Skip to content

Alibaba · Chat

Qwen 3.8 Flash Next

Alibaba 🇨🇳ChatQwen familyOpen weights. One of its sources says the weights are publicly available.
llminfo IQ
136.7
Market median price
$0.23 blended / 1M
Max context
1M
Listings
11

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/Qwen3.8-Flash-Next-FP8llminfo IQ 136.7, ranked among chat models. From 73 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 116.0, 95% interval 99–133. From 10 benchmark families across 3 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 computedReleased 26 Aug 2026Maker HQ: CN (source)
Sources: LMArena data, Apertus LLM Hosting, flex.ai API data, Models.dev data, llminfo researchPrimary data from LMArena from Apertus LLM Hosting: name from flex.ai API: hugging face id 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

Advantages

Open weights available

The weights are public. 4 of the 9 peers that say either way have open weights.

Trade-offs

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 9 maker's prices; 1 market median price.

Input & output

as stated by the model's providers
Text
Images
Video
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt caching

Listings

 Hugging FaceInference by NscaleQwen/Qwen3.8-Flash-Next-FP8 · fp8Source: Hugging Face Inference Providers data1M$0.15$0.47
 Aipgqwen38-flash-next-nvfp4 · nvfp4Source: Models.dev data40K$0.075$0.30
 Apertusqwen3.8-flash-nextSource: Apertus LLM HostingNot published by the provider
 Darkbloomqwen3.8-flash-nextSource: Darkbloom data docsNot published by the provider$0.13cache read $0.065$0.40
 Featherless AIQwen/Qwen3.8-Flash-NextSource: Featherless data262K$0.15$0.50
 FlexaiRegions: 🇪🇺 euQwen3.8-Flash-NextSources: flex.ai API data, flex.ai Pricing262K$0.15cache read $0.0225$0.47
 Qiniuqwen/qwen3.8-flash-nextSources: Qiniu AI data, Qiniu AI Model Plaza Pricing1M
 Tensorxqwen/qwen3.8-flash-nextSource: Models.dev data262K$0.20cache read $0.05$0.50
 Vultrqwen3.8-flash-nextSources: Models.dev data, Vultr Serverless Inference data262K$0.10$0.20

2 listings without a price are hidden.

Benchmarks

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

Agentic

Agents' Last Exam3 related benchmarks · 3 results
Agents' Last Exam
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Overall Score
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · Overall Score
Pass Rate
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · Pass@1
AndroidWorld2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Arena AgentSource: LMArena data
JobBench2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
OSWorld4 related benchmarks · 4 results
2.0 · Binary
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · binary full-task reward
2.0 · Partial
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · aggregate partial reward
OSWorld 2.0
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SWE-Bench Pro2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · Claude Code · temp 1.0 · top_p 0.95 · 256K · corrected/refined tasks
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

General

Coding

Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
NL2RepoSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · mini-SWE-agent · temp 1.0 · top_p 0.95 · 256K
Source: Hugging Face Official Benchmarks data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Vision2Web2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · frontend/webpage/website average · Claude Code · gpt-5.4-2026-03-05 judge
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Reasoning

CoWorkBench2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
ERQA2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · GPT-4o judge
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
Toolathlon VerifiedQwen3.8-Flash-Next release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Multilingual

Vision

CharXiv-R3 related benchmarks · 3 results
CharXiv-R
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
CharXiv (RQ) · With CI
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · with Code Interpreter
CharXiv (RQ) · Without CI
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · without Code Interpreter
LVBench2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
RealWorldQA2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Math

MathVision3 related benchmarks · 3 results
MathVision
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
With CI
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · with Code Interpreter
Without CI
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · without Code Interpreter

Instruction following

IFBench2 results
Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
Qwen3.8-Flash-Next release/model card · published setting
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA DiamondQwen3.8-Flash-Next release/model card · published setting · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.

Other

ClawEval-MM · AverageQwen3.8-Flash-Next release/model card · mean score across three trials · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
ClawEval-MM · Pass@3Qwen3.8-Flash-Next release/model card · Pass@3 · at least one pass in three trials · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
DeepSWE v1.1Qwen3.8-Flash-Next release/model card · best of Claude Code and mini-SWE-agent · temp 1.0 · top_p 0.95 · 256K · Reported by Qwen · via BenchBoard docs · Reported by the model's developer. The source relaying it did not verify it.
NL2Repo-BenchQwen3.8-Flash-Next release/model card · Claude Code · repository-download commands disabled · Reported by 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. · Data by LLM Stats · SEA-HELM leaderboard, AI Singapore (AI Products team), National University of Singapore. Published aggregate scores; results licence not stated (SEA-HELM code is MIT). · LMArena, CC BY 4.0 (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · Steel.dev Agent Leaderboards, MIT (licence)

Also known as: qwen/qwen3.8-flash-next, qwen/qwen3.8-flash-next-fp8, qwen3-8-flash-next, qwen3.8-flash-next@eu, qwen38-flash-next, qwen38-flash-next-nvfp4

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