The main purpose of the present study was to explore the methods of evaluating shade tolerance, analyze the shade tolerance of different soybean genotypes, screen suitable evaluation indicators of shade tolerance, and establish a mathematical evaluation model of shade tolerance. 44 soybean cultivars (lines) were treated under shading and natural light conditions in a field experiment. Corn-soybean intercropping system created the shading conditions in the field, and soybean single planting was used as control. 10 major morphological and yield characteristics of soybean cultivars (lines) were investigated during the mature period, based on the coefficient of the shade tolerance in each index, the shade tolerance of soybeans was evaluated with multivariate statistical method. The results showed that compared with the control, the changing trend of each characteristics and amplitude were different, each index existed in varying degrees of correlation and some correlation reached significant or highly significant levels. 4 independent comprehensive components were obtained from 10 single index by principal component analysis, which reflected 79.77% information of all traits information. The method of membership function was adopted to calculate comprehensive shade tolerance value (D) and make cluster analysis, and 44 soybean cultivars (lines) were divided into 3 shade tolerance types, Class I was the high shade tolerance type, Class II was the medium shade tolerance type and Class III was the low shade tolerance type. A mathematical evaluation model for shade tolerance of soybean was established by stepwise regression analysis. Based on the model, 8 index including plant height, main stem node number, effective branch, pods per plant, seeds per plant, yield per plant, seeds per pod and lodging could be used for identifing intercropping soybean varieties to shade tolerance in Yunnan Province.