Home > Research > Publications & Outputs > On the performance of large language models on ...

Links

Text available via DOI:

View graph of relations

On the performance of large language models on introductory programming assignments

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print

Standard

On the performance of large language models on introductory programming assignments. / Raihan, N.; Goswami, D.; Puspo, S.S.C. et al.
In: Journal of Intelligent Information Systems, 16.08.2025.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Raihan, N, Goswami, D, Puspo, SSC, Siddiq, ML, Newman, C, Ranasinghe, T, Santos, JCS & Zampieri, M 2025, 'On the performance of large language models on introductory programming assignments', Journal of Intelligent Information Systems. https://doi.org/10.1007/s10844-025-00968-y

APA

Raihan, N., Goswami, D., Puspo, S. S. C., Siddiq, M. L., Newman, C., Ranasinghe, T., Santos, J. C. S., & Zampieri, M. (2025). On the performance of large language models on introductory programming assignments. Journal of Intelligent Information Systems. Advance online publication. https://doi.org/10.1007/s10844-025-00968-y

Vancouver

Raihan N, Goswami D, Puspo SSC, Siddiq ML, Newman C, Ranasinghe T et al. On the performance of large language models on introductory programming assignments. Journal of Intelligent Information Systems. 2025 Aug 16. Epub 2025 Aug 16. doi: 10.1007/s10844-025-00968-y

Author

Raihan, N. ; Goswami, D. ; Puspo, S.S.C. et al. / On the performance of large language models on introductory programming assignments. In: Journal of Intelligent Information Systems. 2025.

Bibtex

@article{9132dcdf78a348e5a8c8e381ce5b9396,
title = "On the performance of large language models on introductory programming assignments",
abstract = "Recent advances in artificial intelligence (AI), machine learning (ML), and natural language processing (NLP) have led to the development of a new generation of Large Language Models (LLMs) trained on massive amounts of data. Commercial applications (e.g., ChatGPT) have made this available to the general public, enabling the use of LLMs to produce high-quality texts for academic and professional purposes. Educational institutions are increasingly aware of students{\textquoteright} use of AI-generated content and are researching its impact and potential misuse. Computer Science (CS) and related fields are particularly affected, as LLMs can also generate programming code in various languages. To understand the potential impact of publicly available LLMs in CS education, we extend our previously introduced CSEPrompts (Raihan et al. 2024), a framework comprising hundreds of programming exercise prompts and multiple-choice questions from introductory CS and programming courses. We provide experimental results on CSEPrompts, evaluating the performance of several LLMs in generating Python code and answering basic computer science and programming questions, offering insights into the implications of this technology for CS education.",
author = "N. Raihan and D. Goswami and S.S.C. Puspo and M.L. Siddiq and C. Newman and T. Ranasinghe and J.C.S. Santos and M. Zampieri",
year = "2025",
month = aug,
day = "16",
doi = "10.1007/s10844-025-00968-y",
language = "English",
journal = "Journal of Intelligent Information Systems",
issn = "1573-7675",
publisher = "Springer",

}

RIS

TY - JOUR

T1 - On the performance of large language models on introductory programming assignments

AU - Raihan, N.

AU - Goswami, D.

AU - Puspo, S.S.C.

AU - Siddiq, M.L.

AU - Newman, C.

AU - Ranasinghe, T.

AU - Santos, J.C.S.

AU - Zampieri, M.

PY - 2025/8/16

Y1 - 2025/8/16

N2 - Recent advances in artificial intelligence (AI), machine learning (ML), and natural language processing (NLP) have led to the development of a new generation of Large Language Models (LLMs) trained on massive amounts of data. Commercial applications (e.g., ChatGPT) have made this available to the general public, enabling the use of LLMs to produce high-quality texts for academic and professional purposes. Educational institutions are increasingly aware of students’ use of AI-generated content and are researching its impact and potential misuse. Computer Science (CS) and related fields are particularly affected, as LLMs can also generate programming code in various languages. To understand the potential impact of publicly available LLMs in CS education, we extend our previously introduced CSEPrompts (Raihan et al. 2024), a framework comprising hundreds of programming exercise prompts and multiple-choice questions from introductory CS and programming courses. We provide experimental results on CSEPrompts, evaluating the performance of several LLMs in generating Python code and answering basic computer science and programming questions, offering insights into the implications of this technology for CS education.

AB - Recent advances in artificial intelligence (AI), machine learning (ML), and natural language processing (NLP) have led to the development of a new generation of Large Language Models (LLMs) trained on massive amounts of data. Commercial applications (e.g., ChatGPT) have made this available to the general public, enabling the use of LLMs to produce high-quality texts for academic and professional purposes. Educational institutions are increasingly aware of students’ use of AI-generated content and are researching its impact and potential misuse. Computer Science (CS) and related fields are particularly affected, as LLMs can also generate programming code in various languages. To understand the potential impact of publicly available LLMs in CS education, we extend our previously introduced CSEPrompts (Raihan et al. 2024), a framework comprising hundreds of programming exercise prompts and multiple-choice questions from introductory CS and programming courses. We provide experimental results on CSEPrompts, evaluating the performance of several LLMs in generating Python code and answering basic computer science and programming questions, offering insights into the implications of this technology for CS education.

U2 - 10.1007/s10844-025-00968-y

DO - 10.1007/s10844-025-00968-y

M3 - Journal article

JO - Journal of Intelligent Information Systems

JF - Journal of Intelligent Information Systems

SN - 1573-7675

ER -