Pyyan / Compare / RTMDet vs YOLO26 vs Grounding DINO

RTMDet vs YOLO26 vs Grounding DINO

3 of 5

Object Detection · verified 13 Aug 2026

×RTMDetOpenMMLabcurrent
×YOLO26Ultralyticscurrent
×IGrounding DINOIDEA Researchcurrent
2 slots left
SpecificationRTMDetYOLO26Grounding DINO
SummaryPure throughput, and an MIT licence.The latest in the line most people mean by object detection.Detects whatever you describe in words.
COCO mAP~52~55~52 zero-shot
Speed300+Very highModerate
LicenceMITAGPL-3.0Apache 2.0
FamilySingle stageSingle stageOpen vocabulary
Open vocabularyNoNoYes
Released202220262023
CategoryObject DetectionObject DetectionObject Detection
OfficialOpenMMLabUltralyticsIDEA Research

Highlighted rows are where these differ.

RTMDet

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

Best for high frame-rate video.

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 →

Grounding DINO

  • Text prompt in, boxes out
  • Fine-tuning still beats it on specialised objects

Best for classes you have no data for.

Full spec sheet →