Skip to content

Alibaba · Chat

Qwen 3 235B A22B Thinking 2507

Alibaba 🇨🇳ChatQwen familyOpen weights. One of its sources says the weights are publicly available.
From Venice's listing:
Reasons step by step before it answers. Built for in-depth research and handling long, complex documents. Ideal for technical work and high-precision tasks.
llminfo IQ
124.3
Market median price
$0.9711 blended / 1M
Max context
262K
Listings
31

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-A22B-Thinking-2507 Model architecture, as its sources state it llminfo IQ 124.3, ranked among chat models. From 161 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 99.6, 95% interval 91–108. From 8 benchmark families across 8 sources. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old.How Coding IQ is computedPoor value (40.6). 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 worksReleased 25 Jul 2025 Training-data cutoff, as its sources state it Maker HQ: CN (source)
All rankings: #303 on OpenRouter this week #357 on OpenRouter this month #362 on NanoGPT recently #414 on OpenRouter todaySources: Qiniu AI data, Venice.ai data, Models.dev data, AI/ML API data, Morpheus Inference Marketplace data, OpenRouter data docs, llminfo researchPrimary data from Qiniu AI from Venice.ai: name, description from Models.dev: weights availability from AI/ML API: primary mode from Morpheus Inference Marketplace: architecture from OpenRouter: knowledge cutoff 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 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
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputWeb search

Listings

 IonetQwen/Qwen3-235B-A22B-Thinking-2507Source: Models.dev data262K$0.11cache read $0.055$0.60cache write $0.22
 Flowdotqwen/qwen3-235b-a22b-thinking-2507Source: FlowDot data262K$0.13$0.60
 Hugging FaceInference by Nebius AI StudioQwen/Qwen3-235B-A22B-Thinking-2507Source: GenAI Prices data262K$0.20$0.80
 SubmodelQwen/Qwen3-235B-A22B-Thinking-2507Source: Models.dev data262K$0.20$0.60
 Fireworks AIfireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507Source: LiteLLM data262K$0.22$0.88
 Eden AIInference by DeepInfradeepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507Source: Models.dev data262K$0.23cache read $0.20$2.30
 RequestyInference by DeepInfradeepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507Source: Requesty data262K$0.23cache read $0.20$2.30
 Aihubmixqwen3-235b-a22b-thinking-2507Source: AIHubMix data docs262K$0.28$2.80
 Openroute Cnqwen3-235b-a22b-thinking-2507Source: OpenRoute CN Marketplace262K
 Qiniuqwen3-235b-a22b-thinking-2507Sources: Models.dev data, Qiniu AI data, Qiniu AI Model Plaza Pricing262K
Show all 26 listings

Showing 10 of 26: the cheapest per 1M input tokens from each provider.

Also sold by 302ai, DeepInfra, Gmicloud, Jiekou, Kilo, NanoGPT, Nous Portal, Novita AI, OpenRouter, Venice.

5 listings without a price are hidden.

Benchmarks

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

Coding

CFEvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
SWE-rebenchSource: SWE-rebench

Agentic

BFCL-v3Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Tau2Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Long context

General

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

Human preference

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

Reasoning

OJBenchSource: 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

Vision

Multilingual

Factuality

Other

Horangi36 related benchmarks · 36 results
Nejumi 428 related benchmarks · 28 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
Show 22 more resultsHide 22 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_表現
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled

Data credits: Data by LLM Stats · ArtifactsBench (Tencent Hunyuan), CC BY 4.0 (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Galileo Agent Leaderboard, Apache-2.0 (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · Hugging Face official benchmark leaderboards; licence varies by benchmark · 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/qwen3-235b-a22b-thinking-2507, deepinfra/qwen/qwen3-235b-a22b-thinking-2507, fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507, gmi/qwen/qwen3-235b-a22b-thinking-2507-fp8, novita/qwen/qwen3-235b-a22b-thinking-2507, qwen 3 235b a22b thinking 2507, qwen-3-235b-a22b-thinking-2507, qwen/qwen3-235b-a22b-thinking-2507

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