Compare YOLO26 vs YOLOv10 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
YOLOv10YOLO26 vs YOLOv10 on COCO
At similar sizes, YOLO26 Large (24.8M params) scores 53.6 and YOLOv10 Large (25.8M) scores 52.3.
COCO val2017 mAP 50:95 against parameter count, one point per size · from leaderboard.roboflow.com
YOLO26 vs YOLOv10 Comparison Table
| Property | YOLO26 | YOLOv10 |
|---|---|---|
| Organization | Ultralytics | THU-MIG |
| Category | open | open |
| Modality | vision | vision |
| Release Date | Oct 2025 | May 2024 |
| Context Window | — | — |
| Parameters | 2.4M-55.7M | 2.3M-29.5M |
| 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 | 56.3Extra Large · 55.7M params | 53.6XL · 31.7M params |
| Smallest size | 39.9Nano · 2.4M params | 38.0Nano · 2.8M params |
| mAP range | 39.9–56.3across 5 sizes | 38.0–53.6across 5 sizes |
| Model Sizes COCO mAP 50:95, tested resolution and params per size | ||
| Nano | 39.9640×640 · 2.4M params | 38.0640×640 · 2.8M params |
| Small | 47.2640×640 · 9.5M params | 45.7640×640 · 8.1M params |
| Medium | 52.0640×640 · 20.4M params | 50.3640×640 · 16.5M params |
| Large | 53.6640×640 · 24.8M params | 52.3640×640 · 25.8M params |
| XL | 56.3640×640 · 55.7M params | 53.6640×640 · 31.7M 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. | ||
| Vision Tasks | ||
| Instance Segmentation | Demo (COCO) | Not listed |
Both support 1 more task | ||
YOLO26 vs YOLOv10: Overview
YOLO26 is a real-time object detection model developed by Ultralytics, released in October 2025. It introduces a native end-to-end, NMS-free architecture that eliminates the Non-Maximum Suppression post-processing step, reducing CPU latency by up to 43% for the Nano variant compared to NMS-dependent versions. The model incorporates the MuSGD optimizer and ProgLoss with STAL for improved training stability and small-object detection, and removes Distribution Focal Loss to ensure maximum compatibility with ONNX and TensorRT export targets.
YOLO26 supports object detection, instance segmentation, pose estimation, and oriented bounding box detection within a unified framework, with model sizes available from Nano to Extra Large. Its NMS-free design makes it particularly well suited for deployment scenarios where post-processing overhead is a bottleneck, such as embedded systems and real-time edge inference pipelines.
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.
