Ultralytics' flagship real-time detector family: five sizes (n→x) covering detection, instance segmentation, pose, OBB and classification, up to 54.7 mAP on COCO with ~11 ms TensorRT latency — the default choice for fast industrial object detection.
Ultralytics' flagship real-time detector family: five sizes (n→x) covering detection, instance segmentation, pose, OBB and classification, up to 54.7 mAP on COCO with ~11 ms TensorRT latency — the default choice for fast industrial object detection.
Save it, compare it, request a quote or record that you have used it — with an account.
YOLO11 is the flagship model family of the Ultralytics framework, refining the YOLO single-stage architecture (C3k2 blocks, C2PSA attention) for a better accuracy/latency trade-off — YOLO11m matches YOLOv8m accuracy with 22% fewer parameters. Five sizes from nano to extra-large run the same API across object detection, instance segmentation, pose estimation, oriented bounding boxes and classification. The Python-first tooling handles training, fine-tuning on custom data and one-line export to ONNX, TensorRT, OpenVINO, CoreML and TFLite, which is why it dominates production pick-and-place, palletizing and inspection deployments where per-class fine-tuning is expected.
This product is part of the Birdwave Atlas community.
Contribute evaluations, share integrations and help improve compatibility data.
Discussions, evaluations, integrations and updates