Qwen3 Coder 480B A35B Instruct
Analysis Summary
Qwen3 Coder 480B A35B Instruct is Alibaba's large mixture-of-experts coding model, with an intelligence index of 18, LiveCodeBench at 0.585, and an agentic index of 31.3. Instruction following (IFBench 0.405) and long-context reliability (LCR 0.423) are both strong, and tau2 at 0.436 suggests reliable multi-step task execution.
For businesses, it is a strong fit for software engineering automation, code review, agentic coding pipelines, and long-document analysis. At $1.50 input and $7.50 output per million tokens, pricing is moderate for a model of this scale. The main limitation is that it is a specialist coding model; general reasoning depth is lower than frontier models at similar price points.
A -4 point regional penalty applies. Teams running coding-heavy automation or agentic workflows who can work with Alibaba's infrastructure will find this a capable and cost-competitive option. For Western-hosted deployments, alternatives from Anthropic or OpenAI may be preferable.
Assessed June 30, 2026
Editorial notes
Qwen3 Coder 480B A35B Instruct from Alibaba is a large MoE coding specialist with LiveCodeBench at 0.585, strong agentic and instruction-following scores, and broad task coverage, though a regional penalty applies.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen3 Coder 480B A35B Instruct compares
Qwen3 Coder 480B A35B Instruct ranks #159 of 385 AI models we track for overall intelligence, #141 of 293 for agentic tasks. At $1.50 per million input tokens it is cheaper than 18% of comparable models.
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen3 Coder 480B A35B Instruct stack up?
Compare side-by-side with other professional models.
Model Information
| Provider | Alibaba |
| Release Date | July 22, 2025 |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.50 | $0.001500 |
| Output | $7.50 | $0.007500 |
Leaderboard Categories
Frequently asked questions about Qwen3 Coder 480B A35B Instruct
How much does Qwen3 Coder 480B A35B Instruct cost?
Qwen3 Coder 480B A35B Instruct costs $1.50 per million input tokens and $7.50 per million output tokens.
Who created Qwen3 Coder 480B A35B Instruct?
Qwen3 Coder 480B A35B Instruct is developed by Alibaba and was released on July 22, 2025.
