Abstract: Based on the ideal point method, the uniaxial compressive strength, rock quality designation, integrality coefficient of rock mass, strength coefficient of structural plane and seepage measurement of groundwater are selected as evaluation indexes. The weight coefficients of these evaluation indexes are determined by the Delphi method. Then, a model for classification of surrounding rock of tunnels is established, and it is verified by the surrounding rock mass data of the first stage project in Guangzhou Pumped-Storage Power Station. The results show that the Delphi method and ideal point method are of excellent performance, and their results are basically the same as those from the artificial neural network and catastrophe progression methods. The Delphi method and ideal point method are feasible to classify surrounding rock. Finally, the proposed model based on the Delphi method and ideal point method is applied to Xihualing tunnel of Zhuji-Yongjia Expressway in Zhejiang Province. The results are in good agreement with the practical situation of surrounding rock, which proves that the ideal point method used to classify the surrounding rock of expressway tunnel is reasonable and effective. The successful application of this method not only provides the basis for the design and construction of the expressway tunnel, but gives references for the classification of surrounding rock in other similar highway tunnel projects.