Jati, Handaru, et al. “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, vol. 7, no. 2, June 2026, pp. 58-74, https://publisher.uthm.edu.my/ojs/index.php/jscdm/article/view/24596.