Model comparison · YOLOv9 vs YOLOv5 (v5u)

YOLOv9 vs YOLOv5 (v5u)

A size-tier-by-size-tier comparison of YOLOv9 and Ultralytics YOLOv5 (v5u): published COCO accuracy, parameter counts, licensing and which one to reach for. Every figure is the model authors' own, linked to its source.

CompareYOLOv9
AgainstYOLOv5 (v5u)
52%fewer params

mAP comparison

YOLOv9YOLOv5 (v5u)
31.038.045.052.059.0mAPNanoSmallMediumLargeExtra largeModel size tierYOLOv9t: 38.3 mAP, 2M paramsYOLOv9s: 46.8 mAP, 7.2M paramsYOLOv9m: 51.4 mAP, 20.1M paramsYOLOv9c: 53.0 mAP, 25.5M paramsYOLOv9e: 55.6 mAP, 58.1M paramsYOLOv5nu: 34.3 mAP, 2.6M paramsYOLOv5su: 43.0 mAP, 9.1M paramsYOLOv5mu: 49.0 mAP, 25.1M paramsYOLOv5lu: 52.2 mAP, 53.2M paramsYOLOv5xu: 53.2 mAP, 97.2M params

YOLOv9

  • Nano 38.3
  • Small 46.8
  • Medium 51.4
  • Large 53.0
  • Extra large 55.6

YOLOv5 (v5u)

  • Nano 34.3
  • Small 43.0
  • Medium 49.0
  • Large 52.2
  • Extra large 53.2
COCO mAP at 640px, as published by each model’s authors. The y axis spans 31.0 to 59.0 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
YOLOv9 and YOLOv5 (v5u) compared at each size tier: published COCO mAP50-95 at 640px and parameter counts in millions.
TierYOLOv9YOLOv5 (v5u)Δ mAP
ModelmAPParamsModelmAPParams
NanoYOLOv9t38.32.0MYOLOv5nu34.32.6M+4.0
SmallYOLOv9s46.87.2MYOLOv5su43.09.1M+3.8
MediumYOLOv9m51.420.1MYOLOv5mu49.025.1M+2.4
LargeYOLOv9c53.025.5MYOLOv5lu52.253.2M+0.8
Extra largeYOLOv9e55.658.1MYOLOv5xu53.297.2M+2.4

Δ mAP is YOLOv9 minus YOLOv5 (v5u): positive means YOLOv9 is ahead at that tier. Sources: YOLOv9 docs · YOLOv9 paper · YOLOv5 (v5u) docs

Additional information

  • YOLOv9 posts the higher published COCO mAP at all 5 matched size tiers, averaging 2.68 mAP ahead of YOLOv5 (v5u). The gap is widest at the nano tier, where YOLOv9 leads by 4.0 mAP. At the top of each range, YOLOv9 reaches 55.6 mAP against 53.2.

  • 52% fewer parameters, same accuracy. YOLOv9c reaches 53.0 mAP from 25.5M parameters, matching or beating YOLOv5lu at 52.2 mAP from 53.2M.

    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.

YOLOv9

Fixes deep-network information loss with PGI and GELAN.

Released
2024 · Academia Sinica (Wang et al.)
License
GPL-3.0
Framework
Original repo + Ultralytics (PyTorch)
Tasks
Detect, Segment

Adds Programmable Gradient Information and the GELAN backbone to preserve detail through deep layers, reaching high accuracy with very few parameters.

Download YOLOv9 weights →

YOLOv5 (v5u)

The classic that made YOLO easy to ship, retrained anchor-free.

Released
2020 · Ultralytics
License
AGPL-3.0
Framework
Ultralytics (PyTorch)
Tasks
Detect, Segment, Classify

The anchor-free v5u retrain of the classic PyTorch YOLO, keeping its easy training and export while adopting the newer YOLOv8 detection head for better accuracy.

Download YOLOv5 (v5u) weights →

YOLOv9 and YOLOv5 (v5u) against the whole lineage

YOLOv9 and YOLOv5 (v5u) 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.
ModelReleasedmAP rangeParams rangeLicence
YOLO26202640.9 to 57.52.4M to 55.7MAGPL-3.0
YOLO12202540.6 to 55.22.6M to 59.1MAGPL-3.0
YOLO11202439.5 to 54.72.6M to 56.9MAGPL-3.0
YOLOv10202438.5 to 54.42.3M to 29.5MAGPL-3.0
YOLOv9202438.3 to 55.62.0M to 58.1MGPL-3.0
YOLOv8202337.3 to 53.93.2M to 68.2MAGPL-3.0
YOLOv5 (v5u)202034.3 to 53.22.6M to 97.2MAGPL-3.0

Licenses here cover the weights. Running either model through the Ultralytics package brings AGPL-3.0 with it, and that can reach your own application regardless of how the checkpoint itself is licensed. Check the terms against your distribution plan before you ship.

Every matchup

YOLO26 vs YOLO12YOLO26 vs YOLO11YOLO26 vs YOLOv10YOLO26 vs YOLOv9YOLO26 vs YOLOv8YOLO26 vs YOLOv5 (v5u)YOLO12 vs YOLO11YOLO12 vs YOLOv10YOLO12 vs YOLOv9YOLO12 vs YOLOv8YOLO12 vs YOLOv5 (v5u)YOLO11 vs YOLOv10YOLO11 vs YOLOv9YOLO11 vs YOLOv8YOLO11 vs YOLOv5 (v5u)YOLOv10 vs YOLOv9YOLOv10 vs YOLOv8YOLOv10 vs YOLOv5 (v5u)YOLOv9 vs YOLOv8YOLOv9 vs YOLOv5 (v5u)YOLOv8 vs YOLOv5 (v5u)

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.