Skip to content

Alibaba · Chat

Qwen 2.5 14B Instruct

Alibaba 🇨🇳ChatQwen familyThe maker lists this model as deprecated (29 Jul 2026).

Open Source Qianwen 14B

llminfo IQ
104.8
Market median price
$0.20 blended / 1M
Max context
33K
Listings
5

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/Qwen2.5-14B-Instructllminfo IQ 104.8, ranked among chat models. From 147 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 75.7, 95% interval 65–86. From 5 benchmark families across 3 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 computedReleased 16 Sep 2024Maker HQ: CN (source)
Sources: Together AI data, LiteLLM data, 302.ai data, Hugging FacePrimary data from Together AI from LiteLLM: deprecation date from 302.ai: description from Hugging Face: release date

Advantages and trade-offs

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

Trade-offs

Deprecated by its maker

The maker has already deprecated this model (29 Jul 2026).

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

Listings

 302aiQwen/Qwen2.5-14B-InstructSource: 302.ai data32K$0.10$0.10
 Aihubmixqwen2.5-14b-instructSource: AIHubMix data docsNot published by the provider$0.40$1.20
 Fireworks AIfireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instructSource: LiteLLM data33K$0.20$0.20
 Together AIQwen/Qwen2.5-14B-InstructSources: LiteLLM data, Together AI data33K$0.80$0.80

1 listing without a price is hidden.

Benchmarks

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

Coding

CodeElo28 related benchmarks · 28 results
HumanEvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MBPPSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MBPP+Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Knowledge

INCLUDE-base-44 0-shot32 related benchmarks · 32 results

Multilingual

General

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

Instruction following

Factuality

Math

GSM8KSource: 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

Reasoning

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

Agentic

Science

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

Other

Data credits: Data by LLM Stats · ArtifactsBench (Tencent Hunyuan), CC BY 4.0 (licence) · CodeElo (Qwen). Aggregate scores from the official results file; no results licence asserted. The evaluation scaffold agreement is not presented as a licence for these scores · EvalPlus Leaderboard and EvalPerf (evalplus.github.io), Apache-2.0; EvalPerf win-rate fractions converted to percentages (licence) · FaithJudge, Vectara; Tamber et al., EMNLP 2025 Industry. Public numeric README leaderboard; results licence not separately established. · Speakleash community evaluation of INCLUDE-base-44 (Romanou et al., arXiv:2411.19799). Public results.csv; no results licence stated. · Vasselli, Martínez Peguero, Hudi, Sakajo and Watanabe. Measuring Linguistic Competence of LLMs on Indigenous Languages of the Americas. EACL 2026, ©2026 ACL, CC BY 4.0. Numeric/protocol extract from Tables 1–4; random reference rows omitted. (licence) · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · M-IFEval: Dussolle, Cardeña Díaz, Sato and Devine (Lightblue), arXiv:2502.04688. README leaderboard, repository licensed Apache-2.0. (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Open Arabic LLM Leaderboard (OALL), Apache-2.0 (licence) · OpenLLM French Leaderboard (le-leadboard), Mohamad Alhajar and Alexandre Lavallée; publisher-normalized public result files; results licence not stated (the Space's Apache-2.0 covers code) · pfgen-bench, Preferred Networks. Apache-2.0 except LLM-generated outputs; aggregate scores only. (licence) · SeaExam and SeaBench leaderboard, SeaLLMs (DAMO-NLP-SG). Published leaderboard scores; results licence not stated. · WebWalkerQA (Alibaba NLP), Apache-2.0 (licence)

Around the web

  • Alibaba introduces Qwen 2.5-Max AI model, claims edge over DeepSeek – Computerworld
    Topics Latest Newsletters Resources Buyer’s Guides Events Editions Search Menu Home Artificial Intelligence Generative AI …Topics Latest Newsletters Resources Buyer’s Guides Events Editions Search Menu Home Artificial Intelligence Generative AI by Prasanth Aby Thomas Alibaba introduces Qwen 2.5-Max AI model, claims edge …

    computerworld.com

  • [PDF] Fine-Tuning Qwen 2.5 3B for Realistic Movie Dialogue Generation
    Fine-Tuning Qwen 2.5 3B for Realistic Movie Dialogue Generation Results demonstrate the ability of small …Fine-Tuning Qwen 2.5 3B for Realistic Movie Dialogue Generation Results demonstrate the ability of small models to produce high-quality, realistic dialogue, offering a promising approach for real-tim…

    arxiv.org

  • In-Depth Exploration of Alibaba’s Qwen 2.5 Series - Alibaba Cloud Community
    Community Blog Events Webinars Tutorials Forum Blog Events Webinars Tutorials Forum Create Account Log In …Community Blog Events Webinars Tutorials Forum Blog Events Webinars Tutorials Forum Create Account Log In × Community Blog In-Depth Exploration of Alibaba’s Qwen 2.5 Series In-Depth Exploration of Al…

    alibabacloud.com

  • Alibaba Enters the AI Arms Race with Qwen 2.5 | AI-Pro.org
    Alibaba Cloud heats up the AI race with Qwen 2.5 China’s AI race is gaining …Alibaba Cloud heats up the AI race with Qwen 2.5 China’s AI race is gaining momentum, and Alibaba Cloud’s latest breakthrough, Qwen 2.5, is a testament to its rapid advancements. As artificial intell…

    ai-pro.org

  • What Is Ali Baba’s Qwen 2.5 AI Model, And How Does It Stacks Up?
    By Tor Constantino, MBA , Contributor. Forbes contributors publish independent expert analyses and insights. Tor …By Tor Constantino, MBA , Contributor. Forbes contributors publish independent expert analyses and insights. Tor Constantino is an ex-reporter, turned AI consultant & tech writer. Follow Author Jan 2…

    forbes.com

  • Qwen 2.5: The Future of Coding and AI Integration
    You can explore the capabilities of Qwen 2.5 directly on EdgeAI Chat , a platform …You can explore the capabilities of Qwen 2.5 directly on EdgeAI Chat , a platform designed for secure and versatile AI interactions. One of the featured models, Qwen2.5-Coder-32B , is available for f…

    autonomous.ai

  • Qwen 2.5 32B | Open Laboratory
    Qwen ReadTheDocs Documentation Qwen Team Blog Qwen Team GitHub Qwen Hugging Face Profile Qwen2.5 Blog …Qwen ReadTheDocs Documentation Qwen Team Blog Qwen Team GitHub Qwen Hugging Face Profile Qwen2.5 Blog Post Qwen2.5-32B Model Card Qwen2.5 GitHub Repository Qwen Agent Framework Qwen2.5 Evaluation Rep…

    openlaboratory.com

  • Unlocking the Future of AI with Qwen 2.5 VL: Where Vision Meets Language - Alibaba Cloud Community
    Community Blog Events Webinars Tutorials Forum Blog Events Webinars Tutorials Forum Create Account Log In …Community Blog Events Webinars Tutorials Forum Blog Events Webinars Tutorials Forum Create Account Log In × Community Blog Unlocking the Future of AI with Qwen 2.5 VL: Where Vision Meets Language Unl…

    alibabacloud.com

  • Qwen 2.5 3B | VIPS Learn
    is Qwen 2.5 3B? A 3B-parameter open LLM from Alibaba's Qwen 2.5 family, released September …is Qwen 2.5 3B? A 3B-parameter open LLM from Alibaba's Qwen 2.5 family, released September 2024 under Apache 2.0 with 128k context and multilingual coverage. How does it compare to Phi-3-mini? They a…

    learn.engineering.vips.edu

  • Understanding Qwen 2.5: Features, Benefits, and Practical Applications | Beam
    What is Qwen 2.5? One large language model recently gaining traction is Qwen 2.5, developed …What is Qwen 2.5? One large language model recently gaining traction is Qwen 2.5, developed by Alibaba Cloud. Using a transformer architecture similar to that of other LLMs, Qwen 2.5 displays signifi…

    beam.cloud

Also known as: fireworks_ai/accounts/fireworks/models/qwen-v2p5-14b-instruct, qwen/qwen2.5-14b-instruct, together_ai/qwen/qwen2.5-14b-instruct

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