Model comparison · YOLO12 vs YOLOv10
YOLO12 vs YOLOv10
A size-tier-by-size-tier comparison of YOLO12 and YOLOv10: published COCO accuracy, parameter counts, licensing and which one to reach for. Every figure is the model authors' own, linked to its source.
mAP comparison
YOLO12
- Nano 40.6
- Small 48.0
- Medium 52.5
- Large 53.7
- Extra large 55.2
YOLOv10
- Nano 38.5
- Small 46.3
- Medium 51.1
- Large 53.2
- Extra large 54.4
Accuracy and size, tier by tier
Each row pairs the equivalent rung of both size ladders, so the numbers sit side by side at comparable capacity. Every figure is the model authors’ own.
- COCO mAP50-95 @ 640px
- mAP: higher is better
- Params (M): lower is better
| Tier | YOLO12 | YOLOv10 | Δ mAP | ||||
|---|---|---|---|---|---|---|---|
| Model | mAP | Params | Model | mAP | Params | ||
| Nano | YOLO12n | 40.6 | 2.6M | YOLOv10n | 38.5 | 2.3M | +2.1 |
| Small | YOLO12s | 48.0 | 9.3M | YOLOv10s | 46.3 | 7.2M | +1.7 |
| Medium | YOLO12m | 52.5 | 20.2M | YOLOv10m | 51.1 | 15.4M | +1.4 |
| Large | YOLO12l | 53.7 | 26.4M | YOLOv10l | 53.2 | 24.4M | +0.5 |
| Extra large | YOLO12x | 55.2 | 59.1M | YOLOv10x | 54.4 | 29.5M | +0.8 |
Δ mAP is YOLO12 minus YOLOv10: positive means YOLO12 is ahead at that tier. Sources: YOLO12 docs · YOLO12 paper · YOLOv10 docs · YOLOv10 paper
YOLOv10 also ships YOLOv10b, which sits between the rungs above and has no direct counterpart in YOLO12, so it is left out of the paired rows rather than matched to an unequal one.
Additional information
YOLO12 posts the higher published COCO mAP at all 5 matched size tiers, averaging 1.30 mAP ahead of YOLOv10. The gap is widest at the nano tier, where YOLO12 leads by 2.1 mAP. At the top of each range, YOLO12 reaches 55.2 mAP against 54.4.
50% fewer parameters at the extra large tier. YOLOv10x reaches 54.4 mAP from 29.5M parameters against YOLO12x at 55.2 mAP from 59.1M, so the saving costs 0.8 mAP. No checkpoint from either family matches a larger one from the other outright.
Parameter count is not latency. It is a good proxy for download size and memory, but throughput depends on your hardware, batch size and export format, so measure on your own target.
YOLO12
The attention-centric generation, between YOLO11 and YOLO26.
- Released
- 2025 · Tian, Ye & Doermann (UB / UCAS)
- License
- AGPL-3.0
- Framework
- Ultralytics (PyTorch)
- Tasks
- Detect, Segment, Classify, Pose, OBB
An attention-centric YOLO: area attention and residual ELAN blocks replace some of the pure-convolution stack, buying about a point of mAP over YOLO11 at a similar size.
Download YOLO12 weights →YOLOv10
The first popular NMS-free, end-to-end YOLO.
- Released
- 2024 · Tsinghua University (THU-MIG)
- License
- AGPL-3.0
- Framework
- Built on Ultralytics (PyTorch)
- Tasks
- Detect
The first widely used YOLO that skips the NMS post-processing step, using paired training heads so inference is truly end to end and low latency.
Download YOLOv10 weights →YOLO12 and YOLOv10 against the whole lineage
YOLO12 and YOLOv10 against every other detector here, on one shared scale. The rest are dimmed; hover any row to bring it back.
| Model | Released | mAP range | Params range | Licence |
|---|---|---|---|---|
| YOLO26 | 2026 | 40.9 to 57.5 | 2.4M to 55.7M | AGPL-3.0 |
| YOLO12 | 2025 | 40.6 to 55.2 | 2.6M to 59.1M | AGPL-3.0 |
| YOLO11 | 2024 | 39.5 to 54.7 | 2.6M to 56.9M | AGPL-3.0 |
| YOLOv10 | 2024 | 38.5 to 54.4 | 2.3M to 29.5M | AGPL-3.0 |
| YOLOv9 | 2024 | 38.3 to 55.6 | 2.0M to 58.1M | GPL-3.0 |
| YOLOv8 | 2023 | 37.3 to 53.9 | 3.2M to 68.2M | AGPL-3.0 |
| YOLOv5 (v5u) | 2020 | 34.3 to 53.2 | 2.6M to 97.2M | AGPL-3.0 |
Every matchup
Looking for the weights themselves? Download any of these checkpoints from the model-weights hub, or see how the trackers behind them compare in the YOLO tracker benchmarks.