This study aims to develop predictive models for accurately forecasting the uniaxial compressive strength of concrete enhanced with nanomaterials. Various machine learning algorithms were employed, including the backpropagation neural network (BPNN), random forest (RF), extreme gradient boosting (XGB), and a hybrid ensemble stacking method (HEStack). A comprehensive dataset containing 94 data points for nano-modified concrete was collected, with eight input parameters: water-to-cement ratio, carbon nanotubes, nano-silica, nano-clay, nano-aluminum, cement, coarse aggregates, and fine aggregates. To evaluate the performance of these models, tenfold cross-validation and a case study prediction were conducted. It has been shown that the HEStack model is the most effective approach for precisely predicting the properties of nano-modified concrete. During cross-validation, the HEStack method was found to have superior predictive accuracy and resilience against overfitting compared to the stand-alone models. This underscores the potential of the HEStack algorithm in enhancing model performance. In the case study, the predicted results were assessed using metrics such as the coefficient of determination (R2), mean absolute percentage error (MAPE), root mean square error (RMSE), the ratio of RMSE to the standard deviation of observations (RSR), and the normalized mean bias error (NMBE). The HEStack model achieved the lowest MAPE of 2.84%, RMSE of 1.6495, RSR of 0.0874, and absolute NMBE of 0.0064. In addition, it attained a remarkable R2 value of 0.9924, surpassing the R2 scores of 0.9356 (BPNN), 0.9706 (RF), and 0.9884 (XGB), indicating its exceptional generalization capability.