Skip to content

Alibaba · Chat

Qwen 3 235B A22B

Alibaba 🇨🇳ChatQwen familyOpen weights. One of its sources says the weights are publicly available.

Qwen3-235B-A22B is the flagship model of the Qwen3 series, with **235B total parameters and 22B activated parameters**, using a Mixture of Experts (MoE) architecture. - Particularly suitable for complex tasks requiring high-performance Inference, such as coding, mathematics, and Multimodal applications.

llminfo IQ
119.3
Maker's price
$1.225 blended / 1M
Max context
262K
Listings
22

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/Qwen3-235B-A22Bllminfo IQ 119.3, ranked among chat models. From 185 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 86.4, 95% interval 75–98. From 10 benchmark families across 9 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 computedGood value (53.2). Cheaper per task than its benchmark results predict. From 17 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksReleased 27 Apr 2025Maker HQ: CN (source)
Sources: LMArena data, Models.dev data, CometAPI Pricing data, Hugging FacePrimary data from LMArena from Models.dev: name, weights availability from CometAPI Pricing: description from Hugging Face: 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. 3 of the 9 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, 06:07 UTC.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured output

Listings

 Alibaba Cloudqwen3-235b-a22bSource: Models.dev data131K$0.70$2.80
 Flowdotqwen/qwen3-235b-a22b:free · freeSource: FlowDot data131K$0.00$0.00
 OpenRouterqwen/qwen3-235b-a22b:free · freeSource: Helicone Costs dataNot published by the provider$0.00$0.00
 Gmicloudgmi/Qwen/Qwen3-235B-A22B-FP8 · fp8Source: LiteLLM data33K$0.17$1.09
 DeepInfradeepinfra/Qwen/Qwen3-235B-A22BSource: LiteLLM data41K$0.18$0.54
 302aiqwen/qwen3-235b-a22b-fp8 · fp8Source: 302.ai data41K$0.20$0.80
 Hugging FaceQwen/Qwen3-235B-A22BSource: Models.dev data41K$0.20$0.80
 RequestyInference by DeepInfradeepinfra/Qwen/Qwen3-235B-A22BSource: Requesty data41K$0.20$0.60
 Jiekouqwen/qwen3-235b-a22b-fp8 · fp8Source: Models.dev data41K$0.20$0.80
 Nebius AI Studionebius/Qwen/Qwen3-235B-A22BSource: LiteLLM data262K$0.20$0.60
Show all 22 listings

Showing 10 of 22: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Alibaba Cloud (China), Cometapi, Fireworks AI, Hyperbolic, Merge Gateway, Novita AI, Qiniu.

Benchmarks

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

Human preference

Arena ELO29 related benchmarks · 84 results
Arena ELO
Source: LMArena data · Nov 2026
Setting not reported
Arena Hard
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Arena-Hard-v2.0-Preview
Source: Arena-Hard-Auto data
Creative Writing, Ensemble GPT-4.1 and Gemini 2.5 as Judges (Best Configuration for Creative Writing)
Hard Prompt, Style Control, and Gemini-2.5 as Judge (Official Configuration)
Hard Prompt, Style Control, and GPT-4.1 as Judge (If prefer OpenAI API)
Chinese
Source: LMArena data · Nov 2026
Setting not reported
Creative Writing
Source: LMArena data · Nov 2026
Setting not reported
English
Source: LMArena data · Nov 2026
Setting not reported
Show 68 more resultsHide 68 results
Exclude Ties
Source: LMArena data · Nov 2026
Setting not reported
Expert
Source: LMArena data · Nov 2026
Setting not reported
French
Source: LMArena data · Nov 2026
Setting not stated
German
Source: LMArena data · Nov 2026
Setting not reported
Hard Prompts
Source: LMArena data · Nov 2026
Setting not reported
Hard Prompts English
Source: LMArena data · Nov 2026
Setting not reported
Industry Business and Management and Financial Operations
Source: LMArena data · Nov 2026
Setting not reported
Industry Entertainment and Sports and Media
Source: LMArena data · Nov 2026
Setting not reported
Industry Life and Physical and Social Science
Source: LMArena data · Nov 2026
Setting not reported
Industry Mathematical
Source: LMArena data · Nov 2026
Setting not reported
Industry Medicine and Healthcare
Source: LMArena data · Nov 2026
Setting not reported
Industry Software and It Services
Source: LMArena data · Nov 2026
Setting not reported
Industry Writing and Literature and Language
Source: LMArena data · Nov 2026
Setting not reported
Japanese
Source: LMArena data · Nov 2026
Setting not reported
Korean
Source: LMArena data · Nov 2026
Setting not reported
Longer Query
Source: LMArena data · Nov 2026
Setting not reported
Multi Turn
Source: LMArena data · Nov 2026
Setting not reported
Non English
Source: LMArena data · Nov 2026
Setting not reported
Polish
Source: LMArena data · Nov 2026
Setting not reported
Russian
Source: LMArena data · Nov 2026
Setting not reported
Spanish
Source: LMArena data · Nov 2026
Setting not reported
Style-Controlled
Source: LMArena data · Nov 2026
Setting not reported

Coding

AiderSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
EvalplusSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
LiveCodeBench8 related benchmarks · 9 results
LiveCodeBench
Source: LiveCodeBench Leaderboard data
Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Setting not stated
AtCoder
Source: LiveCodeBench Leaderboard data
Codeforces
Source: LiveCodeBench Leaderboard data
platform:codeforces
Easy
Source: LiveCodeBench Leaderboard data
Hard
Source: LiveCodeBench Leaderboard data
LeetCode
Source: LiveCodeBench Leaderboard data
Show 2 more resultsHide 2 results
Medium
Source: LiveCodeBench Leaderboard data
Pro
Source: LiveCodeBench Pro data · May 2025
MBPPSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SWE-rebenchSource: SWE-rebench

Multilingual

LaoBench16 related benchmarks · 16 results
Show 10 more resultsHide 10 results
MMMLUSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Math

AIME 2024Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
AIME 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GSM8KSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
LiveBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MATHSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MathArenaSource: MathArena data
MGSMSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
ValsSource: Vals AI

Long context

RULERSource: RULER official results data · Reported by the model's developer. The source relaying it did not verify it.

General

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

Science

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

Agentic

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

Reasoning

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

Factuality

Instruction following

Vision

Other

CRUX-OSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Nejumi 428 related benchmarks · 28 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_表現
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B: reasoning-enabled

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · Arena-Hard-Auto, LMArena, Apache-2.0 (licence) · ArtifactsBench (Tencent Hunyuan), CC BY 4.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · Lin et al., CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks, arXiv:2604.19262v1, CC BY 4.0. Table 2 scores extracted without change. (licence) · CyberGym leaderboard (Wang, Shi, He, Cai, Zhang, Song; UC Berkeley), ICLR 2026. Results evaluated and submitted by the listed teams. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only. · JMLE2026-Bench and IgakuQA119 by Naoto Iwase; results licence not stated (code MIT, question data CC BY 4.0). · 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. · LiveMCPBench leaderboard, ICIP-CAS (Mo et al., 2025). Sheet linked from the Apache-2.0 project README; sheet licence not separately stated. · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · Hugging Face official benchmark leaderboards; licence varies by benchmark · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · pfgen-bench, Preferred Networks. Apache-2.0 except LLM-generated outputs; aggregate scores only. (licence) · NVIDIA RULER, Hsieh et al. Official README numeric table; no separate results licence asserted. · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Vectara Hallucination Leaderboard, Apache-2.0 (licence)

Around the web

Also known as: deepinfra/qwen/qwen3-235b-a22b, fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b, gmi/qwen/qwen3-235b-a22b-fp8, hyperbolic/qwen/qwen3-235b-a22b, nebius/qwen/qwen3-235b-a22b, novita/qwen/qwen3-235b-a22b-fp8, qwen/qwen3-235b-a22b, qwen/qwen3-235b-a22b-fp8, qwen/qwen3-235b-a22b:free, qwen3-235b-a22b-non-thinking, qwen3-235b-a22b-thinking, sophnet/qwen3-235b-a22b

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