Compare YOLOv12 vs YOLOv8 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.
YOLOv12 vs YOLOv8 Comparison Table
| Property | YOLOv12 | YOLOv8 |
|---|---|---|
| Organization | THU-MIG | Ultralytics |
| Category | open | open |
| Modality | vision | vision |
| Release Date | Feb 2025 | Jan 2023 |
| Context Window | — | — |
| Parameters | 2.6M-59.1M | 3.2M-68.2M |
| License | AGPL 3.0 | AGPL 3.0 |
| Commercial use | commercial use needs a license (included on Roboflow cloud) | commercial use needs a license (included on Roboflow cloud) |
| COCO Benchmark object detection, mAP 50:95 on COCO val2017 | ||
| Best size | Not benchmarked | 52.9XL · 68.2M params |
| Smallest size | Not benchmarked | 36.5Nano · 3.2M params |
| mAP range | Not benchmarked | 36.5–52.9across 5 sizes |
| Model Sizes COCO mAP 50:95, tested resolution and params per size | ||
| Nano | Not available | 36.5640×640 · 3.2M params |
| Small | Not available | 44.1640×640 · 11.2M params |
| Medium | Not available | 49.2640×640 · 25.9M params |
| Large | Not available | 51.8640×640 · 43.7M params |
| XL | Not available | 52.9640×640 · 68.2M 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. The live demo runs some of these sizes at other resolutions, which were not benchmarked. | ||
| Vision Tasks | ||
| Object Detection | Supported | Demo (COCO) |
| Classification | Supported | Not listed |
| Instance Segmentation | Supported | Not listed |
| Pose Estimation | Supported | Not listed |
| Model Features | ||
Both support 1 more feature | ||
YOLOv12 vs YOLOv8: Overview
YOLOv12 is an attention-centric real-time object detection model developed by researchers at Tsinghua University, with the arXiv paper published in February 2025 under the AGPL-3.0 license. It introduces an Area Attention module that partitions feature maps into regions and applies self-attention within each region, reducing the quadratic complexity of full self-attention while capturing long-range dependencies. It also incorporates R-ELAN for improved feature aggregation and scaled residual connections for training stability.
YOLOv12-L achieves 54.0% AP on COCO, while the YOLOv12-N variant achieves 40.5% mAP at 1.62ms latency on an NVIDIA T4 GPU. The model is built on the Ultralytics codebase, supporting detection, segmentation, and other standard YOLO tasks at competitive real-time speeds.
YOLOv8 is an object detection and multi-task vision model developed by Ultralytics, released in January 2023 under the AGPL-3.0 license. It succeeds YOLOv5 and introduces an anchor-free detection head, a new C2f module for improved gradient flow, and a decoupled head that separates classification and regression tasks. These changes improve both accuracy and training efficiency compared to earlier Ultralytics models.
YOLOv8 supports object detection, instance segmentation, image classification, pose estimation, and oriented bounding box detection within a unified codebase. It is available in five sizes from Nano to Extra Large and exports to ONNX, TensorRT, CoreML, and other formats. YOLOv8 is one of the most widely adopted detection models in production and is directly supported by Roboflow Inference for custom model training and deployment.
