Correlating combustion performance parameters to the main operating variables of combustors with mathematical expressions contributes to reducing the number of experiments and simplifying the design procedure of gas turbines. The application of empirical formulations meets the requirement with finite precision. The present study aims at adopting symbolic regression method to establish empirical formulations to correlate combustion efficiency with the main operating variables of gas turbine combustors. Differing from ordinary data modeling methods that search model parameters only with model structures fixed, symbolic regression method can search the structures and parameters of mathematical models simultaneously. In this article, attempts to correlate the experimental data of Combustor I using the mechanism model of burning velocity model, neural network, polynomial regression, and symbolic regression are shown sequentially. Burning velocity model has not satisfactory accuracy by comparing the predictions with the experimental data which means its lower generalization ability. Comparatively, the predictions of the empirical formulation obtained by the present symbolic regression method are in good agreement with the experimental data and also excel those of neural network and polynomial regression in generalization ability. Another two formulations are obtained by symbolic regression using the experimental data of Combustor II and III, and the different model structures of the two formulations indicate that there is still room for improvement in the present method.