The literature on predicting the load-carrying capacity of symmetrical concrete-filled steel tube (Sy-CFST) columns using different machine learning methods has mainly focused on a single method or cross section type in each study. Sy-CFST column has been widely used in the engineering field because of its several benefits such as increased strength due to confinement generation, better ductility due to high steel ratio, and less construction cost and time as compared to the encased reinforced concrete. This study attempted to evaluate the load-carrying capacity of these columns with circular and square cross-sections based on the simultaneous use of the two gene expression programming (GEP) and artificial neural network (ANN) approaches. The database required for extracting GEP and ANN models was based on the empirical results of 993 specimens. Variables considered here include the compressive strength of concrete (fc), yield stress of steel (fy), cross-sectional areas of concrete (Ac) and steel (As), diameter to thickness ratio of the steel tube (D/t or B/t), and slenderness ratio of Sy-CFST columns (λ). Moreover, parametric and sensitivity analyses were conducted separately to assess the contribution of each effective parameter to the axial capacity. To validate the efficiency of the models, prediction values of GEP and ANN were compared with the predictions of existing codes (6 codes) and different studies (8 studies). The results indicated that the developed models provide accurate predictions for the load-carrying capacity of Sy-CFST columns. In addition, the variation of parameters in the proposed models is consistent with experimental trends observed in other studies, which confirms the consistency of the proposed numerical models with physical observations
