A Comparative Review of the Next-Generation YOLO Models: YOLOv10 and YOLO11

Abstract

In recent years, the YOLO (You Only Look Once) series has remained a mainstream framework in object detection, continuously driving the balance between lightweight design and high accuracy. This paper focuses on two pivotal versions—YOLOv10 and YOLO11—and provides a systematic comparison and analysis in terms of architectural design, core modules, performance characteristics, and application scenarios. YOLOv10 introduces a unified end-to-end architecture that eliminates anchors and post-processing steps, thereby simplifying the detection pipeline and significantly improving deployment efficiency. In contrast, YOLO11 builds upon YOLOv8 by reconstructing its modules through the introduction of the C3k structure and an optimized feature fusion pathway, further enhancing detection accuracy and model representation capabilities. This review outlines the similarities and differences in structural philosophy and application orientation between the two models, summarizes their technological evolution, and explores the potential future directions of the YOLO series in multi-task integration, adaptive modeling, and lightweight deployment. The findings of this study aim to serve as a reference for the design and selection of object detection systems.