Global climate change has posed a serious threat to agricultural production and food security. Crop growth models, with their excellent simulation and prediction capabilities, have become one of the important tools for guiding agricultural production and ensuring food security. This study provides a review of the research progress in crop growth models. The development history of the models is summarized into four stages, including process modeling, system simulation, model application, and algorithm expansion. According to different driving factors, the crop growth models can be categorized into solar radiation-driven, soil moisture content-driven, meteorological factor-driven, and integrated factor-driven models. In terms of the countries of development, the models mainly include those from the Netherlands, the United States, Australia, and China. Regarding applications, crop growth models are primarily applicable to adaptability assessment, agricultural resource and crop cultivation management, and climate change evaluation. Since their initial development, these models have enhanced their mechanistic nature through various approaches, such as incorporating surface mulching modules, considering the response of root water uptake to soil salt stress, and preliminarily introducing physiological regulation processes. By integrating with remote sensing technology, the spatial scale of the models has been expanded from the point scale to the regional or even global scale, and the accuracy of regional-scale yield estimation has been significantly improved through assimilation with remote sensing. Meanwhile, crop growth models have also been combined with intelligent algorithms to optimize irrigation scheduling, and to perform model parameter optimization. Looking forward, potential future research directions of crop growth models include extending the soil submodule from one-dimensional to two/three-dimensional water–heat–solute transport, moving toward a more mechanistic crop growth modeling, integration with remote sensing, and incorporating artificial intelligence. This study serves as a reference for further development and application of crop growth models, and provides technical support for the development of sustainable agriculture.