Get the latest tech news
Qwen3-Coder: Agentic coding in the world
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.
By automatically scaling test cases of diversity coding tasks, we created high-quality training instances and successfully unlocked the full potential of reinforcement learning. In real-world software engineering tasks like SWE-Bench, Qwen3-Coder must engage in multi-turn interaction with the environment, involving planning, using tools, receiving feedback, and making decisions. We are still actively working to improve the performance of our Coding Agent, aiming for it to take on more complex and tedious tasks in software engineering, thereby freeing up human productivity.
Or read this on Hacker News
