SAM 3
Type 'yellow school bus' — it masks every single one
Latest: SAM 3.1 (Mar 27, 2026) — multiplexing tracks up to 16 objects per forward pass, doubling video throughput from 16 to 32 fps on one H100
The first SAM that understands language: an 848M-parameter unified detector-plus-tracker that finds, segments, and tracks every instance of a concept from a short text phrase ('red baseball cap') or image exemplar, across images and video. Released November 19, 2025 with open checkpoints, alongside the browser-based Segment Anything Playground.
Why it matters
SAM 3 gave Segment Anything language: type 'yellow school bus' and it finds, masks and tracks every instance across images and video, reaching 75-80% of human performance on a 270,000-concept benchmark. It ships inside Instagram Edits and Meta AI, and the 3.1 update doubled video throughput to 32 fps on one H100.
Facts
- You type 'yellow school bus' and it finds and masks every single one — in video, in near real time.
- Its SA-Co benchmark covers 270,000 unique concepts — over 50x more than prior benchmarks — and SAM 3 reaches 75-80% of human performance on it.
- It ships in real products: object-level video effects in Instagram's Edits app and Meta AI.
- Meta also released SA-FARI, a wildlife dataset of 10,000+ camera-trap videos spanning 100+ species.
- Its data engine produced 4M unique concept labels with hard negatives.
Try it yourself
Segment Anything Playground ↗ Weights on Hugging Face ↗ Run the official notebook in Colab ↗
Lineage
Sources
arXiv ↗GitHub · sam3 ↗Meta AI blog ↗Meta AI research ↗Meta Newsroom ↗