YOLOv12 vs YOLOv8 Instance Segmentation
We don't benchmark YOLOv12 or YOLOv8 Instance Segmentation on Vision Evals. Both are open-weight under AGPL 3.0, so commercial use needs a license (included on Roboflow cloud).
Compare YOLOv12 vs YOLOv8 Instance Segmentation 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 Instance Segmentation Comparison Table
| Property | YOLOv12 | YOLOv8 Instance Segmentation |
|---|---|---|
| Organization | THU-MIG | Ultralytics |
| Category | open | open |
| Modality | vision | vision |
| Release Date | Feb 2025 | Jan 2023 |
| Context Window | — | — |
| Parameters | 2.6M-59.1M | 2.7M-62.8M |
| 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) |
| Model Sizes input resolution per size variant | ||
| Nano | Not available | 1280×1280, 640×640 |
| Small | Not available | 1280×1280, 640×640 |
| Medium | Not available | 1280×1280, 640×640 |
| Large | Not available | 1280×1280, 640×640 |
| XL | Not available | 1280×1280, 640×640 |
| Vision Tasks | ||
| Instance Segmentation | Supported | Demo (COCO) |
| Classification | Supported | Not listed |
| Object Detection | Supported | Not listed |
| Pose Estimation | Supported | Not listed |
| Model Features | ||
Both support 1 more feature | ||
YOLOv12 vs YOLOv8 Instance Segmentation: 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 Instance Segmentation is the segmentation variant of the YOLOv8 model developed by Ultralytics, released in January 2023 under the AGPL-3.0 license. It extends the standard YOLOv8 detection head with a mask prediction branch that generates pixel-level segmentation masks for each detected object using a prototype mask approach. This enables real-time instance segmentation within a single forward pass.
YOLOv8 Instance Segmentation shares the same backbone and neck architecture as the base detection model and is available in the same size range. It is deployable through Roboflow Inference and supports fine-tuning on custom COCO-format segmentation datasets. It is suited for applications requiring both object localization and precise mask prediction at real-time speeds.