Intel / article

Qwen3-Coder: Agentic Coding in the World

Source: qwenlm.github.io
Date: Jul 21, 2026

Why it matters

Meet Qwen3-Coder-480B, an open MoE model with 35B active params
Native 256K context, extendable to 1M tokens via extrapolation
Claims SOTA open-model results rivaling Claude Sonnet 4 on agentic coding

Key quotes

“Today, we’re announcing Qwen3-Coder, our most agentic code model to date.”

“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.”

Transcript

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.

Read the source ↗qwenlm.github.io