Alibaba Cloud / Qwen Team model product
Qwen3 Coder 480B A35B
Qwen3 Coder 480B A35B is an MoE code model with 480 billion total parameters and 35 billion activated parameters.
Updated Oct 23, 2026. Default version: Qwen3-Coder 480B A35B Instruct
LLMBoard Score33.6Qwen3-Coder 480B A35B Instruct
Coverage80%9 benchmark families
Context window262.1KTokens
Official input price$1.5Alibaba API
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.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkSpider | Score31.10% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMM-Mind2Web | Score55.80% | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMulti-SWE-Bench | Score25.80% | Rank07 | Participants7 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Airline | Score60.00% | Rank07 | Participants23 | Percentile72.73% | EvidenceC | Evaluated |
| BenchmarkTAU-bench Retail | Score77.50% | Rank08 | Participants25 | Percentile70.83% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot | Score61.80% | Rank11 | Participants22 | Percentile52.38% | EvidenceC | Evaluated |
| BenchmarkBFCL-v3 | Score68.70% | Rank13 | Participants20 | Percentile36.84% | EvidenceC | Evaluated |
| BenchmarkSWE-bench Multilingual | Score54.70% | Rank41 | Participants50 | Percentile18.37% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.0 | Score37.50% | Rank50 | Participants53 | Percentile5.77% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score39.33% | Rank64 | Participants96 | Percentile33.68% | EvidenceB | EvaluatedN/A |
| BenchmarkSWE-Bench Verified | Score69.60% | Rank73 | Participants120 | Percentile39.50% | EvidenceC | Evaluated |
| BenchmarkLM Arena Webdev | Score1,274.69 rating | Rank94 | Participants107 | Percentile12.26% | EvidenceA | Evaluated |
| BenchmarkAA IFBench | Score40.48% | Rank114 | Participants168 | Percentile32.34% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Factuality | Score1,400.52 rating | Rank115 | Participants131 | Percentile12.31% | EvidenceA | Evaluated |
| BenchmarkAA CritPt | Score0.00% | Rank127 | Participants200 | Percentile36.68% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score45.67% | Rank131 | Participants193 | Percentile32.29% | EvidenceB | EvaluatedN/A |
| BenchmarkLM Arena Text Style Control | Score1,387.52 rating | Rank133 | Participants218 | Percentile39.17% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,356.54 rating | Rank141 | Participants218 | Percentile35.48% | EvidenceA | Evaluated |
| BenchmarkAA GPQA Diamond | Score61.82% | Rank156 | Participants199 | Percentile21.72% | EvidenceB | EvaluatedN/A |
| BenchmarkAA Omniscience Accuracy | Score15.68% | Rank163 | Participants201 | Percentile19.00% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score4.54% | Rank166 | Participants200 | Percentile17.09% | EvidenceB | EvaluatedN/A |
Qwen3 Coder 480B A35B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext factuality | Categoryhard prompts | Rank85 | Rating / score1,453.62 | Votes1,447 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-react | Rank87 | Rating / score1,257.45 | Votes4,125 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryindustry software and it services | Rank90 | Rating / score1,464.33 | Votes310 | ObservationsN/A | Result date |
| Arenatext factuality | Categorynon english | Rank91 | Rating / score1,412.50 | Votes1,797 | ObservationsN/A | Result date |
| Arenawebdev | Categoryoverall | Rank94 | Rating / score1,274.69 | Votes12,709 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev | Rank94 | Rating / score1,274.69 | Votes12,709 | ObservationsN/A | Result date |
| Arenawebdev | Categorywebdev-html | Rank95 | Rating / score1,286.94 | Votes8,578 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank100 | Rating / score1,430.35 | Votes449 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryexclude ties | Rank111 | Rating / score1,394.90 | Votes2,403 | ObservationsN/A | Result date |
| Arenatext style control | Categorycoding | Rank111 | Rating / score1,456.88 | Votes4,806 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank113 | Rating / score1,326.77 | Votes922 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank115 | Rating / score1,400.52 | Votes3,445 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank116 | Rating / score1,310.51 | Votes922 | ObservationsN/A | Result date |
| Arenatext style control | Categorylonger query | Rank116 | Rating / score1,408.05 | Votes4,936 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank116 | Rating / score1,369.66 | Votes1,618 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank116 | Rating / score1,392.18 | Votes1,690 | ObservationsN/A | Result date |
| Arenatext | Categoryfrench | Rank117 | Rating / score1,398.01 | Votes449 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank118 | Rating / score1,412.26 | Votes4,806 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry software and it services | Rank119 | Rating / score1,436.09 | Votes8,457 | ObservationsN/A | Result date |
| Arenatext style control | Categorycreative writing | Rank120 | Rating / score1,362.35 | Votes3,237 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry legal and government | Rank121 | Rating / score1,399.58 | Votes1,559 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank121 | Rating / score1,325.08 | Votes612 | ObservationsN/A | Result date |
| Arenatext style control | Categorymulti turn | Rank121 | Rating / score1,397.13 | Votes4,250 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank121 | Rating / score1,387.23 | Votes686 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts english | Rank123 | Rating / score1,424.86 | Votes5,143 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry medicine and healthcare | Rank123 | Rating / score1,409.20 | Votes1,487 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry writing and literature and language | Rank124 | Rating / score1,366.58 | Votes5,329 | ObservationsN/A | Result date |
| Arenatext | Categorylonger query | Rank125 | Rating / score1,378.16 | Votes4,936 | ObservationsN/A | Result date |
| Arenatext style control | Categoryhard prompts | Rank125 | Rating / score1,413.76 | Votes11,532 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank125 | Rating / score1,390.28 | Votes4,380 | ObservationsN/A | Result date |
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
- 14
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| Providersubmodel | Provider model IDQwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | Regionglobal | Input / 1M$0.20 | Output / 1M$0.80 | Context262.1K | Updated |
| ProviderMerge Gateway | Provider model IDqwen/qwen3-coder-480b-a35b-instruct | Regionglobal | Input / 1M$0.22 | Output / 1M$1.8 | Context131.1K | Updated |
| ProviderVercel AI Gateway | Provider model IDalibaba/qwen3-coder | Regionglobal | Input / 1M$0.22 | Output / 1M$1.8 | Context262.1K | Updated |
| ProviderJiekou.AI | Provider model IDqwen/qwen3-coder-480b-a35b-instruct | Regionglobal | Input / 1M$0.38 | Output / 1M$1.55 | Context262.1K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDqwen3-coder-480b-a35b-instruct | Regionglobal | Input / 1M$0.38 | Output / 1M$1.55 | Context262.1K | Updated |
| ProviderAbacus | Provider model IDQwen/Qwen3-Coder-480B-A35B-Instruct | Regionglobal | Input / 1M$0.38 | Output / 1M$1.55 | Context262.1K | Updated |
| ProviderAmazon Bedrock | Provider model IDqwen.qwen3-coder-480b-a35b-v1:0 | Regionglobal | Input / 1M$0.45 | Output / 1M$1.8 | Context131.1K | Updated |
| Provider302.AI | Provider model IDqwen3-coder-480b-a35b-instruct | Regionglobal | Input / 1M$0.86 | Output / 1M$3.43 | Context262.1K | Updated |
| ProviderAlibaba (China) | Provider model IDqwen3-coder-480b-a35b-instruct | Regionglobal | Input / 1M$0.861 | Output / 1M$3.44 | Context262.1K | Updated |
| ProviderQiniu | Provider model IDqwen3-coder-480b-a35b-instruct | Regionglobal | Input / 1M$0.8696 | Output / 1M$3.48 | Context262K | Updated |
| ProviderAI/ML API | Provider model IDalibaba/qwen3-coder-480b-a35b-instruct | Regionglobal | Input / 1M$1.06 | Output / 1M$5.16 | Context262K | Updated |
| ProviderAlibaba | Provider model IDqwen3-coder-480b-a35b-instruct | Regionglobal | Input / 1M$1.5 | Output / 1M$7.5 | Context262.1K | Updated |
| ProviderHugging Face | Provider model IDQwen/Qwen3-Coder-480B-A35B-Instruct | Regionglobal | Input / 1M$2 | Output / 1M$2 | Context262.1K | Updated |
| ProviderTogether AI | Provider model IDQwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | Regionglobal | Input / 1M$2 | Output / 1M$2 | Context262.1K | Updated |
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
No 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 Specifications
Technical details for the model's default version.
- Version
- Qwen3-Coder 480B A35B Instruct
- Released
- Jan 31, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 480B
- Context window
- 262.1K
- Max output
- 262.1K
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Qwen3 Coder 480B A35B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionQwen3-Coder 480B A35B Instruct | Released | LLMBoard33.56 | Parameters480B | Context262.1K | Max output262.1K | Open weightsYes | LicenseApache 2.0 |
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 VL 30B A3B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 30B A3B
Alibaba Cloud / Qwen Team
AC
Qwen3 32B
Alibaba Cloud / Qwen Team
What is Qwen3 Coder 480B A35B?
Key information about Qwen3 Coder 480B A35B and its available data.
Qwen3-Coder-480B-A35B-Instruct is a code model from Alibaba Cloud / Qwen Team designed for agentic coding, browser use, and foundational coding tasks. It has a native 256K-token context length, extendable to 1M tokens with YaRN, and supports repository-scale understanding and specialized function calls.
Data as of 2026-10-22.
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.