Skip to content

Alibaba · Chat

Qwen3 Coder

Alibaba 🇨🇳ChatQwen familyOpen weights. One of its sources says the weights are publicly available.
From NanoGPT's listing:
Qwen 3 Coder 480B, a 480 billion total parameter model with 35B active, and 160 total experts with 8 active. Performs similar to Claude 4 Sonnet in coding benchmarks, but does so at a much lower price.
llminfo IQ
119.2
Maker's price
$3.00 blended / 1M
Max context
1M
Listings
55

Evidence and sources

International storefront (alibabacloud.com) is Singapore-incorporated; mainland operating entity 杭州阿里云智能科技有限公司 (Hangzhou).

🤗 Qwen/Qwen3-Coder-480B-A35B-Instructllminfo IQ 119.2, ranked among chat models. From 84 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 92.6, 95% interval 87–98. From 13 benchmark families across 7 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (34.9). Costs more per task than its benchmark results predict. From 13 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsTerse (39 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 2,304 output tokens per task at default effort.How the Yap score worksReleased 22 Jul 2025 Training-data cutoff, as its sources state it Maker HQ: CN (source)
All rankings: #241 on NanoGPT recentlySources: GenAI Prices data, Models.dev data, OpenRouter data docs, NanoGPT, llminfo researchPrimary data from GenAI Prices from Models.dev: name, weights availability from OpenRouter: knowledge cutoff from NanoGPT: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 2 of the 8 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputPrompt cachingBatch API

Listings

 Alibaba Cloudqwen3-coder-480b-a35b-instructSource: Models.dev data262K$1.50$7.50
 Flowdotqwen/qwen3-coder:free · freeSource: FlowDot data262K$0.00$0.00
 OpenRouterqwen/qwen3-coder:free · freeSource: Helicone Costs dataNot published by the provider$0.00$0.00
 SubmodelQwen/Qwen3-Coder-480B-A35B-Instruct-FP8 · fp8Source: Models.dev data262K$0.20$0.80
 GoogleRegions: globalvertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas · maasSource: LiteLLM data262K$0.22cache read $0.022batch $0.11$1.80batch $0.90
 Merge Gatewayqwen/qwen3-coder-480b-a35b-instructSource: Models.dev data131K$0.22$1.80
 SiliconFlowQwen/Qwen3-Coder-480B-A35B-InstructSource: Models.dev data262K$0.25$1.00
 Cometapiqwen3-coder-480b-a35b-instructSource: CometAPI Pricing dataNot published by the provider$0.30$1.20
 Hugging FaceInference by DeepInfraQwen/Qwen3-Coder-480B-A35B-InstructSource: Hugging Face Inference Providers data262K$0.30$1.00
 Kiloqwen/qwen3-coderSources: Kilo AI Gateway data, Models.dev data262K$0.30cache read $0.10$1.00

8 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

Coding

Arena ELOSource: LMArena data · Nov 2026
SWE-bench Verified10 related benchmarks · 10 results
SWE-bench Verified
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SWE-bench Multilingual
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Show 4 more resultsHide 4 results

Agentic

BFCL-v3Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Source: OpenRouter benchmark exports · Oct 2026
qwen3-coder-480b-a35b-07-25 · 90-day results
Across 5 providers lowest 35% median 41% highest 43.8%OpenRouter's automatic routing 45%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • OpenRouter's automatic routing
  • Google
  • DeepInfra
  • Venice
  • Alibaba
  • Novita

Science

GPQA Diamond6 results
Source: OpenRouter benchmark exports · Oct 2026
qwen3-coder-480b-a35b-07-25 · 90-day results
Across 5 providers lowest 60% median 60.6% highest 61.5%OpenRouter's automatic routing 60.7%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • Novita
  • Google
  • OpenRouter's automatic routing
  • DeepInfra
  • Venice
  • Alibaba

Reasoning

SpiderSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

General

Instruction following

Math

Other

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · ArtifactsBench (Tencent Hunyuan), CC BY 4.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Terminal-Bench (Laude Institute), Apache-2.0 (licence)

Also known as: alibaba/qwen3-coder, alibaba/qwen3-coder-480b-a35b-instruct, bedrock_mantle/ap-northeast-1/qwen.qwen3-coder-480b-a35b-instruct, bedrock_mantle/ap-south-1/qwen.qwen3-coder-480b-a35b-instruct, bedrock_mantle/ap-southeast-2/qwen.qwen3-coder-480b-a35b-instruct, bedrock_mantle/ap-southeast-3/qwen.qwen3-coder-480b-a35b-instruct, bedrock_mantle/eu-west-2/qwen.qwen3-coder-480b-a35b-instruct, bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct, bedrock_mantle/sa-east-1/qwen.qwen3-coder-480b-a35b-instruct, deepinfra/qwen/qwen3-coder-480b-a35b-instruct, fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct, fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-instruct-bf16, gmi/qwen/qwen3-coder-480b-a35b-instruct-fp8, novita/qwen/qwen3-coder-480b-a35b-instruct, ollama/qwen3-coder:480b-cloud, qwen/qwen3-coder, qwen/qwen3-coder-480b-a35b-instruct, qwen/qwen3-coder-480b-a35b-instruct-fp8, qwen/qwen3-coder:exacto, qwen/qwen3-coder:free, qwen3-coder-480b, qwen3-coder-480b-a35b-instruct, qwen3-coder-480b-a35b-instruct-fp8, qwen3-coder-480b-a35b-instruct:web, qwen3-coder-480b-instruct, sophnet/qwen3-coder, tensormesh/qwen/qwen3-coder-480b-a35b-instruct-fp8, together_ai/qwen/qwen3-coder-480b-a35b-instruct-fp8, vercel_ai_gateway/alibaba/qwen3-coder, vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works