Qwen-MT: Where Speed Meets Smart Translation

Qwen-MT: Where Speed Meets Smart Translation | Qwen

We have a new blog! View this page at qwen.ai . This page will automatically redirect in 5 seconds. If you are not redirected automatically, please click the button below. Go Now

Qwen-MT: Where Speed Meets Smart Translation July 24, 2025 · 6 min · 1220 words · Qwen Team | Translations: 简体中文

DEMO API DISCORD Introduction # Here we introduce the latest update of Qwen-MT (qwen-mt-turbo) via Qwen API . This update builds upon the powerful Qwen3, leveraging trillions multilingual and translation tokens to comprehensively enhance the model’s multilingual understanding and translation capabilities. By integrating reinforcement learning techniques, the model achieves significant improvements in translation accuracy and linguistic fluency. Key Features: Multilingual Support for 92 Languages : Qwen-MT enables high-quality translation across 92 major official languages and prominent dialects, covering over 95% of the global population to meet diverse cross-lingual communication needs. High Customizability : The new version provides advanced translation capabilities such as terminology intervention, domain prompts and translation memory. By enabling customizable prompt engineering, it delivers optimized translation performance tailored to complex, domain-specific, and mission-critical application scenarios. Low Latency & Cost Efficiency : By leveraging a lightweight Mixture of Experts (MoE) architecture, Qwen-MT achieves high translation performance with faster response times and significantly reduced API costs (as low as $0.5 per million output tokens). This is particularly well-suited for high-concurrency environments and latency-sensitive applications.

Translation Quality # Automatic Evaluation # We evaluate Qwen-MT on multi-domain translation benchmark, specifically Chinese-English and English-German translation, as well as WMT24 multilingual translation benchmark. Experimental results demonstrate that Qwen-MT significantly outperforms comparably-sized models including GPT-4.1-mini, Gemini-2.5-Flash, and Qwen3-8B. Notably, even when compared to state-of-the-art large language models such as GPT-4.1, Gemini-2.5-Pro, and Qwen3-235B-A22B, Qwen-MT maintains competitive translation quality while its optimized lightweight architecture enables rapid translation processing. Human Evaluation # Automatic evaluation methods have inherent limitations, we further implemented human evaluation protocols leveraging real-world translation data across ten major languages: Chinese, English, Japanese, Korean, Thai, Arabic, Italian, Russian, Spanish, and French. Our rigorous evaluation framework involved three independent professional translators scoring each test sample, followed by systematic cross-validation procedures to ensure both objectivity and reliability of the assessment outcomes. Notably, Qwen-MT achieved superior performance metrics, demonstrating significant advantages in both acceptance rates and excellence rates, validating its exceptional translation capabilities in practical deployment scenarios.

Here are some translation examples： Source Text Qwen-MT Make your cubicle neat, tidy and make it a homey charm . 让你的 隔间 整洁有序，营造出 温馨舒适 的氛围。 Little study hack for y’all … do your homework/assignments the first day it was given to you… NO PROCRASTINATING!!! the day it was assigned 给 大家 一个学习小 技巧 ……拿到作业/任务的第一天就完成它……千万别拖延！ 就在布置的当天完成！ Kim also attended her ex’s first Donda listening party at Atlanta’s Mercedes-Benz Stadium on July 22. 金·卡戴珊也 于7月22日出席了她前男友在亚特兰大的梅赛德斯-奔驰体育场举行的首场《Donda》专辑 试听会 。 作为互联网公司搬砖的表示，用结果来推导自己的论点，真是闲得蛋疼，马后炮事后诸葛亮就别分析那么多。 As a representation of working hard at an internet company, it’s really annoying to use results to deduce one’s own arguments. Don’t overanalyze things after the fact like a hindsight expert . 浪姐 一、二季还行，挺励志的。虽然什么成团确实挺扯的，起码过程也算新鲜，可以看。后面就有点 炒回锅肉 的赶脚了：大家意识到了浪姐的讨论度，然后都来上浪姐，浪姐有需要继续办下去，所以就有了故取所需的 赶脚 。 Seasons one and two of “ Sister Who Makes Waves ” were decent and quite inspiring. Although the idea of forming a group was indeed ridiculous, at least the process itself was fresh and worth watching. Later on, it started to feel like reheated leftovers : everyone realized the show’s popularity, so they all jumped on the bandwagon. Since the show needed to continue, it felt like everything was being done for the sake of convenience. 发言人陈斌华表示：大陆企业出品的 3A游戏《黑神话：悟空》 ，受到 岛内 青年、游戏爱好者的追捧和好评。一方面是游戏本身制作精良、体验感好、趣味性强；另一方面是取材于《西游记》 的故事和人物角色，融入了大量古代建筑、东方美学、国风音乐等中华文化元素， 岛内玩家 很熟悉、易亲近，毕竟大家都是读着 四大名著长大的中国人。 Spokesperson Chen Binhua stated: The 3A game “Black Myth: Wukong” produced by a mainland company, has been enthusiastically embraced and highly praised by young people and gaming enthusiasts in Taiwan . On one hand, the game itself is well-made, offers an excellent experience, and is highly engaging. On the other hand, it draws inspiration from the story and characters of “Journey to the West,” incorporating numerous elements of traditional Chinese culture, such as ancient architecture, Eastern aesthetics, and national-style music. These elements are familiar and easily relatable to players in Taiwan , after all, they are all Chinese who grew up reading the Four Great Classical Novels. 且夫秦欲璧，赵弗予璧，两无所曲直也。入璧而秦弗予城，曲在秦；秦出城而璧归，曲在赵。 Moreover, if Qin desires the jade, and Zhao refuses to give it, neither side is at fault. If Zhao gives the jade but Qin does not provide the city, the fault lies with Qin; if Qin provides the city but the jade returns to Zhao, the fault lies with Zhao.

Language Support # Language Family Language Name Indo-European Afrikaans, Armenian, Assamese, Asturian, Belarusian, Bengali, Bosnian, Bulgarian, Catalan, Croatian, Czech, Danish, Dutch, English, French, Galician, German, Greek, Gujarati, Hindi, Icelandic, Italian, Latvian, Lithuanian, Luxembourgish, Macedonian, Maithili, Marathi, Nepali, Norwegian Bokmål, Norwegian Nynorsk, Occitan, Odia, Polish, Portuguese, Romanian, Russian, Serbian, Sicilian, Sindhi, Sinhala, Slovak, Slovenian, Spanish, Swedish, Tosk Albanian, Ukrainian, Urdu, Venetian, Welsh, Western Persian Sino-Tibetan Chinese (Cantonese, Simplified, and Traditional), Burmese Afro-Asiatic Arabic (Standard, Egyptian, Mesopotamian, Moroccan, Najdi, North Levantine, South Levantine, Ta’izzi-Adeni, and Tunisian), Hebrew, Maltese Austronesian Cebuano, Indonesian, Javanese, Malay, Pangasinan, Tagalog, Waray Dravidian Kannada, Tamil,…