This paper presents a semi-empirical model to estimate the ultimate shear strength of steel fiber-reinforced concrete (SFRC) beams without shear reinforcement using the gene expression programming (GEP) technique. An extensive, reliable dataset consisting of the data of 266 SFRC beams with no stirrups was established for the development of this model. The most effective variables including the compressive strength (), ratio of shear span-to-effective depth (), ratio of flexural reinforcement (), and fiber factor () were employed as input parameters in the GEP-based modeling. The accuracy of the proposed model was verified by its ability to predict a portion of data that had not been used in the training phase. Moreover, the performance of the model was evaluated using different statistical criteria. Sensitivity analysis and parametric studies were conducted on the proposed model to determine its ability to correctly consider the effect of input parameters for predicting the ultimate shear strength. In addition, the proposed model was compared with some other models proposed in the literature, and it was found that the proposed model demonstrates the best performance and accuracy among the considered shear strength prediction models.
