Jati, H.; Indrihapsari, Y.; Romadhon, S. .; Setialana, P. .; Wijaya , D. .; Ardy , S. A. . 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.