Evaluating LLMs on Kazakhstan's mathematics exam for university admission
These findings provide important empirical evidence that LLMs can perform competitively on mathematics tasks in non-English languages. The results challenge prior assumptions about limited performance in under-resourced linguistic settings and highlight the potential of LLMs to support bilingual education and promote equitable access to higher education.
Authors
- Shirali Kadyrov (ORCID: https://orcid.org/0000-0002-8352-2597)
- Bolatbek Abdrasilov (ORCID: https://orcid.org/0000-0002-2100-3564)
- Alfira Makhmutova
- Patrick C. Kyllonen (ORCID: https://orcid.org/0000-0002-6517-4576)
- Aslan Sabyrov
- Nurseit Baizhanov
Institutions
- Educational Testing Service (US)
- Narxoz University (KZ)
- Kazakh-American University (KZ)
- National Center for Biotechnology (KZ)
- National Research Center for Maternal and Child Health (KZ)
- New Uzbekistan University (UZ)
- National University of Uzbekistan (UZ)
Publication Details
- Journal
- Frontiers in Artificial Intelligence
- Published
- 2025-09-12
- DOI
- https://doi.org/10.3389/frai.2025.1642570
- Primary Topic
- Educational Assessment and Pedagogy
- Type
- article
- Field-Weighted Citation Impact
- 0.00