From YOLOv1 to YOLO26: A Unified Comparative Review of the Evolution, Architecture, and Applications of YOLO-Based Object Detection Frameworks

Object detection has evolved from classical feature-based methods to deep-learning frameworks, with the YOLO (You Only Look Once) family becoming one of the most widely adopted paradigms for real-time detection. Despite rapid architectural change from YOLOv1 to YOLO26, the literature remains fragmented, lacking a unified synthesis that integrates structural innovations, quantitative benchmarking, and domain-specific deployment. This review provides a longitudinal analysis of the YOLO lineage—from Darknet backbones to hypergraph-enhanced correlation modeling (YOLOv13) and end-to-end, NMS-free architectures (YOLO26), and from anchor-based to anchor-free, decoupled, and end-to-end heads. We compile and harmonize source-reported metrics (mAP, FPS, FLOPs, parameters) across canonical datasets (PASCAL VOC, MS COCO, KITTI) and domain benchmarks, treating the result as a cross-source synthesis rather than hardware-normalized re-benchmarking. Recent 2025–2026 advances are highlighted: YOLOv13 reports a +3.0% mAP@[0.5:0.95] gain over YOLO11-N (38.6%→41.6%) through high-order correlation modeling, while YOLO26 reports up to 43% faster CPU inference relative to YOLO11. Through a multi-sector analysis across seven application domains, we map design choices to operational constraints, identify persistent challenges (domain generalization, small-object localization, open-set detection), and outline a research agenda emphasizing hybrid correlation-enhancement architectures, deployment-centric training, data-efficient learning, and sustainability-aware benchmarking.