This study proposes a deep learning-based model for the automated classification of brain tumors using magnetic resonance imaging (MRI) scans. The model is based on the EfficientNetB3 architecture and was trained on a dataset of 7,023 MRI images. The model achieved a 100% accuracy rate in classifying brain tumors into three categories: pituitary, meningioma, and glioma. The model's performance was evaluated using a confusion matrix, which showed a high number of true positives and a low number of false negatives. The model also demonstrated high precision with a low number of false positives. The study highlights the effectiveness of deep learning in the classification of brain tumors, as it provides a reliable and accurate method for diagnosing and categorizing brain tumors based on MRI scans. The proposed model outperforms existing systems and has the potential to be used in clinical settings for the automated detection and classification of brain tumors. The study also discusses the challenges and limitations of current brain tumor detection methods and emphasizes the importance of developing more accurate and efficient diagnostic tools for brain tumor classification. The research contributes to the field of medical imaging and deep learning by providing a novel approach for the automated classification of brain tumors using MRI scans.This study proposes a deep learning-based model for the automated classification of brain tumors using magnetic resonance imaging (MRI) scans. The model is based on the EfficientNetB3 architecture and was trained on a dataset of 7,023 MRI images. The model achieved a 100% accuracy rate in classifying brain tumors into three categories: pituitary, meningioma, and glioma. The model's performance was evaluated using a confusion matrix, which showed a high number of true positives and a low number of false negatives. The model also demonstrated high precision with a low number of false positives. The study highlights the effectiveness of deep learning in the classification of brain tumors, as it provides a reliable and accurate method for diagnosing and categorizing brain tumors based on MRI scans. The proposed model outperforms existing systems and has the potential to be used in clinical settings for the automated detection and classification of brain tumors. The study also discusses the challenges and limitations of current brain tumor detection methods and emphasizes the importance of developing more accurate and efficient diagnostic tools for brain tumor classification. The research contributes to the field of medical imaging and deep learning by providing a novel approach for the automated classification of brain tumors using MRI scans.