Skip to content

Alibaba · Chat

Qwen3 30B A3B

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

Has 30.5 billion total parameters and 3.3 billion active parameters, using a Mixture-of-Experts (MoE) architecture to balance performance and resource requirements. It is suitable for enterprise-level applications requiring efficient processing of complex tasks, such as intelligent customer service and content generation.

llminfo IQ
114.4
Market median price
$0.215 blended / 1M
Max context
262K
Listings
47

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/Qwen3-30B-A3B-Thinking-2507-FP8llminfo IQ 114.4, ranked among chat models. From 142 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 90.3, 95% interval 80–101. From 7 benchmark families across 7 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 computedPoor value (35.8). Costs more 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 2025 Training-data cutoff, as its sources state it Maker HQ: CN (source)
All rankings: #286 on NanoGPT recentlySources: LMArena data, DeepInfra data, flex.ai API data, Models.dev data, OpenRouter data docs, CometAPI Pricing data, Hugging FacePrimary data from LMArena from DeepInfra: name from flex.ai API: hugging face id from Models.dev: weights availability from OpenRouter: knowledge cutoff 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 8 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 7 maker's prices; 3 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured output

Listings

 OpenRouterqwen/qwen3-30b-a3b:free · freeSource: Helicone Costs dataNot published by the provider$0.00$0.00
 Cloudflare Workers AIcloudflare/@cf/qwen/qwen3-30b-a3b-fp8 · fp8Sources: LiteLLM data, Models.dev data33K$0.0509$0.335
 Llmgateway Providersgreenference/qwen3-30b-a3bSource: Models.dev data8K$0.076$0.228
 Flowdotqwen/qwen3-30b-a3b-thinking-2507 · thinking, 2507Source: FlowDot data131K$0.08$0.40
 Gmicloudgmi/Qwen/Qwen3-30B-A3BSource: LiteLLM data41K$0.08$0.25
 Hugging FaceInference by Novita AIQwen/Qwen3-30B-A3BSource: GenAI Prices data41K$0.09$0.45
 Jiekouqwen/qwen3-30b-a3b-fp8 · fp8Source: Models.dev data41K$0.09$0.45
 Novita AInovita/qwen/qwen3-30b-a3b-fp8 · fp8Source: LiteLLM data41K$0.09$0.45
 Pinstripespinstripes/ps/qwen3-30b-a3bSource: LiteLLM data131K$0.09$0.20
 Llmgatewayqwen3-30b-a3bSource: LLMGateway data33K$0.095$0.285
Show all 41 listings

Showing 10 of 41: the cheapest per 1M input tokens from each provider.

Also sold by 302ai, Aihubmix, Cometapi, DeepInfra, Fastrouter, Fireworks AI, Flexai, Kilo, Merge Gateway, NanoGPT, Nebius AI Studio, Nous Portal, Qiniu, Tokenmix, Zerogpu.

6 listings without a price are hidden.

Benchmarks

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

Multilingual

IndicParam42 related benchmarks · 42 results
Show 36 more resultsHide 36 results

Human preference

Arena ELO29 related benchmarks · 31 results
Arena ELO
Source: LMArena data · Nov 2026
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
Creative Writing
Source: LMArena data · Nov 2026
English
Source: LMArena data · Nov 2026
Show 23 more resultsHide 23 results
Exclude Ties
Source: LMArena data · Nov 2026
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
Polish
Source: LMArena data · Nov 2026
Russian
Source: LMArena data · Nov 2026
Spanish
Source: LMArena data · Nov 2026
Style-Controlled
Source: LMArena data · Nov 2026

Coding

SWE-rebenchSource: SWE-rebench

Long context

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

Math

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

Science

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

General

Agentic

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

Reasoning

Instruction following

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

Knowledge

Factuality

Vision

Other

Nejumi 428 related benchmarks · 56 results
ALT_バイアス
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
ALT_倫理・道徳
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
ALT_制御性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
ALT_堅牢性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
ALT_毒性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
ALT_真実性
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
Show 44 more resultsHide 44 results
AVG_jaster_0shot
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
AVG_jaster_2shots
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_アプリケーション開発
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_コーディング
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_一般的知識
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_基礎的言語性能
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_専門的知識
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_応用的言語性能
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_情報検索
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_意味解析
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_抽象的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_推論能力
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_数学的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_構文解析
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_知識・質問応答
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_翻訳
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_表現
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_論理的推論
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
GLP_関数呼び出し
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
TOTAL_SCORE
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
アラインメント(ALT)_AVG
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled
汎用的言語性能(GLP)_AVG
Source: Nejumi Leaderboard 4 data docs
Qwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled
Qwen/Qwen3-30B-A3B: reasoning-enabled

Data credits: Data by LLM Stats · Hugging Face official benchmark leaderboards; licence varies by benchmark · LMArena, CC BY 4.0 (licence) · Arena-Hard-Auto, LMArena, Apache-2.0 (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · 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) · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · JMLE2026-Bench and IgakuQA119 by Naoto Iwase; results licence not stated (code MIT, question data CC BY 4.0). · Maheshwari et al., IndicParam, arXiv:2512.00333v3. Cited numeric scores under the owner's 2026-10-10 task-only restriction scope decision; no results licence established. Tasks, prompts and generations excluded. · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · NVIDIA RULER, Hsieh et al. Official README numeric table; no separate results licence asserted. · 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) · WebWalkerQA (Alibaba NLP), Apache-2.0 (licence)

Also known as: @cf/qwen/qwen3-30b-a3b-fp8, cloudflare/@cf/qwen/qwen3-30b-a3b-fp8, dashscope/qwen3-30b-a3b, deepinfra/qwen/qwen3-30b-a3b, fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b, fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b-thinking-2507, gmi/qwen/qwen3-30b-a3b, greenference/qwen3-30b-a3b, nebius/qwen/qwen3-30b-a3b, novita/qwen/qwen3-30b-a3b-fp8, pinstripes/ps/qwen3-30b-a3b, qwen/qwen3-30b-a3b, qwen/qwen3-30b-a3b-2507, qwen/qwen3-30b-a3b-fp8, qwen/qwen3-30b-a3b-thinking-2507, qwen/qwen3-30b-a3b:free, qwen3-30b-a3b-fp8, qwen3-30b-a3b-thinking-2507, qwen3-30b-a3b-thinking-2507-fp8, qwen_ai_platform/qwen3-30b-a3b, qwencloud/qwen3-30b-a3b, sophnet/qwen3-30b-a3b-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