RF-DETR Segmentation vs SAM 3
Compare RF-DETR Segmentation and SAM 3 side-by-side.
Compare RF-DETR Segmentation 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.
Models in this comparison
RF-DETR Segmentation vs SAM 3 Comparison Table
Evals updated October 13, 2026Pricing updated October 16, 2026
| Property | RF-DETR Segmentation | SAM 3 |
|---|---|---|
| Organization | Roboflow | Meta |
| Category | open | open |
| Modality | vision | multimodal |
| Release Date | Oct 2025 | Nov 2025 |
| Context Window | — | — |
| Parameters | 33.6M-38.6M | Unknown |
| License | Apache 2.0 | Custom |
| Commercial use | free for commercial use | See license terms |
| Model Sizes input resolution per size variant | ||
| Nano | 312×312 | Not available |
| Small | 384×384 | Not available |
| Medium | 432×432 | Not available |
| Large | 504×504 | Not available |
| XL | 624×624 | Not available |
| 2XL | 768×768 | Not available |
| Vision Tasks | ||
| Instance Segmentation | Demo (COCO) | Supported |
| 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 |
| Model Features | ||
| Foundation Vision | Not listed | Supported |
| Multimodal Vision | Not listed | Supported |
| Real-Time Vision | Supported | Not listed |
| Zero-shot Detection | Not listed | Supported |
RF-DETR Segmentation vs SAM 3: Overview
RF-DETR Segmentation is a real-time instance segmentation model developed by Roboflow, with a preview base model released in October 2025 under the Apache 2.0 license and the full variant family — Nano through 2XL — released in January 2026. Every size is Apache 2.0, so it's commercially usable out of the box: you can ship it in closed-source, commercial products without paying a license fee or open-sourcing your code. It extends the RF-DETR object detection architecture with a segmentation head inspired by MaskDINO, enabling pixel-level object delineation while maintaining the real-time performance characteristics of the base model. It is deployable through Roboflow Inference and the open-source rfdetr Python package.
RF-DETR Segmentation supports fine-tuning on custom COCO- or YOLO-format instance segmentation datasets and is benchmarked on Microsoft COCO. It is suited for applications requiring both precise object masks and real-time inference, such as robotic manipulation, quality control, and augmented reality overlays.
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.
