Pyyan / Compare / YOLO-World vs YOLO26 vs YOLOv12 vs RTMDet

YOLO-World vs YOLO26 vs YOLOv12 vs RTMDet

4 of 5

Object Detection · verified 13 Aug 2026

×YOLO-WorldTencentcurrent
×YOLO26Ultralyticscurrent
×YOLOv12Ultralyticscurrent
×RTMDetOpenMMLabcurrent
1 slot left
SpecificationYOLO-WorldYOLO26YOLOv12RTMDet
SummaryOpen-vocabulary detection at YOLO speed.The latest in the line most people mean by object detection.Attention-centric YOLO, still widely deployed.Pure throughput, and an MIT licence.
COCO mAP~46 zero-shot~55~55~52
SpeedHighVery highVery high300+
LicenceGPL-3.0AGPL-3.0AGPL-3.0MIT
FamilyOpen vocabularySingle stageSingle stageSingle stage
Open vocabularyYesNoNoNo
Released2024202620252022
CategoryObject DetectionObject DetectionObject DetectionObject Detection
OfficialTencentUltralyticsUltralyticsOpenMMLab

Highlighted rows are where these differ.

YOLO-World

  • The speed of YOLO with text-defined classes
  • Weaker than Grounding DINO on hard prompts

Best for prompted detection that has to be fast.

Full spec sheet →

YOLO26

  • Strong on Jetson, Snapdragon and ARM CPUs
  • AGPL-3.0: open-source your derivative work or buy a licence

Best for edge and mobile deployment.

Full spec sheet →

YOLOv12

  • Attention added to the classic single-stage design
  • Same licensing consideration as YOLO26

Best for teams already on the YOLO toolchain.

Full spec sheet →

RTMDet

  • Wins on raw speed where accuracy is sufficient
  • MIT, so no derivative-work obligation

Best for high frame-rate video.

Full spec sheet →