Background: Students’ academic performance is a crucial indicator of their mastery of core competencies obtained throughout the learning process in higher education. These competencies become an essential benchmark, not only for academic evaluation, but also for the industry that expects graduates to meet professional standards. Therefore, an objective and data-driven evaluation method is needed to identify students’ academic performance and support academic decision-making. Methods: This study employs the Fuzzy C-Means (FCM) clustering method as an educational data mining technique to classify civil engineering students based on their academic results. Three key competency areas are used in this study, i.e., Structure and Material (SM), Geometry and Transportation (GT), and Construction Management (CM). A total of 221 students were analysed, exceeding the minimum sample size. The clustering process was performed using multiple cluster models (three, four, and five clusters), and the silhouette coefficient was used to evaluate the quality and accuracy of the clusters. Results: The findings reveal that the three-cluster model provides the most representative structure, showing the highest silhouette coefficient value compared with others. This indicates that three clusters offer the most appropriate grouping for evaluating academic performance. Cluster 1 represents students with excellent academic achievement, cluster 2 consists of students with good performance, and cluster 3 represents students with concerning academic performance requiring additional academic support. Conclusion: Overall, the study concludes that the three-cluster model, consisting of an excellent, good, and concerning performance group, offers the most accurate and representative evaluation of civil engineering students’ academic performance. These results provide valuable insights to design targeted interventions, enhance learning support, and optimize curriculum alignment to ensure that students achieve the competencies required before entering the professional field.