<![CDATA[This study aims to develop a Natural Language Processing (NLP)-based Quranic verse retrieval model to support Quranic verse exploration and Computational Thinking (CT)-oriented learning in Islamic Education. The study employed the ADDIE development framework, and the model was implemented with Grade XI students and Islamic Education teachers at a private high school. Data were collected using a mixed-methods approach, including pre- and post-tests, perception questionnaires, expert validation, and teacher interviews. Quantitative data were analyzed using descriptive statistics, the Shapiro–Wilk test, the Wilcoxon signed-rank test, N-gain analysis, and descriptive percentage analysis of questionnaire responses, while qualitative data were analyzed through thematic analysis. The results demonstrated a significant improvement in students’ mean scores, increasing from 74.40 to 96.40 (*p* < 0.001), with a high average N-gain of 0.882. Student and teacher responses reached 90.19% and 77.50%, respectively, indicating positive acceptance of the proposed model. Although the one-group pretest–posttest design limits causal inference and CT was operationalized through learning-process indicators and user perceptions rather than comprehensive performance-based assessment, the findings suggest that the model has considerable potential as a technology-enhanced medium for exploratory learning in Islamic Education. Future research should focus on expanding the Quranic corpus, integrating tafsir resources, validating retrieval performance using standard information retrieval metrics, and incorporating performance-based assessments to measure Computational Thinking more comprehensively.]]>
