Trends in education, 2025 (vol. 18), issue 1

TVV 2025, 18(1)


CAN AI PASS THE CZECH UNIVERSITY ENTRANCE TEST?

TOMASZEK Lukas, MIKLO©ÍKOVÁ Miroslava, ©ALOUN Petr
Palacky University Olomouc, VSB - Technical University of Ostrava


This article explores the ability of large language models to successfully complete the general academic prerequisites test, which is part of the national comparative examinations conducted by SCIO and used as an entrance exam for Czech universities. For the experiment, a 2024 test was adapted for processing by reformatting questions, mathematical expressions, and graphical information. Several language models were tested, including GPT-3.5, GPT-4, Gemini, Claude 3.5, LLaMA 3.1, and Mistral Large 2. The results show that all models outperformed the median student score, with stronger performance in the verbal section compared to the analytical section. Additionally, the models demonstrated the ability to clearly explain their reasoning processes, offering potential support for students preparing for these exams.

Keywords: Large Language Models, SCIO Exam, Entrance Test

Received: June 10, 2025; Revised: June 10, 2025; Accepted: October 30, 2025; Prepublished online: February 19, 2026; Published: January 1, 2026  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
TOMASZEK, L., MIKLO©ÍKOVÁ, M., & ©ALOUN, P. (2025).
CAN AI PASS THE CZECH UNIVERSITY ENTRANCE TEST? Trends in education, 18(1), 
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    This is an open access article distributed under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0), which permits use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content