A comparative review of modern large language model paradigms: GPT-4, BERT, Gemini, and DeepSeek
Computer Science and Information Technologies · 31.08.2026 · 7 (3) · 404-418
DOI: 10.11591/csit.v7i3.p404-418 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Science and Information Technologies, online erschienen am 31.08.2026. Verfasst von Kavish Sanghvi und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
This review provides comparative analysis of GPT-4, BERT (bidirectional encoder representations from transformers), Gemini, and DeepSeek large language models (LLM), focusing architectures, training methodologies, and real-world applications. The primary research question is: How do these models differ in design, strengths, limitations, and potential areas for enhancement? By addressing this question, the study aims to provide insights into the trade-offs and future directions for optimizing LLM performance and deployment. The analysis reveals GPT-4 excels in natural language generation and complex reasoning, supporting up to 128K tokens with moderate latency and higher costs making it effective for conversational artificial intelligence (AI). BERT excels bidirectional contextual understanding with smaller computational overhead and broad open-source adoption, effective for text classification. Gemini demonstrates superior multimodal integration processing text, image, audio, and code with context lengths up to 1M tokens, enabling cross-domain adaptability. DeepSeek excels in specialized domains like finance and programming, is optimized for efficiency and supports extended context windows exceeding 200K tokens. However, all models face challenges related to computational cost, hallucinations, and ethical concerns, necessitating further improvements. Despite advancements, LLMs continue to grapple with issues such as data bias, model interpretability, and responsible AI deployment. Future research should focus on hybrid model approaches, domain-specific fine-tuning, and transparency to mitigate risks while maximizing the transformative potential of LLMs in real-world applications.
Zitieren
APA
Sanghvi, K., Sharma, A. S., & Hooda, S. (2026). A comparative review of modern large language model paradigms: GPT-4, BERT, Gemini, and DeepSeek. Computer Science and Information Technologies, 7(3), 404-418. https://doi.org/10.11591/csit.v7i3.p404-418
Vancouver
Sanghvi K, Sharma AS, Hooda S. A comparative review of modern large language model paradigms: GPT-4, BERT, Gemini, and DeepSeek. Computer Science and Information Technologies. 2026;7(3):404-418. doi:10.11591/csit.v7i3.p404-418
BibTeX
@article{Sanghvi2026,
author = {Sanghvi, Kavish and Sharma, Aparna S. and Hooda, Surbhi},
title = {A comparative review of modern large language model paradigms: GPT-4, BERT, Gemini, and DeepSeek},
journal = {Computer Science and Information Technologies},
year = {2026},
volume = {7},
number = {3},
pages = {404--418},
doi = {10.11591/csit.v7i3.p404-418}
}
EUVIMED