Jati, Handaru, Yuniar Indrihapsari, Susilo Romadhon, Pradana Setialana, Danang Wijaya, and Satya Adhiyaksa Ardy. 2026. “Closed-Source Vs. Open-Weights Language Models: Accuracy, Stability, and Deployment Trade-Offs in Educational Assessment (GPT-4o Vs. LLaMA 3.1)”. Journal of Soft Computing and Data Mining 7 (2): 58-74. https://publisher.uthm.edu.my/ojs/index.php/jscdm/article/view/24596.