Purpose <p>Previous studies in brain tumor detection primarily focused on architectural modifications to improve performance with limited exploration into class-wise comparisons, intersection-over-union (IoU) threshold adjustments, or targeted data augmentation. The purpose of this study was to investigate the effects of the size and IoU threshold on the tumor detection and classification performance in YOLO architectures.</p> Methods <p>A publicly available Figshare dataset that contains slices with the brain tumors was used for training (<i>n</i> = 2,144), validation (<i>n</i> = 616), and testing (<i>n</i> = 304). YOLOv5n/s/m, v8n/s/m, and v11n/s/m models were used for model development. The data were labeled as one of three classes: meningioma, pituitary or glioma. To evaluate the effect of tumor size, we divided the test dataset into small, medium, and large groups. Moreover, we investigated the effect of IoU threshold on the tumor classification performance.</p> Results <p>The YOLO models’ performance depended on class type. The average precision at IoU 50% (AP@0.5) values ranged 0.969–0.989 for meningioma, 0.952–0.983 for pituitary. The glioma class showed the lowest AP@0.5 range of 0.768–0.837. The small-sized group of glioma showed significantly lower AP@0.5 values than the medium- and large-sized glioma groups. The lower the IoU threshold, the better classification performance especially in the glioma class. Image flip in coronal and axial slices for data augmentation further improved the classification performance.</p> Conclusion <p>The YOLO models can classify the small-sized glioma with higher accuracy when using slice-specific data augmentation and lowered IoU threshold, which is reasonable choice for the brain tumor detection.</p>