Skip to content

Alibaba · Chat

Qwen3 Next 80B A3B Instruct

Alibaba 🇨🇳ChatQwen familyOpen weights. One of its sources says the weights are publicly available.The maker lists this model as deprecated (2 Apr 2026).
From Aiml API's listing:
Alibaba's Qwen 3 Next 80B A3B Instruct is a multilingual model with enhanced instruction-following capabilities.
llminfo IQ
118.1
Max context
262K
Listings
46

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-Next-80B-A3B-Instructllminfo IQ 118.1, ranked among chat models. From 154 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 91.7, 95% interval 81–102. From 7 benchmark families across 5 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedFair value (47.6). Costs per task about what its benchmark results predict. From 5 benchmarks with measured task costs. A fair amount of data behind it.How Value for money worksReleased 10 Sep 2025 Training-data cutoff, as its sources state it Maker HQ: CN (source)
All rankings: #42 on NanoGPT recentlySources: LMArena data, DeepInfra data, LiteLLM data, Models.dev data, AI/ML API data, OpenRouter data docs, llminfo researchPrimary data from LMArena from DeepInfra: name from LiteLLM: deprecation date from Models.dev: weights availability from AI/ML API: primary mode, description from OpenRouter: knowledge cutoff from llminfo research: release date

Advantages and trade-offs

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

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (2 Apr 2026).

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 maker's prices; 1 market median price.

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 Clouddashscope/qwen3-next-80b-a3b-instructSources: LiteLLM data, Models.dev data262K$0.15$1.20——
 Flowdotqwen/qwen3-next-80b-a3b-instruct:free · freeSource: FlowDot data262K$0.00$0.00——
 OpenRouterInference by DeepInfraqwen/qwen3-next-80b-a3b-instruct · fp8/flex · fp8Source: OpenRouter data docs262K$0.072$0.88791,131ms
 Eden AIInference by DeepInfradeepinfra/Qwen/Qwen3-Next-80B-A3B-InstructSource: Models.dev data262K$0.09$1.10——
 Fastrouterqwen/qwen3-next-80b-a3b-instructSource: FastRouter data262K$0.09$1.10——
 Hugging FaceInference by DeepInfraQwen/Qwen3-Next-80B-A3B-InstructSource: Hugging Face Inference Providers data262K$0.09$1.10——
 NanoGPTqwen/qwen3-next-80b-a3b-instructSources: Models.dev data, NanoGPT262K$0.09cache read $0.045$1.10——
 Vercelalibaba/qwen3-next-80b-a3b-instructSources: Models.dev data, Vercel AI Gateway data262K$0.09$1.10——
 DeepInfraQwen/Qwen3-Next-80B-A3B-Instruct · fp8Sources: DeepInfra data, LiteLLM data, Models.dev data262K$0.09$1.10——
 IonetQwen/Qwen3-Next-80B-A3B-InstructSources: IO Intelligence (io.net) data, Models.dev data262K$0.0993cache read $0.0496$1.18250.001252.273ms
Show all 42 listings

Showing 10 of 42: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by 302ai, Aimlapi, Alibaba Cloud (China), Amazon Web Services, Databricks, Fireworks AI, Gmicloud, Google, Jalapeno, Jiekou, Kilo, Merge Gateway, Neon, Nous Portal, Novita AI, Parasail, Qiniu, Together AI.

4 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

Arena ELO42 related benchmarks · 42 results
Arena ELO
Source: LMArena data · Nov 2026
Arena-Hard v2
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Chinese
Source: LMArena data · Nov 2026
Creative Writing
Source: LMArena data · Nov 2026
English
Source: LMArena data · Nov 2026
Exclude Ties
Source: LMArena data · Nov 2026
Show 36 more resultsHide 36 results
Expert
Source: LMArena data · Nov 2026
French
Source: LMArena data · Nov 2026
German
Source: LMArena data · Nov 2026
Hard Prompts
Source: LMArena data · Nov 2026
Hard Prompts English
Source: LMArena data · Nov 2026
Industry Mathematical
Source: LMArena data · Nov 2026
Japanese
Source: LMArena data · Nov 2026
Korean
Source: LMArena data · Nov 2026
Longer Query
Source: LMArena data · Nov 2026
Multi Turn
Source: LMArena data · Nov 2026
Non English
Source: LMArena data · Nov 2026

Agentic

BFCL-v3Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GAIA8 results
Source: GAIA Leaderboard data
Difficulty level
Difficulty not reported
Level 1, Vertex AI MaaS
Level 2, Vertex AI MaaS
Level 3, Vertex AI MaaS
Tau2 Retail4 related benchmarks · 9 results
Tau2 Retail
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Tau2 Airline
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Tau2 Telecom
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
tau2-bench airline
Source: OpenRouter benchmark exports · Oct 2026
qwen3-next-80b-a3b-instruct-2509 · 90-day results
Across 5 providers lowest 42.3% median 46.8% highest 47.1%OpenRouter's automatic routing 46.7%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • DeepInfra
  • Google
  • Parasail
  • OpenRouter's automatic routing
  • Novita
  • Alibaba

Multilingual

LaoBench16 related benchmarks · 16 results
Show 10 more resultsHide 10 results

Coding

SWE-rebenchSource: SWE-rebench

Long context

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond6 results
Source: OpenRouter benchmark exports · Oct 2026
qwen3-next-80b-a3b-instruct-2509 · 90-day results
Across 5 providers lowest 70.5% median 71.7% highest 72.8%OpenRouter's automatic routing 72%
Show results from 5 providers and OpenRouter's automatic routingHide results from 5 providers and OpenRouter's automatic routing
  • Parasail
  • Google
  • OpenRouter's automatic routing
  • Alibaba
  • Novita
  • DeepInfra
SuperGPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Knowledge

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

Math

AIME 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
HMMT25Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
PolyMATHSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Instruction following

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

Reasoning

General

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

Other

Nejumi 428 related benchmarks · 28 results

Data credits: Data by LLM Stats · LMArena, CC BY 4.0 (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · LaoBench, BAAI et al., arXiv:2511.11334v3. Cited numeric results only. arXiv non-exclusive distribution notice establishes no results reuse grant; dataset Apache licence is not a results grant. · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Swallow LLM Leaderboard v2, Swallow LLM team (Institute of Science Tokyo). Contents CC BY 4.0; Japanese post-trained task scores on the source's 0..1 scale. (licence)

Also known as: alibaba/qwen3-next-80b-a3b-instruct, bedrock_mantle/ap-northeast-1/qwen.qwen3-next-80b-a3b-instruct, bedrock_mantle/ap-south-1/qwen.qwen3-next-80b-a3b-instruct, bedrock_mantle/ap-southeast-2/qwen.qwen3-next-80b-a3b-instruct, bedrock_mantle/ap-southeast-3/qwen.qwen3-next-80b-a3b-instruct, bedrock_mantle/eu-central-1/qwen.qwen3-next-80b-a3b-instruct, bedrock_mantle/eu-north-1/qwen.qwen3-next-80b-a3b-instruct, bedrock_mantle/eu-south-1/qwen.qwen3-next-80b-a3b-instruct, bedrock_mantle/eu-west-1/qwen.qwen3-next-80b-a3b-instruct, bedrock_mantle/eu-west-2/qwen.qwen3-next-80b-a3b-instruct, bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct, bedrock_mantle/sa-east-1/qwen.qwen3-next-80b-a3b-instruct, dashscope/qwen3-next-80b-a3b-instruct, databricks/databricks-qwen3-next-80b-a3b-instruct, databricks/databricks-qwen3-next-80b-a3b-instruct@eu, deepinfra/qwen/qwen3-next-80b-a3b-instruct, fireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct, gmi/qwen/qwen3-next-80b-a3b-instruct, novita/qwen/qwen3-next-80b-a3b-instruct, parasail-qwen-3-next-80b-instruct, qwen/qwen3-next-80b-a3b-instruct, qwen/qwen3-next-80b-a3b-instruct-fp8, qwen/qwen3-next-80b-a3b-instruct:free, qwen_ai_platform/qwen3-next-80b-a3b-instruct, qwencloud/qwen3-next-80b-a3b-instruct, sophnet/qwen3-next-80b-a3b-instruct, together_ai/qwen/qwen3-next-80b-a3b-instruct, vertex_ai/qwen/qwen3-next-80b-a3b-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