Breast cancer is cancer that forms in the cells of the breasts. Breast cancer is the most diagnosed cancer in women. Breast cancer can occur in both men and women, but it's far more common in women. Detection of disease in its advanced stages and treatment can greatly improve the survival rate of patients. In this paper, we use new hybrid methods namely support vector machine (SVM) and Gray wolf optimizer (GWO) for detecting the type of the breast tumor whether malignant or benign. We compare predictive performance of this hybrid model with SVM for the breast cancer data available from the Wisconsin from UCI machine learning with a total 569 rows and 32 columns. Results presented in this paper showed that the proposed GWO-SVM model has a fast convergence speed and achieve accuracy better than SVM.