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 [Internet]. 2026 Jun. 30 [cited 2026 Jul. 23];7(2):58-74. Available from: https://publisher.uthm.edu.my/ojs/index.php/jscdm/article/view/24596