Comparison of the Abilities of High School Students, Gemini, and Perplexity on an Electromagnetism Concept Understanding Test

Authors

  • Nurul Fatia Itami Universitas Tadulako
  • I Komang Werdhiana Universitas Tadulako
  • I Wayan Darmadi Universitas Tadulako
  • Rudi Santoso Universitas Tadulako

DOI:

https://doi.org/10.24252/al-khazini.v6i2.72015

Keywords:

Electromagnetism, Gemini, Artificial intelligence, Perplexity, Conceptual understanding

Abstract

The development of Artificial Intelligence (AI) has encouraged its use in education, including as a support for physics learning. This study aims to determine the differences in the abilities of high school students, Gemini, and Perplexity in completing the Electromagnetic concept understanding test. This study uses a quantitative approach with a comparative design. The research sample consisted of 50 students of SMA Negeri 5 Palu, while Gemini and Perplexity were given the same instrument with each item tested repeatedly 50 times so that the amount of data in each group was equal. The research instrument was 32 multiple-choice questions translated from the Conceptual Survey of Electricity and Magnetism (CSEM) and validated by a language expert lecturer. Data analysis was carried out using descriptive statistics, the Kolmogorov–Smirnov Normality test, the Kruskal–Wallis test, and post hoc pairwise comparisons. The results showed that there were significant differences in the abilities of students, Gemini, and Perplexity in completing the Electromagnetic concept understanding test (p < 0.001). Gemini achieved the highest average score, followed by Perplexity, while students achieved the lowest average score. Thus, the generative AI models, specifically Gemini and Perplexity, performed better than students in completing the Electromagnetic Concept Understanding test.

 

 

Downloads

Download data is not yet available.

References

Akbar, S. (2015). Instrumen perangkat pembelajaran. Remaja Rosdakarya.

Al-Thani, S. N., Al-Kuwari, M. G., Al-Malki, A. M., et al. (2025). Comparative performance of ChatGPT, Gemini, and final-year emergency medicine clerkship students in answering multiple-choice questions. International Journal of Emergency Medicine, 18(1), 1–10. https://doi.org/10.1186/s12245-025-00949-6

Anderson, L. W., & Krathwohl, D. R. (Eds.). (2001). A taxonomy for learning, teaching, and assessing: A revision of Bloom’s taxonomy of educational objectives. Longman.

Ardiansyah, A., Abdin, M., & Salis, M. R. (2024). Analisis komparatif generative artificial intelligence: ChatGPT, Gemini, dan Perplexity sebagai media pembelajaran akuntansi. Jurnal Teknodik, 28(2), 95–112. https://doi.org/10.32550/teknodik.vi.1192

Azizah, M. A., & Mansyur, J. (2024). Perbandingan kapabilitas respons ChatGPT dan Gemini terhadap pertanyaan konseptual tentang optik. JPFT (Jurnal Pendidikan Fisika Tadulako Online), 12(1), 15–25. https://doi.org/10.22487/jpft.v12i1.3510

Firdaus, T., Sholeha, S. A., Jannah, M., & Setiawan, A. R. (2024). Comparison of ChatGPT and Gemini AI in answering higher-order thinking skill biology questions: Accuracy and evaluation. International Journal of Science Education and Teaching, 3(3), 126–138. https://doi.org/10.14456/ijset.2024.11

Gravina, A. G., Pellegrino, R., Palladino, G., Imperio, G., Ventura, A., & Federico, A. (2024). Charting new AI education in gastroenterology: Cross-sectional evaluation of ChatGPT and Perplexity AI in medical residency exam. Digestive and Liver Disease, 56(8), 1304–1311. https://doi.org/10.1016/j.dld.2024.02.019

Hardani. (2020). Metode penelitian kualitatif & kuantitatif. Pustaka Ilmu.

Iorliam, A., & Ingio, J. A. (2024). A comparative analysis of generative artificial intelligence tools for natural language processing. Journal of Computing Theories and Applications, 1(3), 311–325. https://doi.org/10.62411/jcta.9447

Kahaleh, R., & López Simó, V. (2025). Evaluating large language models in high school physics education: Addressing misconceptions and fostering conceptual understanding. Physics Education, 60(2), Article 025013. https://doi.org/10.1088/1361-6552/adb235

Kaharu, S. N., Werdhiana, I. K., & Mansyur, J. (2026). Comparing ChatGPT and Gemini on a two-tier static fluid test: Capability and scientific consistency. European Journal of Educational Research, 15(1), 223–250. https://doi.org/10.12973/eu-jer.15.1.223

Published

2026-11-17

How to Cite

Itami, N. F., Werdhiana, I. K., Darmadi, I. W., & Santoso, R. (2026). Comparison of the Abilities of High School Students, Gemini, and Perplexity on an Electromagnetism Concept Understanding Test. Al-Khazini: Jurnal Pendidikan Fisika, 6(2), 105–115. https://doi.org/10.24252/al-khazini.v6i2.72015

Issue

Section

Artikel