Jati H, Indrihapsari Y, Romadhon S, Setialana P, Wijaya D, Ardy SA. Closed-Source vs. Open-Weights Language Models: Accuracy, Stability, and Deployment Trade-Offs in Educational Assessment (GPT-4o vs. LLaMA 3.1). jscdm. 2026;7(2):58-74. Accessed July 23, 2026. https://publisher.uthm.edu.my/ojs/index.php/jscdm/article/view/24596