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.
Roboflow Model Leaderboard · F1 at IoU 0.75, small objects
- Source
- Roboflow Model Leaderboard (reviewed publisher results)
- Version
- COCO 2017 (publisher version unspecified)
- Measurement date
- 2025-07-03
- Metric
- fraction · Higher is better
- Evaluation scope
- COCO 2017 object detection; small objects; publisher-reported F1 at evaluation IoU 0.75; source fractions on 0–1 scale; inference parameters {"conf":0,"imgsz":640,"max_det":100}; 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; IoU threshold is not inference confidence; no peak-F1 or confidence-optimization claim
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.
#1RTMDet-x
openmmlab/rtmdet-x
0.03936316757166378 fraction
View modelEvidence independent#2RTMDet-l
openmmlab/rtmdet-l
0.038350401629087275 fraction
View modelEvidence independent#3RTMDet-m
openmmlab/rtmdet-m
0.035884966546874696 fraction
View modelEvidence independent#4RTMDet-s
openmmlab/rtmdet-s
0.02831706801269971 fraction
View modelEvidence independent#5RTMDet-t
openmmlab/rtmdet-tiny
0.027234560106853843 fraction
View modelEvidence independent