Cohere releases open-weight translation model North Small Translate, scoring 83.60 on WMT26 to beat DeepL and Google Translate
Original title:Introducing North Small Translate: A leading sovereign open-weight machine translation model
AI summary
Cohere released the machine translation model North Small Translate, an MoE architecture with 218B total parameters and 25B active, supporting 50+ languages. It scores 83.60 across all languages on WMT26, above DeepL NextGen's 81.37 and Google Translate's 68.20, with the Agentic version reaching 84.36.
Key Takeaways
- Cohere released the machine translation model North Small Translate,an MoE architecture with 218B…
- It scores 83.
- 60 across all languages on WMT26,above DeepL NextGen's 81.
- 37 and Google Translate's 68.
- 20,with the Agentic version reaching 84.
Quick Facts
- Published
- Updated
- Source
- Cohere 产品与研究博客(网页)
- Category
- Model Releases
- AI score
- 66
官方公布了 WMT26 各语言和分区域得分、吞吐与单任务成本数据,读者可据此评估其相对 DeepL 和开源模型的位置。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Cohere releases open-weight translation model North Small Translate, scoring 83.60 on WMT26 to beat DeepL and Google Translate. September 10, 2026. https://new.nat6.net/en/news/cmuh2jk8606ssrolz2ouuav48/