Steam Generator (SG) is an important energy exchange equipment for nuclear power plants, and the level control of steam generators plays a key role in the stable operation of the plants. In order to improve the level control performance of steam generators, it is necessary to adjust the parameters of the level control system during the commissioning process of nuclear power plants. However, the parameter tuning process is heavily dependent on engineers' experience, requires a large amount of operational history data, and is difficult to ensure optimal performance. To address these issues, this paper proposes a hybrid iterative model reconstruction-based steam generator level control performance optimization method based on the idea of data-driven optimization. The method proposes a fusion idea and implementation mechanism in which process data and hybrid model are jointly driven under the data-driven framework to maximize the advantages of different modeling mechanisms in order to achieve the performance optimization of SG level control system. The method first constructs the initial data set with a small-sample Latin-square experiment design, and builds two different fitting models, SVM and Kriging, based on the initial data set respectively under the hybrid model fusion idea. After that, the particle swarm optimization algorithm is used to calculate the optimal point of the current valid model, and the optimization process is controlled by establishing the iteration termination judgment based on the historical iteration data. Then, the current iteration point is used to dynamically reconstruct the two types of models. Finally, the two types of models are dynamically reconstructed using the current iteration points. The above process is iterated until the optimal iterative process of the system is satisfied. The results of this paper show that this method has better optimization performance and can significantly improve the efficiency of steam generator level control performance optimization than the traditional optimization estimation method under the framework of single model optimization.