A Comparison of OpenAI's GPT-3.5-turbo, GPT-4-turbo, and GPT-4o when Communicating in Shona in an Educational Environment

Authors

Laurie Butgereit, Nelson Mandela University, South Africa

Helper Zhou, University of KwaZulu Natal, South Africa

Godknows Zhou, Women's University in Africa, Zimbabwe

Published in

IST-Africa 2026 Conference Proceedings

ISSN: 2576-8581

ISBN: 978-1-905824-76-2

DOI: https://doi.org/tbc

Publisher

IST-Africa Institute and IIMC International Information Management Corporation Ltd

Published in Ireland

Abstract

When OpenAI released their GPT-4o (Omni) API, an associated blog post on OpenAI's website asserted that GPT-4o has "significant improvement on text in non-English languages." Prior research by the authors into using earlier versions OpenAI's GPT API to tutor the subject of Python Programming in Shona showed promising results. This paper presents both objective and subjective results in comparing OpenAI's GPT-3.5-turbo, GPT-4-turbo, and GPT-4o when communicating in Shona in an educational environment. The three authors of the paper have a variety of backgrounds in order to contribute to this multi-disciplinary paper including expertise in configuring chatbots, expertise in integrating the GPT API into applications, language expertise as home language Shona speakers, and expertise in Shona language education.

Keywords

GPT-4o, Shona, Python, chatbots, tutoring

Cite this paper

L. Butgereit, H. Zhou and G. Zhou (2026) "A Comparison of OpenAI's GPT-3.5-turbo, GPT-4-turbo, and GPT-4o when Communicating in Shona in an Educational Environment", IST-Africa 2026 Conference Proceedings, Miriam Cunningham and Paul Cunningham (Eds), IST-Africa Institute and IIMC, 2026, ISSN: 2576-8581, ISBN: 978-1-905824-76-2, https://doi.org/tbc

Access Paper

Click here to access this paper.

IST-Africa Community Members can download papers by logging into their existing account.

If you wish to become a member of IST-Africa Community, pleaseregister your profile and you will then receive login details which you can use to access the papers.

Access to papers in the IST-Africa 2026 Conference Proceedings is for INDIVIDUAL USE only. Neither the Conference Proceedings (or individual double blind peer reviewed papers) are to be included in any public or institutional repository or processed in the context of any AI tool or large language model without prior written permission from the Publishers.

While the IST-Africa Institute and IIMC retain copyright of the Conference Proceedings, each author retains copyright to their individual paper. No paper or part thereof may be reproduced without the written permission of both the Conference Proceedings Publishers and appropriate author(s).