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: Jul. 23, 2026. [Online]. Available: https://publisher.uthm.edu.my/ojs/index.php/jscdm/article/view/24596