Is YOLOv10 better than YOLOv8?

On published COCO accuracy, YOLOv10. It leads 5 of the 5 size tiers where both families publish a figure, by an average of 0.9 mAP. The gap is widest at the small tier, where YOLOv10 is ahead by 1.4 mAP. YOLOv10 tops out at 54.4 mAP and YOLOv8 at 53.9. "Better" still depends on your constraint, though: accuracy is one axis and parameter count, task coverage and licence are the others, all of which are in the table above.

What is the difference between YOLOv10 and YOLOv8?

YOLOv10 (Tsinghua University (THU-MIG), 2024) and YOLOv8 (Ultralytics, 2023) are 1 year apart. The first popular NMS-free, end-to-end YOLO. The workhorse that made anchor-free multi-task YOLO mainstream. Task coverage differs too: YOLOv10 supports 1 (Detect) against YOLOv8's 5 (Detect, Segment, Classify, Pose, OBB).

Which is smaller, YOLOv10 or YOLOv8?

YOLOv10 gets more out of each parameter. YOLOv10x reaches 54.4 mAP on 29.5M parameters, matching or beating YOLOv8x at 68.2M: about 57% fewer parameters for the same accuracy. That is the comparison worth making, since it is the same result from a smaller checkpoint.

Is YOLOv10 faster than YOLOv8?

Nothing on this page is a speed measurement, and it would be dishonest to imply one: every figure here is published COCO accuracy and parameter count. Parameters are a rough guide to inference cost within one family, but they do not transfer across architectures, and the post-processing step matters as much as the backbone. Export both to ONNX and measure on your own hardware and footage, which is the only comparison that predicts what you will actually get.

Are YOLOv10 and YOLOv8 free for commercial use?

Both ship under AGPL-3.0, so the licence is not a tiebreaker here: choose on accuracy and size. AGPL-3.0 is free for open-source, research and internal use, but a closed-source product or paid service needs an Ultralytics Enterprise licence. Read the licence text before you ship; this is a plain reading of it, not legal advice.

Model comparison · YOLOv10 vs YOLOv8

YOLOv10 vs YOLOv8

A size-tier-by-size-tier comparison of YOLOv10 and Ultralytics YOLOv8: published COCO accuracy, parameter counts, licensing and which one to reach for. Every figure is the model authors' own, linked to its source.

CompareYOLOv10

AgainstYOLOv8

57%fewer params

mAP comparison

YOLOv10YOLOv8

YOLOv10

Nano 38.5
Small 46.3
Medium 51.1
Large 53.2
Extra large 54.4

YOLOv8

Nano 37.3
Small 44.9
Medium 50.2
Large 52.9
Extra large 53.9

COCO mAP at 640px, as published by each model’s authors. The y axis spans 34.5 to 57.0 rather than starting at zero, so small differences stay visible. Points are the published checkpoints; the joining lines are for reading order only.

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

YOLOv10 and YOLOv8 compared at each size tier: published COCO mAP50-95 at 640px and parameter counts in millions.
Tier	YOLOv10			YOLOv8			Δ mAP
Tier	Model	mAP	Params	Model	mAP	Params	Δ mAP
Nano	YOLOv10n	38.5	2.3M	YOLOv8n	37.3	3.2M	+1.2
Small	YOLOv10s	46.3	7.2M	YOLOv8s	44.9	11.2M	+1.4
Medium	YOLOv10m	51.1	15.4M	YOLOv8m	50.2	25.9M	+0.9
Large	YOLOv10l	53.2	24.4M	YOLOv8l	52.9	43.7M	+0.3
Extra large	YOLOv10x	54.4	29.5M	YOLOv8x	53.9	68.2M	+0.5

Δ mAP is YOLOv10 minus YOLOv8: positive means YOLOv10 is ahead at that tier. Sources: YOLOv10 docs · YOLOv10 paper · YOLOv8 docs

YOLOv10 also ships YOLOv10b, which sits between the rungs above and has no direct counterpart in YOLOv8, so it is left out of the paired rows rather than matched to an unequal one.

Additional information

YOLOv10 posts the higher published COCO mAP at all 5 matched size tiers, averaging 0.86 mAP ahead of YOLOv8. The gap is widest at the small tier, where YOLOv10 leads by 1.4 mAP. At the top of each range, YOLOv10 reaches 54.4 mAP against 53.9.
57% fewer parameters, same accuracy. YOLOv10x reaches 54.4 mAP from 29.5M parameters, matching or beating YOLOv8x at 53.9 mAP from 68.2M.
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.

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 →

YOLOv8

The workhorse that made anchor-free multi-task YOLO mainstream.

Released: 2023 · Ultralytics
License: AGPL-3.0
Framework: Ultralytics (PyTorch)
Tasks: Detect, Segment, Classify, Pose, OBB

The anchor-free model that made multi-task YOLO mainstream: one architecture for detection, segmentation, pose, classification and OBB, with the largest ecosystem.

Download YOLOv8 weights →

YOLOv10 and YOLOv8 against the whole lineage

YOLOv10 and YOLOv8 against every other detector here, on one shared scale. The rest are dimmed; hover any row to bring it back.

Every YOLO detector in this section, with release year, publisher, published COCO mAP50-95 range at 640px, parameter-count range and licence.
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

Frequently asked questions

Is YOLOv10 better than YOLOv8?: On published COCO accuracy, YOLOv10. It leads 5 of the 5 size tiers where both families publish a figure, by an average of 0.9 mAP. The gap is widest at the small tier, where YOLOv10 is ahead by 1.4 mAP. YOLOv10 tops out at 54.4 mAP and YOLOv8 at 53.9. "Better" still depends on your constraint, though: accuracy is one axis and parameter count, task coverage and licence are the others, all of which are in the table above.
What is the difference between YOLOv10 and YOLOv8?: YOLOv10 (Tsinghua University (THU-MIG), 2024) and YOLOv8 (Ultralytics, 2023) are 1 year apart. The first popular NMS-free, end-to-end YOLO. The workhorse that made anchor-free multi-task YOLO mainstream. Task coverage differs too: YOLOv10 supports 1 (Detect) against YOLOv8's 5 (Detect, Segment, Classify, Pose, OBB).
Which is smaller, YOLOv10 or YOLOv8?: YOLOv10 gets more out of each parameter. YOLOv10x reaches 54.4 mAP on 29.5M parameters, matching or beating YOLOv8x at 68.2M: about 57% fewer parameters for the same accuracy. That is the comparison worth making, since it is the same result from a smaller checkpoint.
Is YOLOv10 faster than YOLOv8?: Nothing on this page is a speed measurement, and it would be dishonest to imply one: every figure here is published COCO accuracy and parameter count. Parameters are a rough guide to inference cost within one family, but they do not transfer across architectures, and the post-processing step matters as much as the backbone. Export both to ONNX and measure on your own hardware and footage, which is the only comparison that predicts what you will actually get.
Are YOLOv10 and YOLOv8 free for commercial use?: Both ship under AGPL-3.0, so the licence is not a tiebreaker here: choose on accuracy and size. AGPL-3.0 is free for open-source, research and internal use, but a closed-source product or paid service needs an Ultralytics Enterprise licence. Read the licence text before you ship; this is a plain reading of it, not legal advice.

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.