Alibaba’s Qwen staff launched a brand new synthetic intelligence (AI) coding mannequin on Tuesday. Dubbed Qwen 3 Coder, the mannequin comes with a number of agentic capabilities together with agentic coding, agentic browser-use, and agentic tool-use. The researchers have launched just one variant of the mannequin to this point, the Qwen3-Coder-480B-A35B-Instruct, which is probably the most highly effective variant within the household. When it comes to efficiency in coding, Alibaba’s AI staff claims the open-source mannequin is similar to Anthropic’s Claude Sonnet 4 mannequin. The brand new massive language mannequin (LLM) is on the market to obtain domestically.
Qwen 3 Coder Mannequin With Agentic Capabilities Launched
In a blog post, the researchers detailed the brand new agentic coding device. Accessible in open-source, people can obtain the weights from Qwen’s Hugging Face listing and GitHub listing. The mannequin is on the market with a permissive Apache 2.0 licence which permits for each educational and business utilization. Alongside the mannequin, an open-source command-line device dubbed Qwen Code can also be obtainable for agentic coding.
Coming to the mannequin, the Qwen 3 Coder is a mixture-of-expert (MoE) mannequin with 480 billion parameters. Out of that, the mannequin features with 35 billion lively parameters and a context size of two,56,000 tokens natively. The context window could be expanded to 1 million tokens utilizing extrapolation strategies. The researchers highlighted that the mannequin helps agentic coding, agentic browser-use, and agentic tool-use.
The corporate claims that Qwen 3 Coder achieved state-of-the-art (SOTA) efficiency amongst open-source fashions on the SWE-Bench Verified benchmark. Right here, SOTA refers back to the highest rating which was beforehand unattainable by every other mannequin. The Qwen staff stated this rating was achieved by making a scalable system utilizing Alibaba Cloud’s infrastructure that would run 20,000 unbiased environments in parallel.
To allow agentic coding, the staff has additionally launched the Qwen Code command-line device. Constructed from Gemini Code, it has been outfitted with customized prompts and performance calling protocols. These functionalities enable the AI mannequin to not solely write and edit code but additionally to deploy and execute it in an built-in improvement atmosphere (IDE).
Whereas Qwen Code natively helps Qwen 3 Coder AI mannequin, it can be built-in with the OpenAI software program improvement equipment (SDK) when calling LLMs. Alternatively, the Qwen coding mannequin can be used with Claude Code. However builders might want to request an API key on Alibaba Cloud Mannequin Studio platform.