GITHUB HUGGING FACE MODELSCOPE DISCORD Today, we’re announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we’re excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports the context length of 256K tokens natively and 1M tokens with extrapolation methods, offering exceptional performance in both coding and agentic tasks. Qwen3-Coder-480B-A35B-Instruct sets new state-of-the-art results among open models on Agentic Coding, Agentic Browser-Use, and Agentic Tool-Use, comparable to Claude Sonnet 4.
Honey, I Shrunk the Coding Agent
Coding Agent Adaptation Lets a 9B LLM Outperform 10x Larger Models on Aider Polyglot Benchmark
qwen3.5:27b
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
MCP Agent Fine tuning Workshop - Ronan McGovern
Can agentic coding raise the quality bar?
Five examples of using agentic coding to improve software quality, instead of delivery throughput.
Prime Agent: A self-improving RLM agent
Prime Agent is our open-source, self-improving coding harness built around two abstractions: the Recursive Language Model (RLM) and the Continual Harness. With Opus 5, it achieves 95.5% on ARC-AGI-3, surpassing the reported human expert baseline.
Running local models is good now
Local agentic coding has gotten great over the past few months
Code execution with MCP: building more efficient AI agents
Learn how code execution with the Model Context Protocol enables agents to handle more tools while using fewer tokens, reducing context overhead by up to 98.7%.
OpenCode Zen | A curated set of reliable optimized models for coding agents
OpenCode - The open source coding agent.
A sufficiently detailed spec is code
Specifications do not address the limitations of agentic coding
Qwen on Twitter / X
📢Meet Qwen3.8-Max — our most capable model to date. Next week, the open weights of Qwen3.8-Max will be released, and Qwen3.8-27B is also going open-weights to meet you all!🎉Qwen3.8-Max, a new bar for coding and cowork at 2.4T parameters:- Autonomous coding: 10+ days of… pic.twitter.com/e3YFj2hqcT— Qwen (@Alibaba_Qwen) August 3, 2026
AI Coding Plan-Code Freely. Ship Faster. No Surprise Bills. - Alibaba Cloud
Experience top-tier performance at a fixed monthly price. Qwen3-Coder-Plus, the cost-effective choice. Works with Cline, Claude Code & Qwen Code.
Vibe coding and agentic engineering are getting closer than I’d like
I recently talked with Joseph Ruscio about AI coding tools for Heavybit’s High Leverage podcast: Ep. #9, The AI Coding Paradigm Shift with Simon Willison. Here are some of my …
Kimi K3 - Kimi API Platform
Kimi K3 is our flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence. The Kimi API Platform provides K3, K2.7 Code, K2.6 and other large language model APIs, supporting long context, multimodal understanding, and Tool Calling.
Agentic Engineering Patterns - Simon Willison's Weblog
Patterns for getting the best results out of coding agents like Claude Code and OpenAI Codex. See my introduction for more on this project.