Need smarter insights in your inbox? Join our weekly newsletters to get solely what issues to enterprise AI, information, and safety leaders. Subscribe Now
Chinese language e-commerce big Alibaba’s “Qwen Workforce” has carried out it once more.
Mere days after releasing without cost and with open supply licensing what’s now the highest performing non-reasoning massive language mannequin (LLM) on this planet — full cease, even in comparison with proprietary AI fashions from well-funded U.S. labs resembling Google and OpenAI — within the type of the lengthily named Qwen3-235B-A22B-2507, this group of AI researchers has come out with yet one more blockbuster mannequin.
That’s Qwen3-Coder-480B-A35B-Instruct, a brand new open-source LLM centered on helping with software program growth. It’s designed to deal with complicated, multi-step coding workflows and might create full-fledged, purposeful purposes in seconds or minutes.
The mannequin is positioned to compete with proprietary choices like Claude Sonnet-4 in agentic coding duties and units new benchmark scores amongst open fashions.
It’s accessible on Hugging Face, GitHub, Qwen Chat, by way of Alibaba’s Qwen API, and a rising listing of third-party vibe coding and AI software platforms.
Open sourcing licensing means low price and excessive optionality for enterprises
However not like Claude and different proprietary fashions, Qwen3-Coder, which we’ll name it for brief, is on the market now underneath an open supply Apache 2.0 license, that means it’s free for any enterprise to take with out cost, obtain, modify, deploy and use of their business purposes for workers or finish prospects with out paying Alibaba or anybody else a dime.
It’s additionally so extremely performant on third-party benchmarks and anecdotal utilization amongst AI energy customers for “vibe coding” — coding utilizing pure language and with out formal growth processes and steps — that not less than one, LLM researcher Sebastian Raschka, wrote on X that: “This could be the very best coding mannequin but. Common-purpose is cool, however if you’d like the very best at coding, specialization wins. No free lunch.”
Builders and enterprises focused on downloading it could possibly discover the code on the AI code sharing repository Hugging Face.
Enterprises who don’t want to, or don’t have the capability to host the mannequin on their very own or by means of numerous third-party cloud inference suppliers, also can use it instantly by means of the Alibaba Cloud Qwen API, the place the per-million token prices begin at $1/$5 per million tokens (mTok) for enter/output of as much as 32,000 tokens, then $1.8/$9 for as much as 128,000, $3/$15 for as much as 256,000 and $6/$60 for the complete million.
Mannequin structure and capabilities
In accordance with the documentation launched by Qwen Workforce on-line, Qwen3-Coder is a Combination-of-Consultants (MoE) mannequin with 480 billion whole parameters, 35 billion energetic per question, and eight energetic specialists out of 160.
It helps 256K token context lengths natively, with extrapolation as much as 1 million tokens utilizing YaRN (One more RoPE extrapolatioN — a way used to increase a language mannequin’s context size past its authentic coaching restrict by modifying the Rotary Positional Embeddings (RoPE) used throughout consideration computation. This capability allows the mannequin to know and manipulate total repositories or prolonged paperwork in a single cross.
Designed as a causal language mannequin, it options 62 layers, 96 consideration heads for queries, and eight for key-value pairs. It’s optimized for token-efficient, instruction-following duties and omits assist for
Excessive efficiency
Qwen3-Coder has achieved main efficiency amongst open fashions on a number of agentic analysis suites:
- SWE-bench Verified: 67.0% (commonplace), 69.6% (500-turn)
- GPT-4.1: 54.6%
- Gemini 2.5 Professional Preview: 49.0%
- Claude Sonnet-4: 70.4%
The mannequin additionally scores competitively throughout duties resembling agentic browser use, multi-language programming, and power use. Visible benchmarks present progressive enchancment throughout coaching iterations in classes like code technology, SQL programming, code modifying, and instruction following.
Alongside the mannequin, Qwen has open-sourced Qwen Code, a CLI software forked from Gemini Code. This interface helps perform calling and structured prompting, making it simpler to combine Qwen3-Coder into coding workflows. Qwen Code helps Node.js environments and may be put in by way of npm or from supply.
Qwen3-Coder additionally integrates with developer platforms resembling:
- Claude Code (by way of DashScope proxy or router customization)
- Cline (as an OpenAI-compatible backend)
- Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers
Builders can run Qwen3-Coder domestically or join by way of OpenAI-compatible APIs utilizing endpoints hosted on Alibaba Cloud.
Publish-training methods: code RL and long-horizon planning
Along with pretraining on 7.5 trillion tokens (70% code), Qwen3-Coder advantages from superior post-training methods:
- Code RL (Reinforcement Studying): Emphasizes high-quality, execution-driven studying on various, verifiable code duties
- Lengthy-Horizon Agent RL: Trains the mannequin to plan, use instruments, and adapt over multi-turn interactions
This section simulates real-world software program engineering challenges. To allow it, Qwen constructed a 20,000-environment system on Alibaba Cloud, providing the dimensions obligatory for evaluating and coaching fashions on complicated workflows like these present in SWE-bench.
Enterprise implications: AI for engineering and DevOps workflows
For enterprises, Qwen3-Coder provides an open, extremely succesful different to closed-source proprietary fashions. With robust ends in coding execution and long-context reasoning, it’s particularly related for:
- Codebase-level understanding: Supreme for AI methods that should comprehend massive repositories, technical documentation, or architectural patterns
- Automated pull request workflows: Its means to plan and adapt throughout turns makes it appropriate for auto-generating or reviewing pull requests
- Device integration and orchestration: Via its native tool-calling APIs and performance interface, the mannequin may be embedded in inside tooling and CI/CD methods. This makes it particularly viable for agentic workflows and merchandise, i.e., these the place the consumer triggers one or a number of duties that it desires the AI mannequin to go off and do autonomously, by itself, checking in solely when completed or when questions come up.
- Knowledge residency and price management: As an open mannequin, enterprises can deploy Qwen3-Coder on their very own infrastructure—whether or not cloud-native or on-prem—avoiding vendor lock-in and managing compute utilization extra instantly
Help for lengthy contexts and modular deployment choices throughout numerous dev environments makes Qwen3-Coder a candidate for production-grade AI pipelines in each massive tech corporations and smaller engineering groups.
Developer entry and greatest practices
To make use of Qwen3-Coder optimally, Qwen recommends:
- Sampling settings: temperature=0.7, top_p=0.8, top_k=20, repetition_penalty=1.05
- Output size: As much as 65,536 tokens
- Transformers model: 4.51.0 or later (older variations might throw errors resulting from qwen3_moe incompatibility)
APIs and SDK examples are offered utilizing OpenAI-compatible Python shoppers.
Builders can outline customized instruments and let Qwen3-Coder dynamically invoke them throughout dialog or code technology duties.
Heat early reception from AI energy customers
Preliminary responses to Qwen3-Coder-480B-A35B-Instruct have been notably constructive amongst AI researchers, engineers, and builders who’ve examined the mannequin in real-world coding workflows.
Along with Raschka’s lofty reward above, Wolfram Ravenwolf, an AI engineer and evaluator at EllamindAI, shared his expertise integrating the mannequin with Claude Code on X, stating, “That is certainly the very best one at present.”
After testing a number of integration proxies, Ravenwolf mentioned he in the end constructed his personal utilizing LiteLLM to make sure optimum efficiency, demonstrating the mannequin’s enchantment to hands-on practitioners centered on toolchain customization.
Educator and AI tinkerer Kevin Nelson additionally weighed in on X after utilizing the mannequin for simulation duties.
“Qwen 3 Coder is on one other degree,” he posted, noting that the mannequin not solely executed on offered scaffolds however even embedded a message throughout the output of the simulation — an surprising however welcome signal of the mannequin’s consciousness of job context.
Even Twitter co-founder and Sq. (now referred to as “Block”) founder Jack Dorsey posted an X message in reward of the mannequin, writing: “Goose + qwen3-coder = wow,” in reference to his Block’s open supply AI agent framework Goose, which VentureBeat coated again in January 2025.
These responses recommend Qwen3-Coder is resonating with a technically savvy consumer base looking for efficiency, adaptability, and deeper integration with current growth stacks.
Wanting forward: extra sizes, extra use circumstances
Whereas this launch focuses on essentially the most highly effective variant, Qwen3-Coder-480B-A35B-Instruct, the Qwen staff signifies that further mannequin sizes are in growth.
These will goal to supply comparable capabilities with decrease deployment prices, broadening accessibility.
Future work additionally contains exploring self-improvement, because the staff investigates whether or not agentic fashions can iteratively refine their very own efficiency by means of real-world use.
