This article provides a literature review on the application of data-driven surrogate models in structural engineering. The review highlights the increasing use of surrogate models and metamodeling techniques in approximating complex systems, which have shown effectiveness in various engineering and scientific fields due to their ability to handle demanding computational requirements. Surrogate models can significantly reduce the time and resources required for calculations, but practitioners in structural engineering face challenges in selecting the appropriate model due to the multitude of available approaches. Despite the advantages of surrogate models, their application in civil engineering has been limited to the past few years, necessitating recommendations for their proper utilization and comprehensive reviews of current research. The article reviews 91 journal articles published from 2003 onwards, analyzing the various surrogate models used and the domains in which they have been applied. The study shows that data-driven surrogate models offer significant benefits in structural engineering due to their flexible computational methods that produce accurate results. However, there are still significant research gaps in the existing literature that need to be addressed in future studies. The review also discusses various surrogate models, including neural networks, Gaussian processes, radial basis functions, support vector machines, and polynomial chaos expansions, among others. The article emphasizes the importance of data-driven surrogate models in structural engineering and calls for further research to address the existing gaps.This article provides a literature review on the application of data-driven surrogate models in structural engineering. The review highlights the increasing use of surrogate models and metamodeling techniques in approximating complex systems, which have shown effectiveness in various engineering and scientific fields due to their ability to handle demanding computational requirements. Surrogate models can significantly reduce the time and resources required for calculations, but practitioners in structural engineering face challenges in selecting the appropriate model due to the multitude of available approaches. Despite the advantages of surrogate models, their application in civil engineering has been limited to the past few years, necessitating recommendations for their proper utilization and comprehensive reviews of current research. The article reviews 91 journal articles published from 2003 onwards, analyzing the various surrogate models used and the domains in which they have been applied. The study shows that data-driven surrogate models offer significant benefits in structural engineering due to their flexible computational methods that produce accurate results. However, there are still significant research gaps in the existing literature that need to be addressed in future studies. The review also discusses various surrogate models, including neural networks, Gaussian processes, radial basis functions, support vector machines, and polynomial chaos expansions, among others. The article emphasizes the importance of data-driven surrogate models in structural engineering and calls for further research to address the existing gaps.