News
ReleasesOVHcloud 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 improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior ReleaseReleasesOVHcloud 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 improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior Release
EveryLLM

Dense decoder transformers

The GPT design: one stack of transformer layers predicting the next token. 308 models on EveryLLM so far.

The dense decoder transformer is the design behind GPT and most chatbots. It is a single stack of identical transformer layers that reads the tokens so far and predicts the next one, with a mask that stops each position from looking ahead. Dense means every parameter is used for every token, unlike in a mixture of experts. GPT-3, PaLM, Llama 3, Chinchilla, Gemma, Phi and OLMo are dense decoders.

Inside each layer

Each layer has two parts. Self-attention lets every token weigh every earlier token and gather what it needs; a feed-forward network then transforms each token's vector on its own. The transformer was introduced by Google researchers in the June 2017 paper Attention Is All You Need, for translation, and OpenAI's GPT-1 (2018) kept only its decoder half. Llama 3.1 405B, released in July 2024, stacks 126 such layers.

Why it won

A decoder trains on any text without labels, because the next token is always the answer to predict, and it scales smoothly: scaling laws published by OpenAI in 2020 and DeepMind in 2022 showed the error falling predictably with more parameters, data and compute. Its weak point is cost. Attention grows with the square of the context length, and every parameter must be read for every token, which is why mixtures of experts became popular.

Famous dense decoder models

Still to be written: OLMo (language model).

Further reading

imgwavChatGPT 🇺🇸 United StatesChatGPT OpenAI's chatbot built on GPT models, handling text, audio and imagesAssistant · API only · 2022 imgfnGrok 🇺🇸 United StatesGrok A chatbot and model line from SpaceX Super Intelligence, launched in 2023.General · API only · 2023 fnGPT-5.6 🇺🇸 United StatesGPT-5.6 OpenAI's 2026 model family in Luna, Terra and Sol tiersGeneral · API only · 2026 imgOpenAI o4-mini 🇺🇸 United StatesOpenAI o4-mini Multimodal reasoning model by OpenAI, now retired.Reasoning · API only · 2025 fnOpenAI Codex 🇺🇸 United StatesOpenAI Codex A code-writing language model fine-tuned from GPT-3Code · API only · 2025 wavDoubao 🇨🇳 ChinaDoubao ByteDance's conversational virtual assistant and language model familyAssistant · API only · 2023 imgfnGPT-5.3-Codex 🇺🇸 United StatesGPT-5.3-Codex OpenAI's code-focused large language model with repository and terminal accessCode · API only · 2026 fnGLM 🇨🇳 ChinaGLM Open-weight Chinese model series used for chat and codingGeneral · Open weights · 2021 Amália 🇵🇹 PortugalAmália A Portuguese language model for public administration.Regional · API only · 2024 IBM Granite 🇺🇸 United StatesIBM Granite IBM's decoder-only foundation models, from 3 to 34 billion parametersGeneral · Open weights · 2023 O3 🇺🇸 United StatesO3 Reasoning model from OpenAI designed for step-by-step logical tasks.Reasoning · API only · 2025 imgfnClaude 🇺🇸 United StatesClaude Anthropic's family of large language models and chatbot, from Haiku to MythosGeneral · API only · 2023 imgPhi 🇺🇸 United StatesPhi Microsoft's small open-weights language models that run on a single deviceSmall · Open weights · 2023 GPT-3 🇺🇸 United StatesGPT-3 A large language model with 175 billion parameters released by OpenAI in 2020.General · API only · 2020 imgwavfnKruti 🇮🇳 IndiaKruti A multilingual agentic chatbot that handles real-world tasks on smartphones.Assistant · API only · 2025 OpenAI o1 🇺🇸 United StatesOpenAI o1 OpenAI's first reasoning model, which thinks before answering.Reasoning · API only · 2024 fnGPT-6 🇺🇸 United StatesGPT-6 OpenAI's 2026 family of large language models, led by AstraGeneral · API only · 2026 imgwavKimi 🇨🇳 ChinaKimi A Chinese chatbot and large language model family by Moonshot AI.Assistant · API only · 2023 imgwavGPT-4 🇺🇸 United StatesGPT-4 Multimodal large language model by OpenAIGeneral · API only · 2023 GPT-6.1 🇺🇸 United StatesGPT-6.1 OpenAI's GPT-6.1 family: Sol, Terra and the unreleased Astra models.General · API only · 2026 fnAmazon Q 🇺🇸 United StatesAmazon Q Amazon's enterprise chatbot for AWS, with document summaries, data analysis and code.Assistant · API only · 2023 imgwavAlice AI 🇷🇺 RussiaAlice AI Yandex's Russian voice assistant and generative chatbot, on phones, PCs and smart speakersAssistant · API only · 2017 imgfnApple Intelligence 🇺🇸 United StatesApple Intelligence Apple's on-device and cloud AI features built into iOS, iPadOS and macOSGeneral · API only · 2024 imgGPT-4.1 🇺🇸 United StatesGPT-4.1 Multimodal large language model released by OpenAI in April 2025.General · API only · 2025 imgfnGemini Robotics 🇺🇸 United StatesGemini Robotics A vision-language-action model from Google DeepMind built for robotsMultimodal · API only · 2025 imgHuawei PanGu 🇨🇳 ChinaHuawei PanGu Huawei's multimodal large model family for industry, from 1B to trillion-scaleMultimodal · Open weights · 2023 imgfnGPT-5 🇺🇸 United StatesGPT-5 Multimodal large language model released by OpenAI in August 2025.Multimodal · API only · 2025 imgwavvidQwen 🇨🇳 ChinaQwen A family of large and small language models developed by Alibaba Cloud.General · Open weights · 2023 imgfnGPT-5.1 🇺🇸 United StatesGPT-5.1 A five-model GPT family with instant, reasoning and coding variantsGeneral · API only · 2025 LaMDA WorldLaMDA Google's conversational language model family, first shown in 2021General · API only · 2020 Claude Mythos 🇺🇸 United StatesClaude Mythos Anthropic's restricted model family for finding software security flawsDomain · Research only · 2026 imgfnMuse 🇺🇸 United StatesMuse Meta's multimodal LLM family, successor to Llama, with open and closed variantsGeneral · API only · 2026 fnDeepSeek 🇨🇳 ChinaDeepSeek A Chinese series of large language models and a free chatbot appGeneral · API only · 2025 imgwavHKChat 🇭🇰 Hong KongHKChat A Hong Kong-focused chatbot app built on the HKGAI V3 language model.Assistant · API only · 2025 imgwavvidGemini 🇺🇸 United StatesGemini Google DeepMind's multimodal LLM family, from Nano to UltraGeneral · API only · 2023 PaLM 🇺🇸 United StatesPaLM Google AI's 540-billion-parameter dense decoder-only transformer language modelGeneral · API only · 2022 GPT-5.2 🇺🇸 United StatesGPT-5.2 OpenAI's December 2025 GPT release, offered in three modes plus a coding variant.General · API only · 2025 imgDALL-E 🇺🇸 United StatesDALL-E Text-to-image model series by OpenAIMultimodal · API only · 2021 fnClaude 4 🇺🇸 United StatesClaude 4 Anthropic's fourth-generation coding and reasoning models, Opus 4 and Sonnet 4General · API only · 2025 imgfnClaude 3.7 Sonnet 🇺🇸 United StatesClaude 3.7 Sonnet Anthropic's hybrid reasoning model with a controllable thinking budgetGeneral · API only · 2025 imgGrok-2 🇺🇸 United StatesGrok-2 xAI's 2024 chat and reasoning model, with a smaller sibling, Grok-2 miniGeneral · Conditional licence · 2024 imgClaude 3.5 Haiku 🇺🇸 United StatesClaude 3.5 Haiku Anthropic's fast, low-latency model for coding, tools and user-facing productsGeneral · API only · 2024 imgClaude 3 Haiku 🇺🇸 United StatesClaude 3 Haiku Anthropic's fastest and lowest-cost model in the Claude 3 familyGeneral · API only · 2024 imgwavfnGrok 4 🇺🇸 United StatesGrok 4 xAI's flagship reasoning model with native tool use and live searchGeneral · API only · 2025 imgClaude 3 Opus 🇺🇸 United StatesClaude 3 Opus Anthropic's largest Claude 3 model, aimed at complex reasoning and analysisGeneral · API only Claude 2 🇺🇸 United StatesClaude 2 Anthropic's 2023 assistant model with a 100K-token window and stronger coding.General · API only · 2023 Claude 1 🇺🇸 United StatesClaude 1 Anthropic's first AI assistant model, offered in two versions via chat and API.Assistant · API only InstructGPT 🇺🇸 United StatesInstructGPT GPT-3 models fine-tuned with human feedback to follow instructionsGeneral · API only · 2022

The weekly digest

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