We present EXAONE Deep series, which exhibits superior capabilities in various reasoning tasks, including math and coding benchmarks. We train our models mainly on the reasoning-specialized dataset that incorporates long streams of thought processes. Evaluation results show that our smaller models, EXAONE Deep 2.4B and 7.8B, outperform other models of comparable size, while the largest model, EXAONE Deep 32B, demonstrates competitive performance against leading open-weight models. All EXAONE Deep models are openly available for research purposes and can be downloaded from https://huggingface.co/LGAI-EXAONE.
@article{arxiv.2503.12524,
title = {EXAONE Deep: Reasoning Enhanced Language Models},
author = {Kyunghoon Bae and Eunbi Choi and Kibong Choi and Stanley Jungkyu Choi and Yemuk Choi and Seokhee Hong and Junwon Hwang and Hyojin Jeon and Kijeong Jeon and Gerrard Jeongwon Jo and Hyunjik Jo and Jiyeon Jung and Hyosang Kim and Joonkee Kim and Seonghwan Kim and Soyeon Kim and Sunkyoung Kim and Yireun Kim and Yongil Kim and Youchul Kim and Edward Hwayoung Lee and Haeju Lee and Honglak Lee and Jinsik Lee and Kyungmin Lee and Sangha Park and Yongmin Park and Sihoon Yang and Heuiyeen Yeen and Sihyuk Yi and Hyeongu Yun},
journal= {arXiv preprint arXiv:2503.12524},
year = {2026}
}