Skip to content

Alibaba · Chat

Qwen3.6 Flash

Alibaba 🇨🇳ChatQwen familyOne of its sources says the weights aren't publicly available.

Newer version: Qwen3.8 Flash. We compared release dates and version names in our catalogue.

From Empiriolabs's listing:
Fast Qwen3.6 vision-language model for agentic coding, math reasoning, spatial understanding, OCR, and text, image, and video input.
llminfo IQ
121.9
Max context
1M
Listings
29

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).

llminfo IQ 121.9, ranked among chat models. From 108 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 100.2, 95% interval 88–112. From 10 benchmark families across 4 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 (36.3). Costs more per task than its benchmark results predict. From 4 benchmarks with measured task costs. A fair amount of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsChatty (60 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 23,209 output tokens per task at default effort.How the Yap score worksReleased 27 Apr 2026Maker HQ: CN (source)
All rankings: #213 on OpenRouter today #215 on OpenRouter this week #219 on OpenRouter this month #412 on NanoGPT recentlySources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, EmpirioLabs data, Models.dev data, llminfo researchPrimary data from Alibaba Cloud Model Studio (DashScope) Multi-Region API from EmpirioLabs: name, primary mode, description from Models.dev: weights availability from llminfo research: release date

Advantages and trade-offs

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

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

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
Images
Video
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingWeb searchBatch API

Listings

 Alibaba CloudRegions: 🇯🇵🇸🇬+4 ap-northeast-1, ap-southeast-1, cn-beijing, cn-hongkong, eu-central-1, us-east-1qwen3.6-flashSources: Alibaba Cloud Model Studio (DashScope) Multi-Region API, Alibaba Cloud Qwen, Models.dev data1M$0.25cache read $0.025$1.50cache write $0.3125——
 Alibaba Cloud (China)qwen3.6-flashSource: Models.dev data1M$0.165cache read $0.0165$0.99cache write $0.2063——
 Empiriolabsqwen3-6-flash:variant1 · variant1Source: EmpirioLabs data984K$0.165$0.99——
 Merge Gatewayqwen/qwen3.6-flashSource: Models.dev data1M$0.165cache read $0.033$0.99cache write $0.2063——
 NetmindQwen/Qwen3.6-FlashSource: NetMind.AI1M$0.167cache read $0.0334$1.00——
 Aihubmixqwen3.6-flashSource: AIHubMix data docs1M$0.169cache read $0.0169$1.014cache write $0.2113——
 MoarkQwen3.6-FlashSource: Models.dev data1M$0.18$1.03——
 Kiloqwen/qwen3.6-flashSources: Kilo AI Gateway data, Models.dev data1M$0.1875$1.125cache write $0.2344——
 Nous Portalqwen/qwen3.6-flashSource: Nous Portal Inference Gateway data1M$0.1875$1.125cache write $0.2344——
 OpenRouterInference by Alibaba Cloudqwen/qwen3.6-flashSource: OpenRouter data docs984K$0.1875$1.125cache write $0.234474579ms
Show all 25 listings

Showing 10 of 25: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by 302ai, Crossmodel, Impossibl, Llmgateway, Llmgateway Providers, Llmtr, NanoGPT, Ofox, Orcarouter, Wavespeed, Zenmux.

4 listings without a price are hidden.

Benchmarks

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

Vision

CharXiv · RQQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
EmbSpatialBenchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
HallusionBenchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
LVBenchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMBenchEN-DEV-v1.1Qwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · DEV v1.1 · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMMUQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMMU-ProQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MVBenchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
RealWorldQAQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
RefCOCO(avg)Qwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
RefSpatialBenchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SimpleVQAQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Video-MMEQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
VideoMMMUQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
VITA-BenchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Reasoning

C-EvalQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepPlanningQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Humanity's Last ExamQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Toolathlon VerifiedQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
WideSearchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ZEROBench-SubQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Coding

LiveCodeBench v6Qwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
QwenWebBenchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SWE-bench VerifiedQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Math

HMMTReported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
IMOAnswerBenchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MathVista-MiniQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Long context

Agentic

MCP AtlasQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
SWE-Bench ProQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
TAU3-BenchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

General

Science

SuperGPQAQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Knowledge

MMLU-ProQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
MMLU-ReduxQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Factuality

Human preference

Instruction following

OCR

CC-OCRQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Other

AI2D_TESTQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
AIME26Qwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claw-Eval · AverageQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Claw-Eval · Pass³Qwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Horangi36 related benchmarks · 36 results
MLVU(M-Avg)Qwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
NL2Repo-BenchQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ODInW13Qwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash · Reported by Alibaba Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence)

Around the web

Also known as: alibaba/qwen3.6-flash, bailian/qwen3.6-flash, empiriolabs/qwen3-6-flash, qwen/qwen3.6-flash, qwen3-6-flash, qwen3.6-flash-2026-04-16

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