Closed-Source vs. Open-Weights Language Models: Accuracy, Stability, and Deployment Trade-Offs in Educational Assessment (GPT-4o vs. LLaMA 3.1)
Handaru Jati, Yuniar Indrihapsari, Susilo Romadhon, Pradana Setialana, Danang Wijaya, Satya Adhiyaksa ArdyNon-Scopus30 Juni 2026Afiliasi: ID, TW