AbstractThe mechanical properties of concrete, such as compressive strength and slump flow rates, are very nonlinear. For academics, it is crucial to forecast these qualities while creating new building methods. Such capabilities should be developed to lower the cost of expensive tests and increase the precision of the measurements. The goal of this study is to create an radial basis function neural network to describe the characteristics of hardness in high‐performance concrete (HPC) mix. Metaheuristic techniques were used to enhance the RBFNN's functionality. A dataset of 181 HPC mixes comprising ecologically beneficial ingredients, such as fly ash and silica fume, was used for training and evaluating the capabilities of the proposed hybrid models. According to the modeling process based on sensitivity analysis of input parameters and the results of hybrid models, the model combined with the multiverse optimization algorithm (MVO) had a higher correlation between the predicted and observed CS and slump values than the model combined with three optimization algorithms in terms of the R2 index being the maximum value of 0.984 in the tasting phase of CS and SL estimation. While evaluating two mechanical aspects of HPC samples, the of the model coupled with the MVO algorithm reconfirmed its accuracy being 3.59.