DETR vs RF-DETR
Compare DETR and RF-DETR side-by-side.
Compare DETR vs RF-DETR 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
DETR vs RF-DETR Comparison Table
Evals updated October 13, 2026Pricing updated October 23, 2026
| Property | DETR | RF-DETR |
|---|---|---|
| Organization | Meta | Roboflow |
| Category | open | open |
| Modality | vision | vision |
| Release Date | May 2020 | Mar 2025 |
| Context Window | — | — |
| Parameters | ~41M | 30.5M-126.9M |
| License | Apache 2.0 | Apache 2.0 |
| Commercial use | free for commercial use | free for commercial use (XL and 2XL: PML 1.0, included on Roboflow cloud) |
| COCO Benchmark object detection, mAP 50:95 on COCO val2017 | ||
| Best size | Not benchmarked | 59.92XL · 126.9M params |
| Smallest size | Not benchmarked | 48.4Nano · 30.5M params |
| mAP range | Not benchmarked | 48.4–59.9across 6 sizes |
| Model Sizes COCO mAP 50:95, tested resolution and params per size | ||
| Nano | Not available | 48.4384×384 · 30.5M params |
| Small | Not available | 53.0512×512 · 32.1M params |
| Medium | Not available | 54.8576×576 · 33.7M params |
| Large | Not available | 56.3704×704 · 33.9M params |
| XL | Not available | 58.5700×700 · 126.4M params |
| 2XL | Not available | 59.9880×880 · 126.9M params |
| COCO val2017 mAP 50:95 and parameter counts from leaderboard.roboflow.com. Size names don't line up across model families, so compare sizes with similar parameter counts. | ||
| Vision Tasks | ||
| Object Detection | Supported | Demo (COCO) |
| Model Features | ||
| Foundation Vision | Supported | Not listed |
| Real-Time Vision | Not listed | Supported |
DETR vs RF-DETR: Overview
DETR (Detection Transformer) is an end-to-end object detection model developed by Facebook Research (Meta), released in May 2020. It is one of the first models to eliminate hand-crafted components such as anchor generation and non-maximum suppression by framing object detection as a direct set prediction problem, solved with a transformer encoder-decoder architecture built on top of a CNN backbone.
DETR achieves 42.0% AP on the COCO benchmark with a ResNet-50 backbone, performing comparably to a well-tuned Faster R-CNN at the time of release. Its attention-based design allows it to reason about global context and long-range dependencies within an image. DETR is primarily used as a research baseline and architectural reference, with subsequent works such as Deformable DETR and DINO building on its foundations to address its slower training convergence and limited small-object detection capability.
RF-DETR is a real-time transformer-based object detection model developed by Roboflow, with code and weights first released in March 2025. RF-DETR Nano, Small, Medium, and Large are released under the Apache 2.0 license, so they're commercially usable out of the box: you can ship them in closed-source, commercial products, including self-hosted deployments, without paying a license fee or open-sourcing your code. RF-DETR XL and 2XL use the Roboflow Platform Model License (PML 1.0): commercial use is included when you deploy on Roboflow, and commercial self-hosting requires the Enterprise add-on. It is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark, built on a DINOv2 vision transformer backbone with weight-sharing neural architecture search used to identify accuracy-latency trade-offs. The full family spans six sizes from Nano (30.5M parameters, 384×384 input) to 2XL (126.9M parameters, 880×880 input), with the accompanying research paper accepted to ICLR 2026.
RF-DETR is designed for strong domain adaptability, achieving state-of-the-art performance on RF100-VL, a benchmark measuring generalization to real-world object detection tasks across diverse domains. It is deployable through Roboflow Inference and supports fine-tuning on custom datasets, making it well suited for domain-specific applications with limited training data.
