Real-time YOLO object detection
Find and localize objects in images and video with Ultralytics YOLO26 detection models. Train on your own data, evaluate with clear metrics, and deploy in real time on edge, cloud, and mobile.
YOLO26 detection models
Object detection is the foundation task of the YOLO26 family, with five model sizes covering everything from embedded CPUs to accuracy-critical cloud workloads. Every size trains on your own data with the same three-line API and exports to the format your hardware runs best.
pip install ultralyticsfrom ultralytics import YOLO
# Load a YOLO26 detection model
model = YOLO("yolo26n.pt")
# Run inference
results = model("image.jpg")| Model | Size (px) | mAP 50-95 | mAP 50-95 (e2e) | CPU ONNX (ms) | T4 TensorRT (ms) | Params (M) | FLOPs (B) |
|---|---|---|---|---|---|---|---|
| YOLO26n | 640 | 40.9 | 40.1 | 38.9 ± 0.7 | 1.7 ± 0.0 | 2.4 | 5.4 |
| YOLO26s | 640 | 48.6 | 47.8 | 87.2 ± 0.9 | 2.5 ± 0.0 | 9.5 | 20.7 |
| YOLO26m | 640 | 53.1 | 52.5 | 220.0 ± 1.4 | 4.7 ± 0.1 | 20.4 | 68.2 |
| YOLO26l | 640 | 55.0 | 54.4 | 286.2 ± 2.0 | 6.2 ± 0.2 | 24.8 | 86.4 |
| YOLO26x | 640 | 57.5 | 56.9 | 525.8 ± 4.0 | 11.8 ± 0.2 | 55.7 | 193.9 |
YOLO26 detection benchmarks from the Ultralytics docs.
Trusted by the world's leading organizations
Our models' impact
Streamline processes across industries with our cutting-edge vision AI models. Speed, accuracy and ease-of-use powered by Ultralytics.
The evolution of Ultralytics YOLO models
See how Ultralytics YOLO evolved from the practical YOLOv5 workflow to edge-ready YOLO26 inference.
Label up to 10x faster with smart annotation
Ultralytics Platform gives you the image annotation tool to build high-quality datasets faster. From smart annotation to precise manual editing, these features are designed to reduce image labeling time without sacrificing quality.
- SAM-powered smart annotation: Masks and bounding boxes in one click.
- Full AI task coverage: Detection, instance segmentation, semantic segmentation, classification, pose, OBB.
- Universal format support: Your choice of YOLO, COCO, and more.
- Team review and versioning: Clear collaboration at every step.
Train on the Best GPUs for Less
26 NVIDIA GPUs starting at $0.24/hr — from Ampere to Blackwell. No markup, no minimums, no commitment.
Explore industry solutions
See how teams apply Ultralytics computer vision across production environments.
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Agriculture
Automotive
Healthcare
Logistics
Manufacturing
Retail
Robotics
Frequently asked questions
Object detection identifies objects in an image or video frame and localizes each one with a bounding box and class label. Ultralytics YOLO models perform detection in a single pass, which is why they run in real time on hardware from edge devices to cloud GPUs. Detection is the foundation task of the Ultralytics YOLO family and the starting point for tracking, counting, and analytics workflows.
Ultralytics YOLO26 is the latest stable generation and the recommended choice for new detection projects. Its end-to-end, NMS-free design simplifies deployment, and the nano variant is optimized for CPU and edge inference. Earlier families like YOLO11 and YOLOv5u remain supported through the same API.
Use the Ultralytics library's train mode with your dataset in YOLO format, or use Ultralytics Platform to annotate images, train on cloud GPUs, and manage runs from the browser. Starting from pretrained weights is recommended: fine-tuning converges faster and needs less data than training from scratch.
Detection models are evaluated with precision, recall, and mean average precision (mAP) computed across IoU thresholds. Ultralytics validation reports these metrics for every class automatically. The model evaluation guide explains how to interpret them and improve your dataset and training setup.
Use export mode to convert trained detectors to formats such as ONNX, TensorRT, CoreML, OpenVINO, and LiteRT for your target hardware. YOLO26's NMS-free design keeps the exported graph simple, and benchmark mode compares speed and accuracy across formats before you ship.
Build object detection with Ultralytics
Annotate data, train YOLO26 detectors, and deploy them anywhere with Ultralytics Platform.