgwavvidMiMo-V2.6-Pro 馃嚚馃嚦 ChinaMiMo-V2.6-Pro Xiaomi鈥檚 1T parameter multimodal model with 1M token contextMultimodal 路 Open weights imgvidNemotron 3.5 Super VL 馃嚭馃嚫 United StatesNemotron 3.5 Super VL NVIDIA's open-weight vision-language model with 120B parameters and 1M-token contextMultimodal 路 Conditional licence 路 2026 imgvidDiffusionGemma 馃嚭馃嚫 United StatesDiffusionGemma A multimodal Gemma 4 model that writes text by denoising blocks of tokens.Multimodal 路 Open weights imgDeepSeek-OCR WorldDeepSeek-OCR Optical character recognition model using visual compressionMultimodal 路 Open weights 路 2025 imgvidfnKimi K2.5 馃嚚馃嚦 ChinaKimi K2.5 Open-source multimodal agentic model with vision and reasoning.Multimodal 路 Open weights imgvidfnKimi K3 馃嚚馃嚦 ChinaKimi K3 Open-weight multimodal agentic model with 2.8T parametersGeneral 路 Open weights 路 2026 imgvidfnStep-5-Preview WorldStep-5-Preview Agentic model with 600B parameters and 1M token contextGeneral 路 Open weights 路 2026 imgfnLeanstral 1.5 馃嚝馃嚪 FranceLeanstral 1.5 An open code agent model built for the Lean 4 proof assistantCode 路 Open weights imgfnMistral Large 3 馃嚝馃嚪 FranceMistral Large 3 A 675B-parameter open-weight mixture-of-experts multimodal model from Mistral AIGeneral 路 Open weights imgMM1 WorldMM1 A family of multimodal language models up to 30B parameters, dense and MoE.Multimodal 路 Research only 路 2024 imgApple Foundation Models 馃嚭馃嚫 United StatesApple Foundation Models Apple's 2025 on-device and server language models for Apple IntelligenceGeneral 路 API only 路 2025 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 4 馃嚭馃嚫 United StatesGemma 4 Google DeepMind's open multimodal models in five sizes, from phones to serversGeneral 路 Open weights imgwavvidQwen3-Omni 馃嚚馃嚦 ChinaQwen3-Omni Multimodal model processing text, audio, video and images with real-time speech output.Multimodal 路 Open weights 路 2025 imgvidMiniMax-M3 WorldMiniMax-M3 Native multimodal model with 1M context and sparse attentionMultimodal 路 Open weights imgvidSeed1.5-VL WorldSeed1.5-VL Multimodal vision-language model with reasoning capabilitiesMultimodal 路 API only 路 2025 imgDeepSeek-VL2 馃嚚馃嚦 ChinaDeepSeek-VL2 Mixture-of-experts vision-language model series for multimodal tasksMultimodal 路 Open weights 路 2024 imgvidfnQwen3-VL 馃嚚馃嚦 ChinaQwen3-VL Vision-language model with deep visual reasoning and long video context.Multimodal 路 Open weights

The weekly digest

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