The main objective of this paper is to implement various machine-learning algorithms for brain tumor detection and classification to choose the best algorithm. The early stage of brain tumor detection is a crucial task. Detecting and classifying brain tumors can be done by examining the biopsy, which can be done by definitive brain surgery. Initially, all the images are preprocessed, segmented, and processed by machine learning algorithms. Some of the machine learning algorithms, including Logistic Regression, Support Vector Machine, K-Nearest Neighbours, Naïve Bayes, Random Forests, K-Means Clustering, and Neural Networks, are examined with their experimental results. Accuracy, Precision, Recall, and F1-Score are calculated using true positive, false positive, true negative, and false negative values. The comparison shows that the logistic regression and random forest obtained 96% accuracy, and the neural Network obtained 95% accuracy. These models perform well in classifying tumor and non-tumor brain images.