Compare RF-DETR vs YOLOS 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.
RF-DETR vs YOLOS Comparison Table
| Property | RF-DETR | YOLOS |
|---|---|---|
| Organization | Roboflow | Hugging Face |
| Category | open | open |
| Modality | vision | vision |
| Release Date | Mar 2025 | Jun 2021 |
| Context Window | — | — |
| Parameters | 30.5M-126.9M | Unknown |
| License | Apache 2.0 | MIT |
| Commercial use | free for commercial use (XL and 2XL: PML 1.0, included on Roboflow cloud) | free for commercial use |
| COCO Benchmark object detection, mAP 50:95 on COCO val2017 | ||
| Best size | 59.92XL · 126.9M params | Not benchmarked |
| Smallest size | 48.4Nano · 30.5M params | Not benchmarked |
| mAP range | 48.4–59.9across 6 sizes | Not benchmarked |
| Model Sizes COCO mAP 50:95, tested resolution and params per size | ||
| Nano | 48.4384×384 · 30.5M params | Not available |
| Small | 53.0512×512 · 32.1M params | Not available |
| Medium | 54.8576×576 · 33.7M params | Not available |
| Large | 56.3704×704 · 33.9M params | Not available |
| XL | 58.5700×700 · 126.4M params | Not available |
| 2XL | 59.9880×880 · 126.9M params | Not available |
| 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 | Demo (COCO) | Supported |
| Model Features | ||
Both support 1 more feature | ||
RF-DETR vs YOLOS: Overview
RF-DETR is a real-time transformer-based object detection model developed by Roboflow, with code and weights first released in March 2025. Its largest size, 2XL, reaches 59.9 mAP 50:95 on Microsoft COCO val2017, the highest of the 60 detectors on leaderboard.roboflow.com. It is 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.
YOLOS (You Only Look at One Sequence) is a transformer-based object detection model widely distributed through Hugging Face Transformers, released in June 2021 under the MIT license. It applies a minimally adapted Vision Transformer to object detection by representing both the image and detection tokens as a flat sequence processed by standard multi-head self-attention, without convolutional components or feature pyramid networks. The architecture demonstrates that detection can be performed without region proposals or multi-scale feature fusion.
YOLOS achieves moderate performance on COCO relative to purpose-built detectors, with its primary contribution being a demonstration of the transferability of ViT pre-training to detection tasks. It is most appropriate for research contexts exploring transformer-based detection architectures and for scenarios where architectural simplicity is preferred over peak accuracy.
