Self-Compacting Concrete (SCC), owing to its ability to flow under its own weight and completely fill formwork without the need for mechanical vibration, plays a significant role in improving construction quality and reducing problems associated with inadequate compaction. However, the proper design of SCC, particularly at low water-to-cementitious materials ratios, requires simultaneous control of fresh properties and compressive strength. In this study, the behavior of silica fume-incorporated SCC was experimentally investigated, and a predictive model for compressive strength was subsequently developed using Gene Expression Programming (GEP). A total of 48 SCC mix designs were prepared based on the National SCC Mix Design Method, of which 46 mixtures satisfied the self-compacting criteria. The main variables included the water-to-cementitious materials ratio at four levels (0.35, 0.40, 0.45, and 0.50) and silica fume replacement at three levels (0%, 5%, and 10% by weight of cement). Fresh concrete properties were evaluated through slump flow, V-funnel, and visual stability index (VSI) tests, while compressive strength was measured at 7, 28, and 90 days. The results indicated that silica fume replacement up to 5% had no adverse effect on workability, whereas a 10% replacement level reduced flowability and increased superplasticizer demand. Furthermore, replacing 5% and 10% of cement with silica fume led to an average increase of 9.3% and 18.4%, respectively, in the 28-day compressive strength compared with the control mixtures. For compressive strength prediction, GEP was employed considering the key mix design parameters. The developed model achieved a coefficient of determination (R²) of approximately 0.90 and a root mean square error (RMSE) of 2.59 MPa, demonstrating satisfactory predictive performance and providing an explicit analytical equation suitable for engineering design applications.