The prevalence of brain tumors and the complexity of their treatment demand advancements in early detection techniques, where machine learning (ML) plays a pivotal role. This paper provides a comprehensive survey of various ML models that have been developed and employed for the detection and classification of brain tumors, focusing primarily on magnetic resonance imaging (MRI) data. A range of ML approaches, including Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and more recent advancements such as hybrid models combining CNNs with Recurrent Neural Networks (RNNs), are discussed in depth. The effectiveness of these models is evaluated based on their accuracy, sensitivity, specificity, and computational efficiency, crucial metrics for clinical applications. This study also explores the challenges of implementing ML models in medical settings, such as data privacy, the need for extensive data sets for training, and the computational demands of model training and inference. The paper highlights the significant potential of ML to revolutionize the field of neuro-oncology by providing tools that can predict and classify brain tumors with high precision, thereby facilitating faster and more accurate diagnosis, tailored treatment plans, and ultimately, better patient outcomes. This survey aims to guide future research and practical applications of ML in brain tumor detection.