Model results

Roboflow Model Leaderboard

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Official source

← All evaluation groups

Roboflow Model Leaderboard · mAP at IoU 0.50:0.95, large objects

Source: Roboflow Model Leaderboard (reviewed publisher results)
Version: COCO 2017 (publisher version unspecified)
Measurement date: 2026-01-14
Metric: fraction · Higher is better
Evaluation scope: COCO 2017 object detection; large objects; publisher-reported mAP at evaluation IoU 0.50:0.95; source fractions on 0–1 scale; inference parameters {"conf":0,"imgsz":640,"iou":0.7,"max_det":100,"verbose":false}; linked evaluator loads val2017/instances_val2017, but live table does not identify its split or dataset digest; declared model variants, not verified execution checkpoint hashes; executed dependency versions, hardware, precision, run count and uncertainty not supplied; publisher run-record date, not release date; size boundaries and exact aggregation implementation unverified

Exact score ties share a position. Positions do not establish statistical significance. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

#1YOLO26x
ultralytics/yolo26x
0.7237757979208893 fraction
View modelEvidence independent
#2YOLO26l
ultralytics/yolo26l
0.6948882838404676 fraction
View modelEvidence independent
#3YOLO26m
ultralytics/yolo26m
0.6830201567716823 fraction
View modelEvidence independent
#4YOLO26s
ultralytics/yolo26s
0.6400593940205617 fraction
View modelEvidence independent
#5YOLO26n
ultralytics/yolo26n
0.5799377632743729 fraction
View modelEvidence independent