Are Large Language Models Smart Coders? Evaluating Correctness and Efficiency of LLM-generated Algorithms
JUCS - Journal of Universal Computer Science · 28.06.2026 · 32 (6) · 851-875
DOI: 10.3897/jucs.169476 ↗Kurz gefasst
Fachartikel in der Zeitschrift JUCS - Journal of Universal Computer Science, online erschienen am 28.06.2026. Verfasst von Jefferson Martins und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Skilled software developers play a crucial role in creating energy-efficient code, contributing to the reduction of carbon emissions and promoting sustainable computing practices. In parallel, Large Language Models (LLMs) have recently emerged as powerful programming assistants, providing support for developers in complex coding tasks. In this context, this study investigates the ability of LLMs to generate computationally efficient implementations of classic algorithms - such as Heap Sort and Binary Search - across different programming languages, with a primary focus on optimizing energy consumption, memory usage, and execution time. Our results show that, in most cases, different LLMs are able to generate these algorithm implementations correctly. Furthermore, in the majority of the evaluated scenarios, LLM-generated code demonstrates superior performance over human-written algorithm code with regard to energy consumption, memory efficiency, and execution time.
Zitieren
APA
Martins, J., Andrade, R., & Pereira, L. F. A. (2026). Are Large Language Models Smart Coders? Evaluating Correctness and Efficiency of LLM-generated Algorithms. JUCS - Journal of Universal Computer Science, 32(6), 851-875. https://doi.org/10.3897/jucs.169476
Vancouver
Martins J, Andrade R, Pereira LFA. Are Large Language Models Smart Coders? Evaluating Correctness and Efficiency of LLM-generated Algorithms. JUCS - Journal of Universal Computer Science. 2026;32(6):851-875. doi:10.3897/jucs.169476
BibTeX
@article{Martins2026,
author = {Martins, Jefferson and Andrade, Rodrigo and Pereira, Luis F. Alves},
title = {Are Large Language Models Smart Coders? Evaluating Correctness and Efficiency of LLM-generated Algorithms},
journal = {JUCS - Journal of Universal Computer Science},
year = {2026},
volume = {32},
number = {6},
pages = {851--875},
doi = {10.3897/jucs.169476}
}
EUVIMED