Alibaba Cloud / Qwen Team model product
Qwen3 Coder 480B A35B
Qwen3-Coder-480B-A35B-Instruct is Qwen's most agentic code model to date, featuring 480 billion total parameters with 35 billion activated parameters using MoE architecture.
Updated Aug 12, 2026. Default version: Qwen3-Coder 480B A35B Instruct
LLMBoard score35.5Qwen3-Coder 480B A35B Instruct
Coverage20%9 benchmark families
Context window262.1KTokens
Official input price$1.5Alibaba API
Qwen3 Coder 480B A35B Specifications
Technical details for the model's default version.
- Version
- Qwen3-Coder 480B A35B Instruct
- Released
- Jan 31, 2025
- Knowledge cutoff
- Apr 1, 2025
- Parameters
- 480B
- Context window
- 262.1K
- Max output
- 65.5K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Qwen3 Coder 480B A35B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3 Coder 480B A35B Benchmark Results
Benchmark scores for Qwen3-Coder 480B A35B Instruct.
| Spider | 31.1% | 02 | 2 | 0.0% | C | |
| MM-Mind2Web | 55.8% | 03 | 3 | 0.0% | C | |
| Multi-SWE-Bench | 25.8% | 06 | 6 | 0.0% | C | |
| TAU-bench Airline | 60.0% | 07 | 23 | 72.7% | C | |
| TAU-bench Retail | 77.5% | 08 | 25 | 70.8% | C | |
| Aider-Polyglot | 61.8% | 11 | 22 | 52.4% | C | |
| BFCL-v3 | 68.7% | 12 | 19 | 38.9% | C | |
| SWE-bench Multilingual | 54.7% | 28 | 34 | 18.2% | C | |
| Terminal-Bench 2.0 | 37.5% | 47 | 49 | 4.2% | C | |
| SWE-Bench Verified | 69.6% | 61 | 105 | 42.3% | C |
Qwen3 Coder 480B A35B Arena Results
Preference and agent-evaluation results for the default version.
| webdev | overall | 93 | 1273.1 | 12,293 | N/A | |
| text factuality | overall | 130 | 1400.5 | 3,539 | N/A | |
| text style control | overall | 155 | 1387.8 | 25,816 | N/A | |
| text | overall | 174 | 1356.6 | 25,816 | N/A |
Qwen3 Coder 480B A35B Runtime Performance
Provider-specific output speed and catalog latency for Qwen3-Coder 480B A35B Instruct. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3 Coder 480B A35B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.5 input, $7.5 output per 1M
- Official provider
- Alibaba
- Lowest third-party
- From $0.20 input, $0.80 output per 1M via submodel
- Tracked offerings
- 16
| Nvidia | qwen/qwen3-coder-480b-a35b-instruct | global | N/A | N/A | 262.1K | |
| submodel | Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | global | $0.20 | $0.80 | 262.1K | |
| Amazon Bedrock | qwen.qwen3-coder-480b-a35b-v1:0 | global | $0.22 | $1.8 | 131.1K | |
| Merge Gateway | qwen/qwen3-coder-480b-a35b-instruct | global | $0.22 | $1.8 | 131.1K | |
| Abacus | Qwen/Qwen3-Coder-480B-A35B-Instruct | global | $0.29 | $1.2 | 262.1K | |
| Jiekou.AI | qwen/qwen3-coder-480b-a35b-instruct | global | $0.29 | $1.2 | 262.1K | |
| LLM Gateway | qwen3-coder-480b-a35b-instruct | global | $0.30 | $1.3 | 262.1K | |
| NovitaAI | qwen/qwen3-coder-480b-a35b-instruct | global | $0.38 | $1.55 | 262.1K | |
| Charm Hyper | qwen3-coder-480b-a35b-instruct-int4-mixed-ar | global | $0.445 | $2.15 | 106K | |
| 302.AI | qwen3-coder-480b-a35b-instruct | global | $0.86 | $3.43 | 262.1K | |
| Alibaba (China) | qwen3-coder-480b-a35b-instruct | global | $0.861 | $3.44 | 262.1K | |
| Alibaba | qwen3-coder-480b-a35b-instruct | global | $1.5 | $7.5 | 262.1K | |
| Vercel AI Gateway | alibaba/qwen3-coder | global | $1.5 | $7.5 | 262.1K | |
| Together AI | Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | global | $2 | $2 | 262.1K | |
| Hugging Face | Qwen/Qwen3-Coder-480B-A35B-Instruct | global | $2 | $2 | 262.1K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen3 Coder 480B A35B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Qwen3-Coder 480B A35B Instruct | 35.5 | 480B | 262.1K | 65.5K | Yes | Apache 2.0 |
What is Qwen3 Coder 480B A35B?
Key information about Qwen3 Coder 480B A35B and its available data.
Qwen3-Coder-480B-A35B-Instruct is Qwen's most agentic code model to date, featuring 480 billion total parameters with 35 billion activated parameters using MoE architecture.
It achieves significant performance among open models on Agentic Coding, Agentic Browser-Use, and foundational coding tasks, with results comparable to Claude Sonnet.
Features native 256K token context length (extendable to 1M tokens with Yarn), optimized for repository-scale understanding, and specialized function call format for agentic coding platforms like Qwen Code and CLINE.
Data as of 2026-08-11.
Qwen3 Coder 480B A35B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Qwen3 Coder 480B A35B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3 VL 32B
Alibaba Cloud / Qwen Team
AC
Qwen3 Next 80B A3B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 4B
Alibaba Cloud / Qwen Team
AC
Qwen3 30B A3B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 30B A3B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 32B
Alibaba Cloud / Qwen Team
FAQ
Common questions about Qwen3 Coder 480B A35B.
When was Qwen3 Coder 480B A35B released?
Qwen3 Coder 480B A35B's default version was released on Jan 31, 2025.
How much does Qwen3 Coder 480B A35B cost?
Qwen3 Coder 480B A35B's official API price is $1.5 per million input tokens and $7.5 per million output tokens via Alibaba. The lowest tracked third-party offer starts at $0.20 input and $0.80 output via submodel.
Who created Qwen3 Coder 480B A35B?
Qwen3 Coder 480B A35B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3 Coder 480B A35B?
The default version has a 262.1K token context window.
Is Qwen3 Coder 480B A35B open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Qwen3 Coder 480B A35B?
16 provider offerings are linked to the default version.
What models should I compare Qwen3 Coder 480B A35B with?
Nearby ranked alternatives include o3 mini, GPT-4.5, Grok Code Fast 1.