In arid and semi-arid regions of the world, including Iran, soil salinity is one of the major abiotic stresses. One of the ways to achieve high performance in these areas is to use salt-tolerant varieties of canola. In order to evaluate the salt tolerance of canola genotypes based on the eight indices using analysis of variance, regression and an artificial neural network (ANN), 39 cultivars and liens of rapeseed were evaluated in terms of tolerance to salinity with the Artificial Neural Network and other statistical methods. Canola varieties were sown in a randomized complete block experiment with four replications in two not identical irrigation conditions (normal and salinity, respectively, 0.831 dSm−1 and 8.7 dSm−1) in Kerman, Iran. The experimental outcomes (the existence of a significant difference between cultivars, as well as the significance of the environmental × cultivar interaction effect and on the other hand the non-significance, 0.021, of the correlation between cultivar's performance in two irrigation conditions) showed that there are the necessary genetic diversity between genotypes for breeding purposes. The four endurance indices including harmonic mean, stress tolerance index, mean product, and geometric mean product had positive and significant correlations with seed performance in both irrigation conditions. According to this, these four indices were the best for predicting salinity tolerant cultivars. The varieties such as Talaye, Talaieh, T98007, Ahmadi, Modena, Option 500 and PP-4010 had high yield in both environments and they are recommended for cultivation in salty soils.