Segment Anything Model 2 (SAM 2) vs SAM 3
We don't benchmark Segment Anything Model 2 (SAM 2) or SAM 3 on Vision Evals. Segment Anything Model 2 (SAM 2) is open-weight under Apache 2.0: free for commercial use. SAM 3 is open-weight under Custom.
Compare Segment Anything Model 2 (SAM 2) vs SAM 3 live
Run the same image across every model that supports a task and compare their outputs side-by-side.
These models don't share enough common tasks for a side-by-side demo. See the comparison table below for their capabilities.
Segment Anything Model 2 (SAM 2) vs SAM 3 Comparison Table
| Property | Segment Anything Model 2 (SAM 2) | SAM 3 |
|---|---|---|
| Organization | Meta | Meta |
| Category | open | open |
| Modality | vision | multimodal |
| Release Date | Jul 2024 | Nov 2025 |
| Context Window | — | — |
| Parameters | 38.9M-224.4M | Unknown |
| License | Apache 2.0 | Custom |
| Commercial use | free for commercial use | See license terms |
| Vision Tasks | ||
| Object Detection | Not listed | Demo |
| Open Vocabulary Object Detection | Not listed | Supported |
| Promptable Concept Segmentation | Not listed | Demo |
| Video Object Tracking | Not listed | Supported |
| Zero Shot Segmentation | Not listed | Supported |
Both support 1 more task | ||
| Model Features | ||
| Foundation Vision | Not listed | Supported |
| Multimodal Vision | Not listed | Supported |
| Zero-shot Detection | Not listed | Supported |
Segment Anything Model 2 (SAM 2) vs SAM 3: Overview
SAM 2 is a real-time image and video segmentation model developed by Meta AI, released in July 2024 under the Apache 2.0 license. It extends the original Segment Anything Model to support video inputs by introducing a streaming memory architecture that maintains object state across frames, enabling consistent segmentation of objects through occlusion, motion, and scene changes. For image inputs, SAM 2 operates similarly to its predecessor with improved mask quality and speed.
SAM 2 accepts point, box, and mask prompts and produces object masks interactively or in a fully automated mode. Its memory architecture enables video segmentation at real-time speeds. SAM 2 is used in annotation pipelines, video analysis, robotic perception, and any application requiring high-quality promptable segmentation across both images and video.
Released on November 19th, 2025, Segment Anything 3 (SAM 3) is a zero-shot image segmentation model that “detects, segments, and tracks objects in images and videos based on concept prompts.” This model was developed by Meta as the third model in the Segment Anything series.
Unlike its previous SAM models (Segment Anything and Segment Anything 2), you can provide SAM 3 with the prompt “shipping container” and it will generate precise segmentation masks for all shipping containers in an image. SAM 3 generates segmentation masks that correspond to the location of the objects found with a text prompt.
