Automated detection of electronic components on printed circuit boards (PCBs) is essential for modern electronics manufacturing, quality control, and defect detection. This study evaluates the performance of five variants of the YOLO11 object detection algorithm, YOLO11n, YOLO11s, YOLO11m, YOLO11l, and YOLO11x, for detecting four key PCB components: capacitors, LEDs, resistors, and resistor arrays. The objective is to assess the trade-offs between model complexity, detection accuracy, and computational efficiency to determine the most suitable YOLO11 variant for automated PCB inspection. A dataset of annotated PCB images was used to train and evaluate all YOLO11 variants under standardized conditions, incorporating data augmentation techniques for improved generalization. The models were assessed using precision, recall, F1-score, and mean Average Precision (mAP) at various IoU thresholds (mAP50, mAP75, and mAP50:95). Results indicate that larger models exhibit superior detection accuracy, with YOLO11x achieving the highest mAP50 values: 0.953 for capacitors, 0.977 for LEDs, 0.904 for resistors, and 0.939 for resistor arrays. In contrast, YOLO11n had the lowest accuracy, with mAP50 values of 0.623, 0.659, 0.551, and 0.602, respectively. One-way ANOVA confirmed statistically significant differences across models (p < 0.001), with the post-hoc Tukey’s HSD tests showing YOLO11x significantly outperforms YOLO11n, especially for LEDs and resistor arrays. Beyond accuracy, computational efficiency was analyzed, revealing that YOLO11x, while the most accurate, demands higher computational resources, making it less ideal for real-time applications.