ChenZiHong-Gavin/llm-tech-report

A summary of technical reports for various large language models (LLMs).

Python

17 commits

updated Aug 19, 2026

README

📄 LLM Technical Reports

A curated collection of technical reports, system cards, and model cards from major LLM labs — organized by company, with links to official documents.

🏢 Organized by company — easy to track a lab's model evolution
📅 Chronological — each company's reports sorted by release date
🌐 Comprehensive — covers both Western and Chinese AI labs

OpenAI
Google / DeepMind
Anthropic
Meta
DeepSeek
Alibaba / Qwen
Shanghai AI Lab / InternLM
ByteDance
Zhipu AI / GLM
Moonshot AI / Kimi
Baidu / ERNIE
Tencent / Hunyuan
MiniMax
Mistral AI
xAI / Grok
Microsoft / Phi
Amazon
Nvidia
AI21 Labs
Databricks
TII / Falcon
Reka AI
Cohere
Apple
Baichuan
01.AI / Yi
Meituan
StepFun
InclusionAI (Ant Group)
Xiaomi / MiMo
Zhijiang Lab / Moxin

Contributing

OpenAI

Date	Model	Type	Link
2018-06	GPT-1	Paper	Improving Language Understanding by Generative Pre-Training
2019-02	GPT-2	Paper	Language Models are Unsupervised Multitask Learners
2020-05	GPT-3	Paper	Language Models are Few-Shot Learners
2022-03	InstructGPT	Paper	Training language models to follow instructions with human feedback
2023-03	GPT-4	Technical Report	GPT-4 Technical Report
2023-09	GPT-4V	System Card	GPT-4V(ision) System Card
2024-05	GPT-4o	System Card	GPT-4o System Card
2024-07	GPT-4o mini	System Card	GPT-4o mini System Card
2024-09	o1	System Card	OpenAI o1 System Card
2024-12	o1 (full)	System Card	o1 and o1 pro System Card
2025-01	o3-mini	System Card	o3-mini System Card
2025-04	o3 / o4-mini	System Card	o3 and o4-mini System Card
2025-08	GPT-5	System Card	GPT-5 System Card
2025-08	GPT-oss-120B/20B	Model Card	GPT-oss Model Card
2025-08	GPT-oss	Paper	GPT-oss Technical Report
2025-12	GPT-5.2	System Card	GPT-5.2 System Card
2026-02	GPT-5.3 Codex	System Card	Codex System Card
2026-04	GPT-5.5	System Card	GPT-5.5 System Card
2026-07	GPT-5.6	System Card	GPT-5.6 System Card
2026-07	GPT-Live-1 / mini	System Card	GPT-Live System Card

Google / DeepMind

Date	Model	Type	Link
2017-06	Transformer	Paper	Attention Is All You Need
2018-10	BERT	Paper	BERT: Pre-training of Deep Bidirectional Transformers
2019-10	T5	Paper	Exploring the Limits of Transfer Learning
2020-01	Meena	Paper	Towards a Human-like Open-Domain Chatbot
2022-01	LaMDA	Paper	LaMDA: Language Models for Dialog Applications
2022-04	PaLM	Paper	PaLM: Scaling Language Modeling with Pathways
2023-05	PaLM 2	Technical Report	PaLM 2 Technical Report
2023-12	Gemini 1.0	Technical Report	Gemini: A Family of Highly Capable Multimodal Models
2024-02	Gemma 1	Technical Report	Gemma: Open Models Based on Gemini Research and Technology
2024-03	Gemini 1.5	Technical Report	Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
2024-08	Gemma 2	Technical Report	Gemma 2: Improving Open Language Models at a Practical Size
2025-03	Gemma 3	Technical Report	Gemma 3 Technical Report
2025-07	Gemini 2.5 Pro	Model Card	Gemini 2.5 Pro Model Card
2025-07	Gemini 2.5 Flash	Model Card	Gemini 2.5 Flash Model Card
2025-07	Gemini 2.5 Flash	Technical Report	Gemini 2.5 Technical Report
2025-07	Gemini 2.5 Pro	Technical Report	Gemini 2.5 Technical Report
2025-11	Gemini 3 Pro	Model Card	Gemini 3 Pro Model Card
2025-12	Gemini 3 Flash	Model Card	Gemini 3 Flash Model Card
2026-05	Gemini 3.5 Flash	Model Card	Gemini 3.5 Flash Model Card
2026-05	Gemini Omni Flash	Model Card	Gemini Omni Flash Model Card
2026-06	Gemini 3.5 Audio	Model Card	Gemini 3.5 Audio Model Card
2026-06	Gemini 3.1 Flash-Lite Image	Model Card	Gemini 3.1 Flash-Lite Image Model Card
2026-07	Gemini 3.6 Flash	Model Card	Gemini 3.6 Flash Model Card
2026-07	Gemini 3.5 Flash-Lite	Model Card	Gemini 3.5 Flash-Lite Model Card
2026-07	Lyria 3.5	Model Card	Lyria 3.5 Model Card
2026-07	Gemini Robotics ER 2	Model Card	Gemini Robotics ER 2 Model Card
2026-07	Gemini Robotics On-Device 2	Model Card	Gemini Robotics On-Device 2 Model Card
2026-08	Gemini 3.7 Flash	Model Card	Gemini 3.7 Flash Model Card

Anthropic

Date	Model	Type	Link
2023-03	Claude (Constitutional AI)	Paper	Constitutional AI: Harmlessness from AI Feedback
2023-07	Claude 2	Model Card	Claude 2 Model Card
2024-03	Claude 3 Family	Model Card	The Claude 3 Model Family
2025-02	Claude 3.7 Sonnet	System Card	Claude 3.7 Sonnet System Card
2025-05	Claude Opus 4 / Sonnet 4	System Card	Claude Opus 4 and Sonnet 4 System Card
2025-06	Claude Opus 4.5	System Card	Claude Opus 4.5 System Card
2025-06	Claude Sonnet 4.5	System Card	Claude Sonnet 4.5 System Card
2026-02	Claude Opus 4.6	System Card	Claude Opus 4.6 System Card
2026-04	Claude Opus 4.7 / Sonnet 4.6	System Card	Claude Opus 4.7 and Sonnet 4.6 System Card
2026-05	Claude Opus 4.8	System Card	Claude Opus 4.8
2026-06	Claude Fable 5 / Mythos 5	System Card	Claude Fable 5 and Mythos 5
2026-06	Claude Sonnet 5	System Card	Claude Sonnet 5 System Card
2026-07	Claude Opus 5	System Card	Claude Opus 5 System Card

Date	Model	Type	Link
2023-02	LLaMA	Paper	LLaMA: Open and Efficient Foundation Language Models
2023-07	Llama 2	Paper	Llama 2: Open Foundation and Fine-Tuned Chat Models
2024-04	Llama 3.1	Paper	The Llama 3 Herd of Models
2024-07	Llama 3	Paper	The Llama 3 Herd of Models
2025-04	Llama 4 Scout / Maverick	Blog	Llama 4: Open, Multimodal Intelligence
2025-06	Llama 4 Behemoth	Blog	Llama 4 Behemoth
2026-04	Muse Spark	Blog	Introducing Muse Spark

DeepSeek

Date	Model	Type	Link
2024-01	DeepSeek LLM (67B)	Paper	DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
2024-01	DeepSeek-Coder	Paper	DeepSeek-Coder: When the Large Language Model Meets Programming
2024-02	DeepSeek-Math	Paper	DeepSeek-Math: Pushing the Limits of Mathematical Reasoning in Open Language Models
2024-03	DeepSeek-VL	Paper	DeepSeek-VL: Towards Real-World Vision-Language Understanding
2024-05	DeepSeek-V2	Paper	DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
2024-06	DeepSeek-Coder-V2	Paper	DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
2024-08	DeepSeek-Prover-V1.5	Paper	DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback
2024-12	DeepSeek-V3	Paper	DeepSeek-V3 Technical Report
2024-12	DeepSeek-VL2	Paper	DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
2025-01	DeepSeek-R1	Paper	DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
2025-04	DeepSeek-Prover-V2	Paper	DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
2025-12	DeepSeek-V3.2	Paper	DeepSeek-V3.2
2026-04	DeepSeek-V4	Technical Report	DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Alibaba / Qwen

Date	Model	Type	Link
2023-09	Qwen	Paper	Qwen Technical Report
2023-10	Qwen-VL	Paper	Qwen-VL: A Versatile Vision-Language Model
2023-11	Qwen-Audio	Paper	Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
2024-07	Qwen2	Paper	Qwen2 Technical Report
2024-07	Qwen2-Audio	Paper	Qwen2-Audio Technical Report
2024-08	Qwen2-Math	Paper	Qwen2-Math Technical Report
2024-09	Qwen2.5	Paper	Qwen2.5 Technical Report
2024-09	Qwen2.5-Coder	Paper	Qwen2.5-Coder Technical Report
2024-09	Qwen2-VL	Paper	Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
2024-11	QwQ-32B-Preview	Blog	QwQ: Reflect Deeply on the Boundaries of the Unknown
2025-01	Qwen2.5-Max	Blog	Qwen2.5-Max: Exploring the Intelligence of Large-scale MoE Model
2025-03	Qwen2.5-VL	Paper	Qwen2.5-VL Technical Report
2025-03	Qwen2.5-Omni	Paper	Qwen2.5-Omni Technical Report
2025-03	QwQ-32B	Blog	QwQ-32B: Embracing the Power of Reinforcement Learning
2025-04	Qwen3	Paper	Qwen3 Technical Report
2025-06	Qwen3-Coder	Blog	Qwen3-Coder
2025-08	Qwen-Image	Paper	Qwen-Image Technical Report
2025-11	Qwen3-VL	Paper	Qwen3-VL Technical Report
2026-02	Qwen 3.5	Blog	Qwen 3.5
2026-04	Qwen3.5-Omni	Paper	Qwen3.5-Omni Technical Report
2026-04	Qwen3.6	Blog	Qwen3.6
2026-07	Qwen-Image-3.0	Blog	Qwen-Image-3.0

Shanghai AI Lab / InternLM

Date	Model	Type	Link
2023-09	InternLM	Paper	InternLM: A Multilingual Language Model with Progressively Enhanced Capabilities
2023-12	InternVL	Paper	InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
2024-03	InternLM2	Paper	InternLM2 Technical Report
2024-04	InternVL 1.5	Paper	How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
2024-07	InternLM-XComposer-2.5	Paper	InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
2024-07	InternVL2	Paper	InternVL2: Better than the Best — Expanding Performance Boundaries of Open-Source Multimodal Models
2024-12	InternVL2.5	Paper	Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
2025-04	InternLM3	GitHub	InternLM3-8B
2026-03	InternVL-U	Paper	InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
2026-05	Intern-S2-Preview	Model Card	Intern-S2-Preview
2026-06	Future-L1	Paper	Imagine Before You Predict: Interleaved Latent Visual Reasoning
2026-06	CapRL++	Paper	CapRL++: Unified RL with Verifiable Rewards for Dense Captioning

ByteDance

Date	Model	Type	Link
2024-10	Doubao/Seed1.0	Blog	Doubao Model Family
2025-04	Seed1.5-Thinking	Paper	Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
2025-05	Seed1.5-VL	Paper	Seed1.5-VL: Better Vision-Language Understanding with Mixture of Experts
2026-02	MedXIAOHE	Paper	MedXIAOHE: A Medical Vision-Language Foundation Model
2026-02	Seed 2.0	Model Card	Seed 2.0 Model Card
2026-04	Seeduplex	Blog	Introducing Seed Full-Duplex Speech LLM
2026-04	Seedance 2.0	Technical Report	Seedance 2.0: Advancing Video Generation for World Complexity
2026-05	Seed3D 2.0	Technical Report	Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
2026-05	Cola DLM	Paper	Continuous Latent Diffusion Language Model
2026-05	TaskMem	Paper	Task-Focused Memorization for Multimodal Agents
2026-06	Seed-2.1-Pro-Preview	Blog	Seed-2.1-Preview Model Release on Arena

Zhipu AI / GLM

Date	Model	Type	Link
2022-10	GLM-130B	Paper	GLM-130B: An Open Bilingual Pre-trained Model
2024-01	CogVLM	Paper	CogVLM: Visual Expert for Pretrained Language Models
2024-06	GLM-4	Paper	ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
2024-08	CogVideoX	Paper	CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
2024-12	GLM-Zero	Blog	GLM-Zero-Preview
2025-08	GLM-4.5	Paper	GLM-4.5: An Open Mixture-of-Experts LLM
2026-02	GLM-5	Paper	GLM-5
2026-04	GLM-4.6V	Blog	GLM-4.6V
2026-06	GLM-5.2	Blog	GLM-5.2: Built for Long-Horizon Tasks

Moonshot AI / Kimi

Date	Model	Type	Link
2024-03	Kimi (Moonshot-v1)	Blog	Kimi — First 200k context length model
2025-07	Kimi K2.0	Paper	Kimi K2.0 Technical Report
2026-02	Kimi K2.5	Paper	Kimi K2.5 Technical Report
2026-04	Kimi K2.6	Blog	Kimi K2.6

Baidu / ERNIE

Date	Model	Type	Link
2021-12	ERNIE 3.0	Paper	ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
2023-12	ERNIE Bot (3.5/4.0)	Paper	ERNIE Bot: Advanced Language Model
2025-06	ERNIE 4.5	Technical Report	ERNIE 4.5 Technical Report
2026-02	ERNIE 5.0	Paper	ERNIE 5.0
2026-05	ERNIE-Image	Technical Report	ERNIE-Image Technical Report
2026-05	ERNIE 5.1	Blog	ERNIE 5.1 Officially Released
2026-06	PaddleOCR-VL-1.6	Technical Report	PaddleOCR-VL-1.6 Technical Report

Tencent / Hunyuan

Date	Model	Type	Link
2024-03	Hunyuan-DiT	Paper	Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
2024-11	Hunyuan-Large	Paper	Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters
2025-03	Hunyuan-T1	Blog	Hunyuan Turbomind T1
2025-05	Yuanbao (Hunyuan-TurboS)	Paper	Hunyuan-TurboS: A Hybrid Transformer-Mamba MoE Model
2026-04	Hy3-preview	GitHub	Hy3-preview
2026-06	Hy-Embodied-0.5-VLA	GitHub	Hy-Embodied-0.5-VLA
2026-07	Hy3	Blog	Tencent Hunyuan Officially Releases Hy3

MiniMax

Date	Model	Type	Link
2025-01	MiniMax-01	Paper	MiniMax-01: Scaling Foundation Models with Lightning Attention
2025-10	MiniMax M2.0	Paper	MiniMax M2.0
2025-12	MiniMax M2.1	GitHub	MiniMax M2.1
2026-02	MiniMax M2.5	Blog	MiniMax M2.5
2026-04	MiniMax M2.7	Blog	MiniMax M2.7
2026-06	MiniMax M3	Model Card	MiniMax-M3
2026-06	MiniMax Sparse Attention	Paper	MiniMax Sparse Attention
2026-07	MiniMax H3	Blog	MiniMax H3: An Open Model Breaking the Boundaries Between Tasks and Modalities

Mistral AI

Date	Model	Type	Link
2023-10	Mistral 7B	Paper	Mistral 7B
2024-01	Mixtral 8x7B	Paper	Mixtral of Experts
2024-05	Mistral 8x22B	Blog	Cheaper, Better, Faster, Stronger
2024-07	Mistral Large 2	Blog	Mistral Large 2
2024-09	Mistral Pixtral 12B	Blog	Pixtral 12B
2024-11	Mistral Pixtral Large	Blog	Pixtral Large
2025-01	Mistral Small 3	Blog	Mistral Small 3
2025-02	Mistral Saba	Blog	Mistral Saba
2025-03	Mistral Small 3.1	Blog	Mistral Small 3.1
2025-05	Mistral Medium 3	Blog	Mistral Medium 3
2025-06	Magistral	Paper	Magistral
2025-08	Devstral	Paper	Devstral: Fine-tuning Language Models for Coding Agent Applications
2026-03	Mistral Small 4	Blog	Introducing Mistral Small 4
2026-06	Mistral OCR 4	Blog	Introducing Mistral OCR 4
2026-07	Leanstral 1.5	Blog	Leanstral 1.5: Proof Abundance for All
2026-07	Robostral Navigate	Paper	Robostral Navigate

xAI / Grok

Date	Model	Type	Link
2024-03	Grok-1	Blog	Open Release of Grok-1
2024-08	Grok-2	Blog	Grok-2 Beta Release
2025-02	Grok-3	Blog	Grok 3
2025-08	Grok 4	Model Card	Grok 4 Model Card
2025-11	Grok 4.1	Model Card	Grok 4.1 Model Card
2026-07	Grok 4.5	Model Card	Grok 4.5 Model Card
2026-07	Grok Voice Think Fast 2.0	Blog	Introducing Grok Voice Think Fast 2.0

Microsoft / Phi

Date	Model	Type	Link
2023-06	Phi-1	Paper	Textbooks Are All You Need
2023-12	Phi-2	Paper	Phi-2: The surprising power of small language models
2024-04	Phi-3	Paper	Phi-3 Technical Report
2024-12	Phi-4	Paper	Phi-4 Technical Report
2025-02	Phi-4-mini	Paper	Phi-4-mini Technical Report
2025-05	Phi-4-reasoning	Paper	Phi-4-reasoning Technical Report
2025-06	Phi-4-multimodal	Paper	Phi-4-multimodal Technical Report
2026-03	Phi-4-reasoning-vision-15B	Paper	Phi-4-reasoning-vision-15B Technical Report

Amazon

Date	Model	Type	Link
2024-12	Nova (Micro/Lite/Pro)	Blog	Introducing Amazon Nova Foundation Models
2025-06	Nova Family	Paper	The Amazon Nova Family of Models: Technical Report and Model Card
2025-12	Amazon Nova 2	Technical Report	Amazon Nova 2: Multimodal Reasoning and Generation Models

Nvidia

Date	Model	Type	Link
2024-06	Nemotron-4 340B	Paper	Nemotron-4 340B Technical Report
2024-10	Llama-3.1-Nemotron-70B	Model Card	Llama-3.1-Nemotron-70B-Instruct
2025-03	Llama-3.1-Nemotron-Ultra-253B	Paper	Llama-Nemotron: An Open Reasoning Model Family
2025-12	NVIDIA Nemotron 3	Paper	NVIDIA Nemotron 3: Efficient and Open Intelligence

AI21 Labs

Date	Model	Type	Link
2024-03	Jamba	Paper	Jamba: A Hybrid Transformer-Mamba Language Model
2024-08	Jamba-1.5	Paper	Jamba-1.5: Hybrid Transformer-Mamba Models at Scale
2026-01	Jamba2	Blog	Introducing Jamba2

Databricks

Date	Model	Type	Link
2024-03	DBRX	Blog	Introducing DBRX: A New State-of-the-Art Open LLM

TII / Falcon

Date	Model	Type	Link
2023-06	Falcon (7B/40B/180B)	Paper	The Falcon Series of Open Language Models
2024-05	Falcon 2 (11B)	Blog	Falcon 2: An 11B Parameter Multilingual Model
2024-12	Falcon 3	Blog	Falcon 3
2026-01	Falcon-H1R 7B	Blog	Introducing Falcon H1R 7B

Reka AI

Date	Model	Type	Link
2024-04	Reka Core/Flash/Edge	Paper	Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models
2025-07	Reka Flash 3.1	Blog	Reka Flash 3.1 and Reka Quant

Baichuan

Date	Model	Type	Link
2023-06	Baichuan	Paper	Baichuan 2: Open Large-scale Language Models
2023-09	Baichuan 2	Paper	Baichuan 2: Open Large-scale Language Models
2025-09	Baichuan-M2	Paper	Baichuan-M2: A Medical LLM
2026-02	Baichuan-M3	Paper	Baichuan-M3
2026-06	Baichuan-M4	Paper	Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care

01.AI / Yi

Date	Model	Type	Link
2024-03	Yi	Paper	Yi: Open Foundation Models by 01.AI
2024-05	Yi-1.5	GitHub	Yi-1.5: Updated, Stronger
2024-09	Yi-Coder	Blog	Yi-Coder: A Small but Mighty LLM for Code
2025-02	Yi-Lightning	Paper	Yi-Lightning Technical Report

Meituan

Date	Model	Type	Link
2025-09	LongCat-Flash	Paper	LongCat-Flash
2025-09	LongCat-Flash-Thinking	Paper	LongCat-Flash-Thinking
2025-10	LongCat-Flash-Omni	Paper	LongCat-Flash-Omni
2025-12	LongCat-Image	Paper	LongCat-Image Technical Report
2026-01	LongCat-Flash-Thinking-2601	Technical Report	LongCat-Flash-Thinking-2601 Technical Report
2026-03	LongCat-Next	Paper	LongCat-Next: Lexicalizing Modalities as Discrete Tokens
2026-05	LongCat-Video-Avatar-1.5	Model Card	LongCat-Video-Avatar-1.5

StepFun

Date	Model	Type	Link
2025-12	Step-DeepResearch	Paper	Step-DeepResearch
2026-02	Step-3.5-Flash	Paper	Step-3.5-Flash
2026-05	StepAudio 2.5	Technical Report	StepAudio 2.5 Technical Report
2026-05	Step-3.7-Flash	Blog	Step 3.7 Flash

InclusionAI (Ant Group)

Date	Model	Type	Link
2026-02	Ling 2.5	GitHub	Ling 2.5
2026-04	LLaDA2.0-Uni	Paper	LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion LLM
2026-04	DR-Venus	Paper	DR-Venus: Frontier Edge-Scale Deep Research Agents
2026-04	Ling-2.6-1T	Model Card	Ling-2.6-1T
2026-04	Ling-2.6-flash	Model Card	Ling-2.6-flash
2026-04	cuLA	GitHub	cuLA
2026-06	Ling/Ring 2.6	Technical Report	Ling and Ring 2.6 Technical Report
2026-06	Sing-Guard	GitHub	Sing-Guard

Zhijiang Lab / Moxin

Date	Model	Type	Link
2024-12	Moxin-7B	Paper	Fully Open Source Moxin-7B Technical Report
2025-09	CC-MoE	Paper	Collaborative Compression for Large-Scale MoE Deployment on Edge
2025-12	Moxin-VLM/VLA	Paper	Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA

Xiaomi / MiMo

Date	Model	Type	Link
2025-04	MiMo-7B	Paper	MiMo: Unlocking the Reasoning Potential of Language Model
2025-07	MiMo-V2-Flash	GitHub	MiMo-V2-Flash
2025-11	MiMo-Embodied	Technical Report	MiMo-Embodied: X-Embodied Foundation Model Technical Report
2025-12	MiMo-VL-Miloco	Technical Report	Xiaomi MiMo-VL-Miloco Technical Report
2025-12	MiMo-Audio	Technical Report	MiMo-Audio: Audio Language Models are Few-Shot Learners
2026-01	MiMo-V2-Flash	Technical Report	MiMo-V2-Flash Technical Report
2026-04	MiMo-V2.5-ASR	GitHub	MiMo-V2.5-ASR
2026-06	MiMo-Code	GitHub	MiMo-Code

Cohere

Date	Model	Type	Link
2024-03	Command R	Blog	Introducing Command R
2024-04	Command R+	Blog	Command R+
2024-08	Aya-23	Paper	Aya 23: Open Weight Releases to Further Multilingual Progress
2024-12	Aya Expanse	Paper	Aya Expanse: Connecting the Global Majority
2025-03	Command A	Blog	Command A
2026-05	Command A+	Blog	Introducing Command A+

Apple

Date	Model	Type	Link
2023-12	Ferret	Paper	Ferret: Refer and Ground Anything Anywhere at Any Granularity
2024-07	Apple Intelligence (AFM)	Paper	Apple Intelligence Foundation Language Models
2024-12	AIMv2	Paper	AIMv2: A Family of Strong Image Encoders
2026-06	Apple Foundation Models (3rd gen)	Blog	Introducing the Third Generation of Apple's Foundation Models

Contributing

Contributions welcome! To add a new report:

Fork this repo
Add the entry to the appropriate company section in README.md
Follow the format: | Date | Model | Type | Link |
Submit a PR

Guidelines:

Only include official publications: technical reports, papers, system cards, model cards, or official blog posts
Use the original source link (arxiv, official CDN, company blog)
Date format: YYYY-MM
Sort entries chronologically within each company section

🤖 AI-assisted maintenance: This repo ships native instruction files for AI assistants — Claude Code skills (.claude/skills/), Cursor rules (.cursor/rules/), and Codex (AGENTS.md) — so your assistant follows the schema and guardrails automatically. See CONTRIBUTING.md.

License

This project is licensed under the MIT License.

Acknowledgements

This project is inspired by:

Contributors

ChenZiHong-Gavin

17 commits

Similar repos

Hannibal046/Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

27,422

harrytea/Awesome-Document-Understanding

Document Artifical Intelligence

202

andysingal/llm-course

887

RUCAIBox/LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

12,219

coderonion/awesome-llm-and-aigc

🚀🚀🚀A collection of some awesome public projects about Large Language Model(LLM), Vision Language…

814

Psi-Robot/Awesome-VLA-Papers

Paper list in the survey: A Survey on Vision-Language-Action Models: An Action Tokenization…

577

yanfeng98/paper-is-all-you-need

论文就是你所需要的。

BradyFU/Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

18,035

Languages

Python

100.0%

ChenZiHong-Gavin/llm-tech-report

A summary of technical reports for various large language models (LLMs).

Python

17 commits

updated Aug 19, 2026

See the code

README

📄 LLM Technical Reports

A curated collection of technical reports, system cards, and model cards from major LLM labs — organized by company, with links to official documents.

🏢 Organized by company — easy to track a lab's model evolution
📅 Chronological — each company's reports sorted by release date
🌐 Comprehensive — covers both Western and Chinese AI labs

OpenAI
Google / DeepMind
Anthropic
Meta
DeepSeek
Alibaba / Qwen
Shanghai AI Lab / InternLM
ByteDance
Zhipu AI / GLM
Moonshot AI / Kimi
Baidu / ERNIE
Tencent / Hunyuan
MiniMax
Mistral AI
xAI / Grok
Microsoft / Phi
Amazon
Nvidia
AI21 Labs
Databricks
TII / Falcon
Reka AI
Cohere
Apple
Baichuan
01.AI / Yi
Meituan
StepFun
InclusionAI (Ant Group)
Xiaomi / MiMo
Zhijiang Lab / Moxin

Contributing

OpenAI

Date	Model	Type	Link
2018-06	GPT-1	Paper	Improving Language Understanding by Generative Pre-Training
2019-02	GPT-2	Paper	Language Models are Unsupervised Multitask Learners
2020-05	GPT-3	Paper	Language Models are Few-Shot Learners
2022-03	InstructGPT	Paper	Training language models to follow instructions with human feedback
2023-03	GPT-4	Technical Report	GPT-4 Technical Report
2023-09	GPT-4V	System Card	GPT-4V(ision) System Card
2024-05	GPT-4o	System Card	GPT-4o System Card
2024-07	GPT-4o mini	System Card	GPT-4o mini System Card
2024-09	o1	System Card	OpenAI o1 System Card
2024-12	o1 (full)	System Card	o1 and o1 pro System Card
2025-01	o3-mini	System Card	o3-mini System Card
2025-04	o3 / o4-mini	System Card	o3 and o4-mini System Card
2025-08	GPT-5	System Card	GPT-5 System Card
2025-08	GPT-oss-120B/20B	Model Card	GPT-oss Model Card
2025-08	GPT-oss	Paper	GPT-oss Technical Report
2025-12	GPT-5.2	System Card	GPT-5.2 System Card
2026-02	GPT-5.3 Codex	System Card	Codex System Card
2026-04	GPT-5.5	System Card	GPT-5.5 System Card
2026-07	GPT-5.6	System Card	GPT-5.6 System Card
2026-07	GPT-Live-1 / mini	System Card	GPT-Live System Card

Google / DeepMind

Date	Model	Type	Link
2017-06	Transformer	Paper	Attention Is All You Need
2018-10	BERT	Paper	BERT: Pre-training of Deep Bidirectional Transformers
2019-10	T5	Paper	Exploring the Limits of Transfer Learning
2020-01	Meena	Paper	Towards a Human-like Open-Domain Chatbot
2022-01	LaMDA	Paper	LaMDA: Language Models for Dialog Applications
2022-04	PaLM	Paper	PaLM: Scaling Language Modeling with Pathways
2023-05	PaLM 2	Technical Report	PaLM 2 Technical Report
2023-12	Gemini 1.0	Technical Report	Gemini: A Family of Highly Capable Multimodal Models
2024-02	Gemma 1	Technical Report	Gemma: Open Models Based on Gemini Research and Technology
2024-03	Gemini 1.5	Technical Report	Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
2024-08	Gemma 2	Technical Report	Gemma 2: Improving Open Language Models at a Practical Size
2025-03	Gemma 3	Technical Report	Gemma 3 Technical Report
2025-07	Gemini 2.5 Pro	Model Card	Gemini 2.5 Pro Model Card
2025-07	Gemini 2.5 Flash	Model Card	Gemini 2.5 Flash Model Card
2025-07	Gemini 2.5 Flash	Technical Report	Gemini 2.5 Technical Report
2025-07	Gemini 2.5 Pro	Technical Report	Gemini 2.5 Technical Report
2025-11	Gemini 3 Pro	Model Card	Gemini 3 Pro Model Card
2025-12	Gemini 3 Flash	Model Card	Gemini 3 Flash Model Card
2026-05	Gemini 3.5 Flash	Model Card	Gemini 3.5 Flash Model Card
2026-05	Gemini Omni Flash	Model Card	Gemini Omni Flash Model Card
2026-06	Gemini 3.5 Audio	Model Card	Gemini 3.5 Audio Model Card
2026-06	Gemini 3.1 Flash-Lite Image	Model Card	Gemini 3.1 Flash-Lite Image Model Card
2026-07	Gemini 3.6 Flash	Model Card	Gemini 3.6 Flash Model Card
2026-07	Gemini 3.5 Flash-Lite	Model Card	Gemini 3.5 Flash-Lite Model Card
2026-07	Lyria 3.5	Model Card	Lyria 3.5 Model Card
2026-07	Gemini Robotics ER 2	Model Card	Gemini Robotics ER 2 Model Card
2026-07	Gemini Robotics On-Device 2	Model Card	Gemini Robotics On-Device 2 Model Card
2026-08	Gemini 3.7 Flash	Model Card	Gemini 3.7 Flash Model Card

Anthropic

Date	Model	Type	Link
2023-03	Claude (Constitutional AI)	Paper	Constitutional AI: Harmlessness from AI Feedback
2023-07	Claude 2	Model Card	Claude 2 Model Card
2024-03	Claude 3 Family	Model Card	The Claude 3 Model Family
2025-02	Claude 3.7 Sonnet	System Card	Claude 3.7 Sonnet System Card
2025-05	Claude Opus 4 / Sonnet 4	System Card	Claude Opus 4 and Sonnet 4 System Card
2025-06	Claude Opus 4.5	System Card	Claude Opus 4.5 System Card
2025-06	Claude Sonnet 4.5	System Card	Claude Sonnet 4.5 System Card
2026-02	Claude Opus 4.6	System Card	Claude Opus 4.6 System Card
2026-04	Claude Opus 4.7 / Sonnet 4.6	System Card	Claude Opus 4.7 and Sonnet 4.6 System Card
2026-05	Claude Opus 4.8	System Card	Claude Opus 4.8
2026-06	Claude Fable 5 / Mythos 5	System Card	Claude Fable 5 and Mythos 5
2026-06	Claude Sonnet 5	System Card	Claude Sonnet 5 System Card
2026-07	Claude Opus 5	System Card	Claude Opus 5 System Card

Date	Model	Type	Link
2023-02	LLaMA	Paper	LLaMA: Open and Efficient Foundation Language Models
2023-07	Llama 2	Paper	Llama 2: Open Foundation and Fine-Tuned Chat Models
2024-04	Llama 3.1	Paper	The Llama 3 Herd of Models
2024-07	Llama 3	Paper	The Llama 3 Herd of Models
2025-04	Llama 4 Scout / Maverick	Blog	Llama 4: Open, Multimodal Intelligence
2025-06	Llama 4 Behemoth	Blog	Llama 4 Behemoth
2026-04	Muse Spark	Blog	Introducing Muse Spark

DeepSeek

Date	Model	Type	Link
2024-01	DeepSeek LLM (67B)	Paper	DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
2024-01	DeepSeek-Coder	Paper	DeepSeek-Coder: When the Large Language Model Meets Programming
2024-02	DeepSeek-Math	Paper	DeepSeek-Math: Pushing the Limits of Mathematical Reasoning in Open Language Models
2024-03	DeepSeek-VL	Paper	DeepSeek-VL: Towards Real-World Vision-Language Understanding
2024-05	DeepSeek-V2	Paper	DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
2024-06	DeepSeek-Coder-V2	Paper	DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
2024-08	DeepSeek-Prover-V1.5	Paper	DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback
2024-12	DeepSeek-V3	Paper	DeepSeek-V3 Technical Report
2024-12	DeepSeek-VL2	Paper	DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
2025-01	DeepSeek-R1	Paper	DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
2025-04	DeepSeek-Prover-V2	Paper	DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
2025-12	DeepSeek-V3.2	Paper	DeepSeek-V3.2
2026-04	DeepSeek-V4	Technical Report	DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Alibaba / Qwen

Date	Model	Type	Link
2023-09	Qwen	Paper	Qwen Technical Report
2023-10	Qwen-VL	Paper	Qwen-VL: A Versatile Vision-Language Model
2023-11	Qwen-Audio	Paper	Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
2024-07	Qwen2	Paper	Qwen2 Technical Report
2024-07	Qwen2-Audio	Paper	Qwen2-Audio Technical Report
2024-08	Qwen2-Math	Paper	Qwen2-Math Technical Report
2024-09	Qwen2.5	Paper	Qwen2.5 Technical Report
2024-09	Qwen2.5-Coder	Paper	Qwen2.5-Coder Technical Report
2024-09	Qwen2-VL	Paper	Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
2024-11	QwQ-32B-Preview	Blog	QwQ: Reflect Deeply on the Boundaries of the Unknown
2025-01	Qwen2.5-Max	Blog	Qwen2.5-Max: Exploring the Intelligence of Large-scale MoE Model
2025-03	Qwen2.5-VL	Paper	Qwen2.5-VL Technical Report
2025-03	Qwen2.5-Omni	Paper	Qwen2.5-Omni Technical Report
2025-03	QwQ-32B	Blog	QwQ-32B: Embracing the Power of Reinforcement Learning
2025-04	Qwen3	Paper	Qwen3 Technical Report
2025-06	Qwen3-Coder	Blog	Qwen3-Coder
2025-08	Qwen-Image	Paper	Qwen-Image Technical Report
2025-11	Qwen3-VL	Paper	Qwen3-VL Technical Report
2026-02	Qwen 3.5	Blog	Qwen 3.5
2026-04	Qwen3.5-Omni	Paper	Qwen3.5-Omni Technical Report
2026-04	Qwen3.6	Blog	Qwen3.6
2026-07	Qwen-Image-3.0	Blog	Qwen-Image-3.0

Shanghai AI Lab / InternLM

Date	Model	Type	Link
2023-09	InternLM	Paper	InternLM: A Multilingual Language Model with Progressively Enhanced Capabilities
2023-12	InternVL	Paper	InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
2024-03	InternLM2	Paper	InternLM2 Technical Report
2024-04	InternVL 1.5	Paper	How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
2024-07	InternLM-XComposer-2.5	Paper	InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
2024-07	InternVL2	Paper	InternVL2: Better than the Best — Expanding Performance Boundaries of Open-Source Multimodal Models
2024-12	InternVL2.5	Paper	Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
2025-04	InternLM3	GitHub	InternLM3-8B
2026-03	InternVL-U	Paper	InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
2026-05	Intern-S2-Preview	Model Card	Intern-S2-Preview
2026-06	Future-L1	Paper	Imagine Before You Predict: Interleaved Latent Visual Reasoning
2026-06	CapRL++	Paper	CapRL++: Unified RL with Verifiable Rewards for Dense Captioning

ByteDance

Date	Model	Type	Link
2024-10	Doubao/Seed1.0	Blog	Doubao Model Family
2025-04	Seed1.5-Thinking	Paper	Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
2025-05	Seed1.5-VL	Paper	Seed1.5-VL: Better Vision-Language Understanding with Mixture of Experts
2026-02	MedXIAOHE	Paper	MedXIAOHE: A Medical Vision-Language Foundation Model
2026-02	Seed 2.0	Model Card	Seed 2.0 Model Card
2026-04	Seeduplex	Blog	Introducing Seed Full-Duplex Speech LLM
2026-04	Seedance 2.0	Technical Report	Seedance 2.0: Advancing Video Generation for World Complexity
2026-05	Seed3D 2.0	Technical Report	Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
2026-05	Cola DLM	Paper	Continuous Latent Diffusion Language Model
2026-05	TaskMem	Paper	Task-Focused Memorization for Multimodal Agents
2026-06	Seed-2.1-Pro-Preview	Blog	Seed-2.1-Preview Model Release on Arena

Zhipu AI / GLM

Date	Model	Type	Link
2022-10	GLM-130B	Paper	GLM-130B: An Open Bilingual Pre-trained Model
2024-01	CogVLM	Paper	CogVLM: Visual Expert for Pretrained Language Models
2024-06	GLM-4	Paper	ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
2024-08	CogVideoX	Paper	CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
2024-12	GLM-Zero	Blog	GLM-Zero-Preview
2025-08	GLM-4.5	Paper	GLM-4.5: An Open Mixture-of-Experts LLM
2026-02	GLM-5	Paper	GLM-5
2026-04	GLM-4.6V	Blog	GLM-4.6V
2026-06	GLM-5.2	Blog	GLM-5.2: Built for Long-Horizon Tasks

Moonshot AI / Kimi

Date	Model	Type	Link
2024-03	Kimi (Moonshot-v1)	Blog	Kimi — First 200k context length model
2025-07	Kimi K2.0	Paper	Kimi K2.0 Technical Report
2026-02	Kimi K2.5	Paper	Kimi K2.5 Technical Report
2026-04	Kimi K2.6	Blog	Kimi K2.6

Baidu / ERNIE

Date	Model	Type	Link
2021-12	ERNIE 3.0	Paper	ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
2023-12	ERNIE Bot (3.5/4.0)	Paper	ERNIE Bot: Advanced Language Model
2025-06	ERNIE 4.5	Technical Report	ERNIE 4.5 Technical Report
2026-02	ERNIE 5.0	Paper	ERNIE 5.0
2026-05	ERNIE-Image	Technical Report	ERNIE-Image Technical Report
2026-05	ERNIE 5.1	Blog	ERNIE 5.1 Officially Released
2026-06	PaddleOCR-VL-1.6	Technical Report	PaddleOCR-VL-1.6 Technical Report

Tencent / Hunyuan

Date	Model	Type	Link
2024-03	Hunyuan-DiT	Paper	Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
2024-11	Hunyuan-Large	Paper	Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters
2025-03	Hunyuan-T1	Blog	Hunyuan Turbomind T1
2025-05	Yuanbao (Hunyuan-TurboS)	Paper	Hunyuan-TurboS: A Hybrid Transformer-Mamba MoE Model
2026-04	Hy3-preview	GitHub	Hy3-preview
2026-06	Hy-Embodied-0.5-VLA	GitHub	Hy-Embodied-0.5-VLA
2026-07	Hy3	Blog	Tencent Hunyuan Officially Releases Hy3

MiniMax

Date	Model	Type	Link
2025-01	MiniMax-01	Paper	MiniMax-01: Scaling Foundation Models with Lightning Attention
2025-10	MiniMax M2.0	Paper	MiniMax M2.0
2025-12	MiniMax M2.1	GitHub	MiniMax M2.1
2026-02	MiniMax M2.5	Blog	MiniMax M2.5
2026-04	MiniMax M2.7	Blog	MiniMax M2.7
2026-06	MiniMax M3	Model Card	MiniMax-M3
2026-06	MiniMax Sparse Attention	Paper	MiniMax Sparse Attention
2026-07	MiniMax H3	Blog	MiniMax H3: An Open Model Breaking the Boundaries Between Tasks and Modalities

Mistral AI

Date	Model	Type	Link
2023-10	Mistral 7B	Paper	Mistral 7B
2024-01	Mixtral 8x7B	Paper	Mixtral of Experts
2024-05	Mistral 8x22B	Blog	Cheaper, Better, Faster, Stronger
2024-07	Mistral Large 2	Blog	Mistral Large 2
2024-09	Mistral Pixtral 12B	Blog	Pixtral 12B
2024-11	Mistral Pixtral Large	Blog	Pixtral Large
2025-01	Mistral Small 3	Blog	Mistral Small 3
2025-02	Mistral Saba	Blog	Mistral Saba
2025-03	Mistral Small 3.1	Blog	Mistral Small 3.1
2025-05	Mistral Medium 3	Blog	Mistral Medium 3
2025-06	Magistral	Paper	Magistral
2025-08	Devstral	Paper	Devstral: Fine-tuning Language Models for Coding Agent Applications
2026-03	Mistral Small 4	Blog	Introducing Mistral Small 4
2026-06	Mistral OCR 4	Blog	Introducing Mistral OCR 4
2026-07	Leanstral 1.5	Blog	Leanstral 1.5: Proof Abundance for All
2026-07	Robostral Navigate	Paper	Robostral Navigate

xAI / Grok

Date	Model	Type	Link
2024-03	Grok-1	Blog	Open Release of Grok-1
2024-08	Grok-2	Blog	Grok-2 Beta Release
2025-02	Grok-3	Blog	Grok 3
2025-08	Grok 4	Model Card	Grok 4 Model Card
2025-11	Grok 4.1	Model Card	Grok 4.1 Model Card
2026-07	Grok 4.5	Model Card	Grok 4.5 Model Card
2026-07	Grok Voice Think Fast 2.0	Blog	Introducing Grok Voice Think Fast 2.0

Microsoft / Phi

Date	Model	Type	Link
2023-06	Phi-1	Paper	Textbooks Are All You Need
2023-12	Phi-2	Paper	Phi-2: The surprising power of small language models
2024-04	Phi-3	Paper	Phi-3 Technical Report
2024-12	Phi-4	Paper	Phi-4 Technical Report
2025-02	Phi-4-mini	Paper	Phi-4-mini Technical Report
2025-05	Phi-4-reasoning	Paper	Phi-4-reasoning Technical Report
2025-06	Phi-4-multimodal	Paper	Phi-4-multimodal Technical Report
2026-03	Phi-4-reasoning-vision-15B	Paper	Phi-4-reasoning-vision-15B Technical Report

Amazon

Date	Model	Type	Link
2024-12	Nova (Micro/Lite/Pro)	Blog	Introducing Amazon Nova Foundation Models
2025-06	Nova Family	Paper	The Amazon Nova Family of Models: Technical Report and Model Card
2025-12	Amazon Nova 2	Technical Report	Amazon Nova 2: Multimodal Reasoning and Generation Models

Nvidia

Date	Model	Type	Link
2024-06	Nemotron-4 340B	Paper	Nemotron-4 340B Technical Report
2024-10	Llama-3.1-Nemotron-70B	Model Card	Llama-3.1-Nemotron-70B-Instruct
2025-03	Llama-3.1-Nemotron-Ultra-253B	Paper	Llama-Nemotron: An Open Reasoning Model Family
2025-12	NVIDIA Nemotron 3	Paper	NVIDIA Nemotron 3: Efficient and Open Intelligence

AI21 Labs

Date	Model	Type	Link
2024-03	Jamba	Paper	Jamba: A Hybrid Transformer-Mamba Language Model
2024-08	Jamba-1.5	Paper	Jamba-1.5: Hybrid Transformer-Mamba Models at Scale
2026-01	Jamba2	Blog	Introducing Jamba2

Databricks

Date	Model	Type	Link
2024-03	DBRX	Blog	Introducing DBRX: A New State-of-the-Art Open LLM

TII / Falcon

Date	Model	Type	Link
2023-06	Falcon (7B/40B/180B)	Paper	The Falcon Series of Open Language Models
2024-05	Falcon 2 (11B)	Blog	Falcon 2: An 11B Parameter Multilingual Model
2024-12	Falcon 3	Blog	Falcon 3
2026-01	Falcon-H1R 7B	Blog	Introducing Falcon H1R 7B

Reka AI

Date	Model	Type	Link
2024-04	Reka Core/Flash/Edge	Paper	Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models
2025-07	Reka Flash 3.1	Blog	Reka Flash 3.1 and Reka Quant

Baichuan

Date	Model	Type	Link
2023-06	Baichuan	Paper	Baichuan 2: Open Large-scale Language Models
2023-09	Baichuan 2	Paper	Baichuan 2: Open Large-scale Language Models
2025-09	Baichuan-M2	Paper	Baichuan-M2: A Medical LLM
2026-02	Baichuan-M3	Paper	Baichuan-M3
2026-06	Baichuan-M4	Paper	Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care

01.AI / Yi

Date	Model	Type	Link
2024-03	Yi	Paper	Yi: Open Foundation Models by 01.AI
2024-05	Yi-1.5	GitHub	Yi-1.5: Updated, Stronger
2024-09	Yi-Coder	Blog	Yi-Coder: A Small but Mighty LLM for Code
2025-02	Yi-Lightning	Paper	Yi-Lightning Technical Report

Meituan

Date	Model	Type	Link
2025-09	LongCat-Flash	Paper	LongCat-Flash
2025-09	LongCat-Flash-Thinking	Paper	LongCat-Flash-Thinking
2025-10	LongCat-Flash-Omni	Paper	LongCat-Flash-Omni
2025-12	LongCat-Image	Paper	LongCat-Image Technical Report
2026-01	LongCat-Flash-Thinking-2601	Technical Report	LongCat-Flash-Thinking-2601 Technical Report
2026-03	LongCat-Next	Paper	LongCat-Next: Lexicalizing Modalities as Discrete Tokens
2026-05	LongCat-Video-Avatar-1.5	Model Card	LongCat-Video-Avatar-1.5

StepFun

Date	Model	Type	Link
2025-12	Step-DeepResearch	Paper	Step-DeepResearch
2026-02	Step-3.5-Flash	Paper	Step-3.5-Flash
2026-05	StepAudio 2.5	Technical Report	StepAudio 2.5 Technical Report
2026-05	Step-3.7-Flash	Blog	Step 3.7 Flash

InclusionAI (Ant Group)

Date	Model	Type	Link
2026-02	Ling 2.5	GitHub	Ling 2.5
2026-04	LLaDA2.0-Uni	Paper	LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion LLM
2026-04	DR-Venus	Paper	DR-Venus: Frontier Edge-Scale Deep Research Agents
2026-04	Ling-2.6-1T	Model Card	Ling-2.6-1T
2026-04	Ling-2.6-flash	Model Card	Ling-2.6-flash
2026-04	cuLA	GitHub	cuLA
2026-06	Ling/Ring 2.6	Technical Report	Ling and Ring 2.6 Technical Report
2026-06	Sing-Guard	GitHub	Sing-Guard

Zhijiang Lab / Moxin

Date	Model	Type	Link
2024-12	Moxin-7B	Paper	Fully Open Source Moxin-7B Technical Report
2025-09	CC-MoE	Paper	Collaborative Compression for Large-Scale MoE Deployment on Edge
2025-12	Moxin-VLM/VLA	Paper	Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA

Xiaomi / MiMo

Date	Model	Type	Link
2025-04	MiMo-7B	Paper	MiMo: Unlocking the Reasoning Potential of Language Model
2025-07	MiMo-V2-Flash	GitHub	MiMo-V2-Flash
2025-11	MiMo-Embodied	Technical Report	MiMo-Embodied: X-Embodied Foundation Model Technical Report
2025-12	MiMo-VL-Miloco	Technical Report	Xiaomi MiMo-VL-Miloco Technical Report
2025-12	MiMo-Audio	Technical Report	MiMo-Audio: Audio Language Models are Few-Shot Learners
2026-01	MiMo-V2-Flash	Technical Report	MiMo-V2-Flash Technical Report
2026-04	MiMo-V2.5-ASR	GitHub	MiMo-V2.5-ASR
2026-06	MiMo-Code	GitHub	MiMo-Code

Cohere

Date	Model	Type	Link
2024-03	Command R	Blog	Introducing Command R
2024-04	Command R+	Blog	Command R+
2024-08	Aya-23	Paper	Aya 23: Open Weight Releases to Further Multilingual Progress
2024-12	Aya Expanse	Paper	Aya Expanse: Connecting the Global Majority
2025-03	Command A	Blog	Command A
2026-05	Command A+	Blog	Introducing Command A+

Apple

Date	Model	Type	Link
2023-12	Ferret	Paper	Ferret: Refer and Ground Anything Anywhere at Any Granularity
2024-07	Apple Intelligence (AFM)	Paper	Apple Intelligence Foundation Language Models
2024-12	AIMv2	Paper	AIMv2: A Family of Strong Image Encoders
2026-06	Apple Foundation Models (3rd gen)	Blog	Introducing the Third Generation of Apple's Foundation Models

Contributing

Contributions welcome! To add a new report:

Fork this repo
Add the entry to the appropriate company section in README.md
Follow the format: | Date | Model | Type | Link |
Submit a PR

Guidelines:

Only include official publications: technical reports, papers, system cards, model cards, or official blog posts
Use the original source link (arxiv, official CDN, company blog)
Date format: YYYY-MM
Sort entries chronologically within each company section

🤖 AI-assisted maintenance: This repo ships native instruction files for AI assistants — Claude Code skills (.claude/skills/), Cursor rules (.cursor/rules/), and Codex (AGENTS.md) — so your assistant follows the schema and guardrails automatically. See CONTRIBUTING.md.

License

This project is licensed under the MIT License.

Acknowledgements

This project is inspired by:

Similar repos

Hannibal046/Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

27,422

harrytea/Awesome-Document-Understanding

Document Artifical Intelligence

202

andysingal/llm-course

887

RUCAIBox/LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

12,219

coderonion/awesome-llm-and-aigc

🚀🚀🚀A collection of some awesome public projects about Large Language Model(LLM), Vision Language…

814

Psi-Robot/Awesome-VLA-Papers

Paper list in the survey: A Survey on Vision-Language-Action Models: An Action Tokenization…

577

yanfeng98/paper-is-all-you-need

论文就是你所需要的。

BradyFU/Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

18,035

Contributors

ChenZiHong-Gavin

17 commits

Languages

Python

100.0%

ChenZiHong-Gavin/llm-tech-report

README

📄 LLM Technical Reports

Table of Contents

OpenAI

Google / DeepMind

Anthropic

Meta

DeepSeek

Alibaba / Qwen

Shanghai AI Lab / InternLM

ByteDance

Zhipu AI / GLM

Moonshot AI / Kimi

Baidu / ERNIE

Tencent / Hunyuan

MiniMax

Mistral AI

xAI / Grok

Microsoft / Phi

Amazon

Nvidia

AI21 Labs

Databricks

TII / Falcon

Reka AI

Baichuan

01.AI / Yi

Meituan

StepFun

InclusionAI (Ant Group)

Zhijiang Lab / Moxin

Xiaomi / MiMo

Cohere

Apple

Contributing

License

Acknowledgements

Contributors

Similar repos

Languages

ChenZiHong-Gavin/llm-tech-report

README

📄 LLM Technical Reports

Table of Contents

OpenAI

Google / DeepMind

Anthropic

Meta

DeepSeek

Alibaba / Qwen

Shanghai AI Lab / InternLM

ByteDance

Zhipu AI / GLM

Moonshot AI / Kimi

Baidu / ERNIE

Tencent / Hunyuan

MiniMax

Mistral AI

xAI / Grok

Microsoft / Phi

Amazon

Nvidia

AI21 Labs

Databricks

TII / Falcon

Reka AI

Baichuan

01.AI / Yi

Meituan

StepFun

InclusionAI (Ant Group)

Zhijiang Lab / Moxin

Xiaomi / MiMo

Cohere

Apple

Contributing

License

Acknowledgements

Similar repos