This technical report presents K-EXAONE, a large-scale multilingual language model developed by LG AI Research. K-EXAONE is built on a Mixture-of-Experts architecture with 236B total parameters, activating 23B parameters during inference. It supports a 256K-token context window and covers six languages: Korean, English, Spanish, German, Japanese, and Vietnamese. We evaluate K-EXAONE on a comprehensive benchmark suite spanning reasoning, agentic, general, Korean, and multilingual abilities. Across these evaluations, K-EXAONE demonstrates performance comparable to open-weight models of similar size. K-EXAONE, designed to advance AI for a better life, is positioned as a powerful proprietary AI foundation model for a wide range of industrial and research applications.
K-EXAONE Technical Report
K-EXAONE is a multilingual language model with a Mixture-of-Experts architecture that achieves competitive performance on various benchmarks while supporting multiple languages and long-context windows.
- Year
- 2026
- Venue
- arXiv 2026
- Authors
- 65
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2601.01739ARXIV-DEFAULT
- TL;DR
- Semantic Scholar
Abstract
Authors
65Yejin ChoiKyungmin LeeHonglak LeeDongkeun YoonSunkyoung KimJinho ParkEunbi ChoiKibong ChoiSeokhee HongJunwon HwangHyojin JeonHyunjik JoJoonkee KimSeongHwan KimSoyeon KimYireun KimYongil KimHaeju LeeJinsik LeeSangha ParkHeuiyeen YeenHwan ChangStanley Jungkyu ChoiJiwon HamKijeong JeonGeunyeong JeongGerrard Jeongwon JoYonghwan JoJiyeon JungNaeun KangDohoon KimEuisoon KimHayeon KimHyosang KimHyunseo KimJieun KimMinu KimMyoungshin KimUnsol KimYouchul KimYoungjin KimChaeeun LeeChaeyoon LeeChanghun LeeDahm LeeEdward Hwayoung LeeJinsang LeeJiyoung LeeSangeun LeeSeungwon LimSolji LimWoohyung LimChanwoo MoonJaewoo ParkYongmin ParkHyerin SeoWooseok SeoYongwoo SongSejong YangSihoon YangChang En YeaSihyuk YiChansik YoonSangyeon YoonHyeongu Yun