> ## Content Index
> Fetch the complete content index at: https://www.theleftshift.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# Alibaba Enters the Vibe Coding Scene with Qwen 3 Coder
- URL: https://www.theleftshift.com/alibaba-enters-the-vibe-coding-scene-with-qwen-3-coder/
- Published: 2025-07-23T05:40:36.000Z
- Updated: 2025-07-23T05:44:37.000Z
- Description: Qwen3-Coder excels at agentic coding—autonomous programming tasks.
- Author: The Left Shift Bureau
- Tags: AI Models

Alibaba team has officially launched [Qwen3-Coder](https://t.co/1LWwUKMrBN?ref=theleftshift.com), its most advanced open-source coding model yet. The flagship variant—480B-parameter Mixture-of-Experts model with 35B active parameters—now supports an impressive 256K context window, expandable to 1 million tokens, revolutionising large-scale code understanding and agent workflows.

Qwen3-Coder excels at agentic coding—autonomous programming tasks—delivering performance on benchmarks like SWE-bench Verified on par with proprietary systems such as Claude Sonnet. The model natively supports browser and tool use, real-time function calling, and runs without separate thinking prompts.

> \>>> Qwen3-Coder is here! ✅  
>  
> We’re releasing Qwen3-Coder-480B-A35B-Instruct, our most powerful open agentic code model to date. This 480B-parameter Mixture-of-Experts model (35B active) natively supports 256K context and scales to 1M context with extrapolation. It achieves… [pic.twitter.com/Z8HfyrVScE](https://t.co/Z8HfyrVScE?ref=theleftshift.com)
> 
> — Qwen (@Alibaba\_Qwen) [July 22, 2025](https://twitter.com/Alibaba%5FQwen/status/1947766835023335516?ref%5Fsrc=twsrc%5Etfw&ref=theleftshift.com)

"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," the company said in a [blog post](https://qwenlm.github.io/blog/qwen3-coder/?ref=theleftshift.com). 

Alongside the model, Alibaba open-sourced Qwen Code, a command-line interface forked from Gemini CLI. It’s tailored for agent interactions and integrates seamlessly with community tools, enabling developers to build agentic workflows efficiently.

The architecture benefits from advanced training: Qwen3-Coder was trained on 7.5T tokens (70% code) using large-scale reinforcement learning and long-horizon optimization. Infrastructure supports 20,000 parallel environments to improve tool and code execution learning, boosting real-world accuracy.

With native 256K context and up to 1M token support, Qwen3-Coder is optimized for repository-scale tasks, personal coding assistants, and multilanguage programming. 

Available now via GitHub, Hugging Face, and conversational APIs, it positions itself as a top-tier open-source rival in agentic AI coding.