H. Jati, Y. Indrihapsari, S. . Romadhon, P. . Setialana, D. . Wijaya, and S. A. . Ardy, “Closed-Source vs. Open-Weights Language Models: Accuracy, Stability, and Deployment Trade-Offs in Educational Assessment (GPT-4o vs. LLaMA 3.1)”, jscdm, vol. 7, no. 2, pp. 58–74, Jun. 2026, Accessed: Aug. 13, 2026. [Online]. Available: https://journal.uthm.edu.my/index.php/jscdm/article/view/24596