Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.12524 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912798767841280 |
|---|---|
| author | Bae, Kyunghoon Choi, Eunbi Choi, Kibong Choi, Stanley Jungkyu Choi, Yemuk Hong, Seokhee Hwang, Junwon Jeon, Hyojin Jeon, Kijeong Jo, Gerrard Jeongwon Jo, Hyunjik Jung, Jiyeon Kim, Hyosang Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Youchul Lee, Edward Hwayoung Lee, Haeju Lee, Honglak Lee, Jinsik Lee, Kyungmin Park, Sangha Park, Yongmin Yang, Sihoon Yeen, Heuiyeen Yi, Sihyuk Yun, Hyeongu |
| author_facet | Bae, Kyunghoon Choi, Eunbi Choi, Kibong Choi, Stanley Jungkyu Choi, Yemuk Hong, Seokhee Hwang, Junwon Jeon, Hyojin Jeon, Kijeong Jo, Gerrard Jeongwon Jo, Hyunjik Jung, Jiyeon Kim, Hyosang Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Youchul Lee, Edward Hwayoung Lee, Haeju Lee, Honglak Lee, Jinsik Lee, Kyungmin Park, Sangha Park, Yongmin Yang, Sihoon Yeen, Heuiyeen Yi, Sihyuk Yun, Hyeongu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12524 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EXAONE Deep: Reasoning Enhanced Language Models Bae, Kyunghoon Choi, Eunbi Choi, Kibong Choi, Stanley Jungkyu Choi, Yemuk Hong, Seokhee Hwang, Junwon Jeon, Hyojin Jeon, Kijeong Jo, Gerrard Jeongwon Jo, Hyunjik Jung, Jiyeon Kim, Hyosang Kim, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Youchul Lee, Edward Hwayoung Lee, Haeju Lee, Honglak Lee, Jinsik Lee, Kyungmin Park, Sangha Park, Yongmin Yang, Sihoon Yeen, Heuiyeen Yi, Sihyuk Yun, Hyeongu Computation and Language Artificial Intelligence 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. |
| title | EXAONE Deep: Reasoning Enhanced Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.12524 |