EXAONE 4.5 Technical Report

Eunbi Choi; Kibong Choi; Sehyun Chun; Seokhee Hong; Junwon Hwang; Hyojin Jeon; Ahra Jo; Hyunjik Jo

cs.CLApr 9, 2026

EXAONE 4.5 Technical Report

Authors: Eunbi Choi, Kibong Choi, Sehyun Chun, Seokhee Hong, Junwon Hwang, Hyojin Jeon, Ahra Jo, Hyunjik Jo, Yeonsik Jo, Joonkee Kim, Seonghwan Kim, Soyeon Kim, Sunkyoung Kim, Yireun Kim, Yongil Kim, Changhun Lee, Haeju Lee, Jinsik Lee, Kyungmin Lee, Sangha Park, Kwangrok Ryoo, Minju Seo, Sejong Yang, Heuiyeen Yeen, Hwan Chang, Stanley Jungkyu Choi, Yejin Choi, Kyubeen Han, Joonwon Jang, Kijeong Jeon, Geunyeong Jeong, Gerrard Jeongwon Jo, Jiyeon Jung, Daeseong Kim, Dohoon Kim, Dohyun Kim, Hyunseo Kim, Minu Kim, Myoungshin Kim, Youchul Kim, Byungoh Ko, Christopher Lee, Edward Hwayoung Lee, Honglak Lee, Jiyoung Lee, Sangeun Lee, Seungwon Lim, Woohyung Lim, Jueun Mun, Jaewoo Park, Jimin Park, Jinho Park, Yongmin Park, Wooseok Seo, Yongwoo Song, Sihyuk Yi, Kyungjae Yoo, Sangyeon Yoon

Abstract

This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integrating a dedicated visual encoder into the existing EXAONE 4.0 framework, enabling native multimodal pretraining over both visual and textual modalities. The model is trained on large-scale data with careful curation, particularly emphasizing document-centric corpora that align with LG's strategic application domains. This targeted data design enables substantial performance gains in document understanding and related tasks, while also delivering broad improvements across general language capabilities. EXAONE 4.5 extends context length up to 256K tokens, facilitating long-context reasoning and enterprise-scale use cases. Comparative evaluations demonstrate that EXAONE 4.5 achieves competitive performance in general benchmarks while outperforming state-of-the-art models of similar scale in document understanding and Korean contextual reasoning. As part of LG's ongoing effort toward practical industrial deployment, EXAONE 4.5 is designed to be continuously extended with additional domains and application scenarios to advance AI for a better life.

Figures & tables

Figure 1: Overview of the EXAONE 4.5 architecture.

Stage	Stage 1	Stage 2
Training Modules	All	All
Image Tokens	420B	225B
Text Tokens	400B	110B
Sequence Length	8K	8K
Amount of computation (FLOPs)	$1.57\times 10^{23}$	$6.43\times 10^{22}$

Table 1: Training configuration across pretraining stages.

	EXAONE 4.5 33B ( Reasoning )	GPT-5 mini [ 42 ] ( Reasoning: high )	Qwen3-VL-32B [ 8 ] Thinking	Qwen3-VL-235B-A22B [ 8 ] Thinking	Qwen3.5-27B [ 37 ] ( Reasoning )
Architecture	Dense	-	Dense	MoE	Dense
# Total Params	33B	-	33B	236B	27B
# Activated Params	33B	-	33B	23B	27B
STEM / Puzzle
MMMU	78.7	79.0	78.1	80.6	82.3
MMMU-Pro	68.6	67.3	68.1	69.3	75.0

Table 2: The main evaluation results of EXAONE 4.5 Reasoning mode on vision benchmarks.

	EXAONE 4.5 33B ( Reasoning )	K-EXAONE-236B-A23B [ 13 ] ( Reasoning )	GPT-5 mini [ 42 ] ( Reasoning: high )	Qwen3-VL-235B-A22B [ 8 ] Thinking	Qwen3.5-27B [ 37 ] ( Reasoning )
Architecture	Dense	MoE	-	MoE	Dense
# Total Params	33B	236B	-	236B	27B
# Activated Params	32B	23B	-	22B	27B
Reasoning
AIME 2026	92.6	92.2	92.4	89.4	93.2
GPQA-Diamond	80.5	79.1	82.3	77.1	85.5

Table 3: The main evaluation results of EXAONE 4.5 Reasoning mode on language benchmarks.

Vision-Language Models

Vision-language models connect visual inputs with text for retrieval, question answering, generation, and grounded multimodal reasoning.

See all 736 papers

K-EXAONE 2.0 Technical Report
Aug 5, 2026Eunbi Choi, Kibong Choi, Sehyun Chun +74Multilingual Language Models Mixture-of-Experts Language Models
Gemma 4 Technical Report
Jul 2, 2026Gemma Team, Sherif El Abd, Vaibhav Aggarwal +298Efficient Multimodal Inference Unified Multimodal Models
Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction
Sep 14, 2026Kushal Patel, Pushkal Shrivastava, Mackenzie Lees +4VLM Evaluation VLM Robustness
John Hancock, 200 Berkeley St, Boston, MA 02116, USA

Aug 5, 2026J/K move · Enter open · S save

K-EXAONE 2.0 Technical Report

Eunbi Choi, Kibong Choi, Sehyun Chun, Seokhee Hong+73

Multilingual Language Models Mixture-of-Experts Language Models Open-Weight Language Models

Open paper AskPDF arXiv

This technical report presents K-EXAONE 2.0, an open-weight multilingual foundation model developed by LG AI Research as a step in our effort toward global frontier-scale foundation models. Rather than training from scratch, we upcycle K-EXAONE and expand its architecture, yielding a Mixture-of-Experts (MoE) model with 750B total parameters and approximately 37B activated per token---more than three times the capacity of its predecessor. K-EXAONE 2.0 supports context lengths of up to 256K tokens and expands multilingual coverage from six to ten languages. Its training pipeline combines continual pre-training, difficulty-focused mid-training, and post-training to strengthen reasoning, agentic coding, multilingual capability, and safety grounded in Korean sociocultural contexts. Across nine evaluation categories selected to reflect the conditions of practical use, K-EXAONE 2.0 improves over K-EXAONE and remains competitive with open-weight models, showing its largest gains in agentic coding and long-context understanding and its clearest strengths in long-context retrieval and safety. Released under the Apache 2.0 license, K-EXAONE 2.0 enables the wider AI ecosystem to evaluate, deploy, adapt, and build upon it, while marking the beginning---rather than the endpoint---of our challenge toward the global frontier.

Abstract

Vision-Language Models

Explore similar work

K-EXAONE 2.0 Technical Report

Gemma 4 Technical Report

Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document Extraction