K-EXAONE Technical Report

TL;DR

K-EXAONE is a large-scale, multilingual language model with 236B parameters, supporting a 256K-token context window, demonstrating competitive performance across diverse benchmarks, and aimed at broad industrial and research use.

Contribution

This report introduces K-EXAONE, a novel large-scale multilingual model with a Mixture-of-Experts architecture and extensive multilingual and reasoning capabilities.

Findings

Achieves performance comparable to similar-sized open models.

Supports six languages with a 256K-token context window.

Demonstrates strong reasoning and multilingual abilities.

Abstract

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.