Kualitas Soal Evaluasi Mata Pelajaran Biologi SMA yang Dikembangkan Menggunakan Gemini AI dengan Analisis Rasch Model Quality of High School Biology Evaluation Items Developed Using Gemini AI with Rasch Model Analysis
Main Article Content
Abstract
The limited variety of items in the item bank remains an obstacle for Biology teachers in developing quality learning evaluations, even though the items used should be measured empirically for their quality and validity in order to provide comprehensive evaluation results. This study aims to examine the quality of senior high school Biology test items developed through Gemini AI. This study employed a quantitative descriptive approach by utilizing primary data from one class at SMA Pembangunan Laboratorium UNP. The research stages included item development using AI, content validation by experts, item tryout, answer collection and scoring, and item quality analysis. The results showed that the senior high school Biology evaluation items generated by Gemini AI and analyzed using the Rasch Model had fairly good quality, although improvements were still needed in several specific item quality indicators. These findings indicate that the use of Gemini AI can support teachers in developing and evaluating Biology test items more systematically. This study affirms that the use of Gemini AI has the potential to become an effective alternative in item quality analysis, while also providing practical implications for teachers to utilize similar technology in developing evaluation items in various subjects in order to obtain more reliable and higher-quality instruments.
Keywords: Biology; Gemini AI; Item Quality; Rasch Model; Learning Evaluation
Downloads
Article Details

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
References
Andrich, D. (2018). Controlling response dependence in the measurement of change using the Rasch model. Statistical Methods in Medical Research, 27(12), 3709–3725. https://doi.org/10.1177/0962280217710834
Azizah, A., & Wahyuningsih, S. (2020). Penggunaan Model Rasch untuk Analisis Instrumen Tes pada Mata Kuliah Matematika Aktuaria. Jurnal Pendidikan Matematika (JUPITEK), 3(1), 45–50. https://doi.org/10.30598/jupitekvol3iss1pp45-50
Bond, T. G., & Fox, C. M. (2015). Applying the Rasch model: Fundamental measurement in the human sciences (3rd ed.). Routledge. https://doi.org/10.4324/9781315814698
Boone, W. J. (2016). Rasch analysis for instrument development: Why, when, and how? CBE—Life Sciences Education, 15(4), rm4. https://doi.org/10.1187/cbe.16-04-0148
Han, C. (2019). William J. Boone, John R. Staver and Melissa S. Yale. Rasch analysis in the human sciences. Journal of Research Design and Statistics in Linguistics and Communication Science, 5(1–2), 208–211. https://doi.org/10.1558/jrds.37535
Jannah, I. K., Mahanal, S., & Mashfufah, A. (2023). Analisis Tingkat Kognitif Soal Asesmen Sumatif Akhir Semester I (ASAS I) IPA Berbasis Jenis Soal AKM berdasarkan Taksonomi Bloom di Kelas V SD Swasta Kota Malang. JIIP - Jurnal Ilmiah Ilmu Pendidikan, 6(2), 806–810. https://doi.org/10.54371/jiip.v6i2.1633
Jayanti, U. N. A. D., & Mahidin. (2021). Perencanaan Pembelajaran Biologi: Tinjauan Teori, Praktik, dan Paradigma Wahdatul ‘Ulum. Perdana Publishing. https://repository.uinsu.ac.id/17030/
Kasprianto, R., Munawar, W., & Sriyono. (2025). Analisis Butir Soal High Order Thinking Skills (HOTS) Berbantuan Artificial Intelligence (AI) untuk Pembelajaran Perawatan dan Perbaikan Sasis Sepeda Motor di SMK. ATIKANOTO: Journal of Automotive Engineering Education, 2(1). https://doi.org/10.17509/atikanoto.v2i1.87360
Nurpitasari, D. (2022). Kualitas Butir Soal Biologi Kelas X IPA MAN 1 Merangin Tahun Ajaran 2021/2022. EDU-BIO: Jurnal Pendidikan Biologi, 6(2), 13–23. https://doi.org/10.30631/edubio.v6i2.17
Rajagukguk, M. J. T., & Naibaho, D. (2023). Mampu Memilih Soal Berdasarkan Tingkat Kesukaran. Pediaqu: Jurnal Pendidikan Sosial dan Humaniora, 2(4), 12736–12747. https://publisherqu.com/index.php/pediaqu/article/view/701
Rochim, A. A., Baharung, S., & Isnaini, I. (2024). Perencanaan Pembelajaran Biologi Berbasis Project Based Learning pada Kurikulum Merdeka di SMAN 1 Bungku Tengah. Jurnal Pendidikan Tambusai, 8(2). https://doi.org/10.31004/jptam.v8i2.15015
Sandy, D. A., & Nugrahaningsih, W. H. (2024). Implementasi Kurikulum Merdeka pada Mata Pelajaran Biologi di Sekolah Daerah Rural. Prosiding Semnas Biologi XII Tahun 2024 FMIPA Universitas Negeri Semarang, 69–74. https://proceeding.unnes.ac.id/semnasbiologi/article/view/3937
Sapitri, A., Kurniati, T., & Yuliawati, A. (2022). Analisis Kualitas Soal UAS Biologi SMA Kelas X dan XI MIA. Bioeduca: Journal of Biology Education, 4(1), 45–56. https://doi.org/10.21580/bioeduca.v4i1.8433
Sudianto, Amrillah Rosyadi, & Yusuf. (2024). Evaluasi Tingkat Pemahaman Konsep Siswa pada Materi Komponen Ekosistem dan Interaksi Antar Komponen Kelas X SMA Negeri 2 Bayan Kabupaten Lombok Utara. Otus Education: Jurnal Biologi dan Pendidikan Biologi, 2(2), 89–102. https://doi.org/10.62588/otusedu.2024.v2i2.0111
Suganda, A. (2023). Memilih AI yang Tepat untuk Guru: Perbandingan Fitur Gemini, ChatGPT, dan Claude AI. Jurnal Inovasi Teknologi Dan Edukasi Teknik, 3(11), 1–10. https://doi.org/10.17977/um068.v3.i11.2023.2
Sumintono, B., & Widhiarso, W. (2015). Aplikasi Pemodelan Rasch pada Assessment Pendidikan. Trim Komunikata.
Wisman, Y., Effrata, E., & Tutesa, T. (2021). Penerapan Konsep Instrumen Evaluasi Hasil Belajar. Jurnal Ilmiah Kanderang Tingang, 12(1), 1–9. https://doi.org/10.37304/jikt.v12i1.105
Zuhri, N. Z., Syihabuddin, & Tatang. (2024). Analisis Validitas, Reliabilitas, dan Tingkat Kesukaran Soal Bahasa Arab Tingkat SMP Berbasis Artificial Intelligence (AI) melalui Platform QuestionWell. Jurnal Pendidikan dan Pembelajaran Indonesia (JPPI), 4(2), 693–704. https://doi.org/10.53299/jppi.v4i2.576




















