Cancer stands as one of the leading causes of mortality across the globe, accounting for nearly 10 million deaths in 2020, or nearly one in six deaths, as per a report produced by the World Health Organization with breast cancer being the one associated with the highest prevailing deaths, summing to around 2.26 million cases. Early breast cancer prognosis has been favorable with an almost 100% 5-year survival rate, thus, considered to be the most effective approach for minimizing mortality and increasing survival rates. However, traditional breast cancer detection methods and machine learning algorithms have been quite challenging due to the complex and dynamic nature of data and factors, thus creating the need for automated breast cancer diagnosis models. In this study, we conduct a comprehensive comparison and propose an extensive, systematic evaluation of the performances of the most effective machine learning models for the detection of cancerous cells in the mammography images of breast mass tissues by comparing. The study also presents differences in the predictive capabilities of each model by highlighting their strengths and limitations for better optimization of predictive accuracy and detection, helping in the advancement of diagnosis and management of breast cancer.