Compare YOLOv10 vs YOLOv8 live
Run the same image across every model that supports a task and compare their outputs side-by-side.
Run a pretrained Object Detection (COCO) model and compare detections on the same image.
Upload an image
Drag and drop an image here, or click to browse
YOLOv10YOLOv10 vs YOLOv8 on COCO
At similar sizes, YOLOv10 Large (25.8M params) scores 52.3 and YOLOv8 Medium (25.9M) scores 49.2.
COCO val2017 mAP 50:95 against parameter count, one point per size · from leaderboard.roboflow.com
YOLOv10 vs YOLOv8 Comparison Table
| Property | YOLOv10 | YOLOv8 |
|---|---|---|
| Organization | THU-MIG | Ultralytics |
| Category | open | open |
| Modality | vision | vision |
| Release Date | May 2024 | Jan 2023 |
| Context Window | — | — |
| Parameters | 2.3M-29.5M | 3.2M-68.2M |
| License | AGPL 3.0 | AGPL 3.0 |
| Commercial use | commercial use needs a license (included on Roboflow cloud) | commercial use needs a license (included on Roboflow cloud) |
| COCO Benchmark object detection, mAP 50:95 on COCO val2017 | ||
| Best size | 53.6XL · 31.7M params | 52.9XL · 68.2M params |
| Smallest size | 38.0Nano · 2.8M params | 36.5Nano · 3.2M params |
| mAP range | 38.0–53.6across 5 sizes | 36.5–52.9across 5 sizes |
| Model Sizes COCO mAP 50:95, tested resolution and params per size | ||
| Nano | 38.0640×640 · 2.8M params | 36.5640×640 · 3.2M params |
| Small | 45.7640×640 · 8.1M params | 44.1640×640 · 11.2M params |
| Medium | 50.3640×640 · 16.5M params | 49.2640×640 · 25.9M params |
| Large | 52.3640×640 · 25.8M params | 51.8640×640 · 43.7M params |
| XL | 53.6640×640 · 31.7M params | 52.9640×640 · 68.2M params |
| COCO val2017 mAP 50:95 and parameter counts from leaderboard.roboflow.com. Size names don't line up across model families, so compare sizes with similar parameter counts. The live demo runs some of these sizes at other resolutions, which were not benchmarked. | ||
| Vision Tasks | ||
Both support 1 more task | ||
| Model Features | ||
| Real-Time Vision | Not listed | Supported |
YOLOv10 vs YOLOv8: Overview
YOLOv10 is a real-time end-to-end object detection model developed by THU-MIG at Tsinghua University, released in May 2024 under the AGPL-3.0 license. It introduces consistent dual assignments during training — using both one-to-many and one-to-one label assignment strategies — to eliminate the need for non-maximum suppression at inference time while maintaining competitive accuracy. This end-to-end design reduces inference latency compared to NMS-dependent detectors at similar accuracy levels.
YOLOv10-B achieves 52.7% AP on COCO with 46% lower latency than YOLOv9-C at comparable performance. The model is available in six sizes from Nano to Extra Large, built on the Ultralytics framework, and exportable to ONNX, TensorRT, and CoreML. YOLOv10 is suited for latency-sensitive deployment scenarios where post-processing overhead is a constraint.
YOLOv8 is an object detection and multi-task vision model developed by Ultralytics, released in January 2023 under the AGPL-3.0 license. It succeeds YOLOv5 and introduces an anchor-free detection head, a new C2f module for improved gradient flow, and a decoupled head that separates classification and regression tasks. These changes improve both accuracy and training efficiency compared to earlier Ultralytics models.
YOLOv8 supports object detection, instance segmentation, image classification, pose estimation, and oriented bounding box detection within a unified codebase. It is available in five sizes from Nano to Extra Large and exports to ONNX, TensorRT, CoreML, and other formats. YOLOv8 is one of the most widely adopted detection models in production and is directly supported by Roboflow Inference for custom model training and deployment.
