PyyanThe AI Index

Pyyan / Compare / SAM 2 vs Grounding DINO

SAM 2 vs Grounding DINO

2 of 5

Object Detection · verified 13 Aug 2026

SAM 2Metacurrent
IGrounding DINOIDEA Researchcurrent
3 slots left
SpecificationSAM 2Grounding DINO
SummarySegment anything, now including video.Detects whatever you describe in words.
COCO mAPNot applicable~52 zero-shot
SpeedReal timeModerate
LicenceApache 2.0Apache 2.0
FamilySegmentationOpen vocabulary
Open vocabularyYesYes
Released20242023
CategoryObject DetectionObject Detection
OfficialMeta ↗IDEA Research ↗

Highlighted rows are where these differ.

SAM 2

  • Not a detector: it segments what you point at
  • Transformed how detection datasets get labelled

Best for segmentation and annotation.

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 →