Energy costs of communicating with AI
Frontiers in Communication · 19.06.2025 · 10
DOI: 10.3389/fcomm.2025.1572947 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Communication, online erschienen am 19.06.2025. Verfasst von Maximilian Dauner und 1 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study presents a comprehensive evaluation of the environmental cost of large language models (LLMs) by analyzing their performance, token usage, and CO 2 equivalent emissions across 14 LLMs ranging from 7 to 72 billion parameters. Each LLM was tasked with answering 500 multiple-choice and 500 free-response questions from the MMLU benchmark, covering five diverse subjects. Emissions were measured using the Perun framework on an NVIDIA A100 GPU and converted through an emission factor of 480 gCO 2 /kWh. Our results reveal strong correlations between LLM size, reasoning behavior, token generation, and emissions. While larger and reasoning-enabled models achieve higher accuracy, up to 84.9%, they also incur substantially higher emissions, driven largely by increased token output. Subject-level analysis further shows that symbolic and abstract domains such as Abstract Algebra consistently demand more computation and yield lower accuracy. These findings highlight the trade-offs between accuracy and sustainability, emphasizing the need for more efficient reasoning strategies in future LLM developments.
Zitieren
APA
Dauner, M., & Socher, G. (2025). Energy costs of communicating with AI. Frontiers in Communication, 10. https://doi.org/10.3389/fcomm.2025.1572947
Vancouver
Dauner M, Socher G. Energy costs of communicating with AI. Frontiers in Communication. 2025;10. doi:10.3389/fcomm.2025.1572947
BibTeX
@article{Dauner2025,
author = {Dauner, Maximilian and Socher, Gudrun},
title = {Energy costs of communicating with AI},
journal = {Frontiers in Communication},
year = {2025},
volume = {10},
doi = {10.3389/fcomm.2025.1572947}
}
EUVIMED