The aim followed in this study was to compare the performance of multiple regression vs neural network models to predict the activity of antioxidant enzymes Super Oxide Dismutase (SOD), CAT alase (CAT), Ascorbate Pero Xidase (APX) and PeroXidase (POX) in the shoots of wheat (Triticum aestivum), Alvand cultivar in a soil polluted with cadmium. The treatments consisted of four levels of cadmium (0 (control), 25, 50 and 100 mg kg-1 soil), respectively. After 30 days (almost simultaneous with the stage of the plant’s stem elongation) plant samples were harvested. The following ten different parameters namely: wet and dry weight, chlorophyll a and b, concentrations of cadmium, copper, iron, manganese, zinc and potassium, were determined. The activities of the enzymes SOD, CAT, APX and POX were assessed. As a next step, the correlation coefficients between the ten parameters and the activity of antioxidant enzymes were determined. The results of multiple regression and neural network models optimized, showed that the efficiency of Artificial Neural Network, in predicting the activity of SOD and POX enzymes, was more pronounced than those of the Multiple Regression models. Coefficients of multiple determinations (r2) between measured and predicted values of SOD activity for Multiple Regression and Neural Network models were recorded as 0.76 and 0.87 respectively. Coefficients of Multiple Determination (r2) of POX activity for Multiple Regression vs Neural Network models were 0.96 and 0.98 respectively. Also the coefficients of Multiple Determination (r2) between the measured and predicted values of CAT activity for multiple regression and neural network models were 0.97 and were 0.98 respectively. With regard to the APX enzyme, coefficients for Multiple Regression and Neural Network models were 0.97 and 0.99 respectively. According to the results of the research, in general the efficiency of artificial neural network model in predicting the activity of antioxidant enzymes in wheat shoots, and under toxicity of Cd was more than that of the multivariate regression model.