Benchmark Almanac

Object Detection Leaderboard

jozhang97/deta-swin-large 55.6 tops its leaderboard
Not in model cards

Models locate and classify objects in images. The board compares average precision.

The Space loads the latest CSV from its configured dataset.

Made by
Hugging Face
Released
September 2023
Kind
Detection and captioning
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Images → Text
Interaction
Single turn
Items from
Another benchmark
Refresh
One fixed set
Run by
Anyone
In views
Vision
30
Entries on its own leaderboard, 0 models we track

jozhang97/deta-swin-large tops the leaderboard with 55.6

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

  1. 1 jozhang97/deta-swin-large 55.6
  2. 2 jozhang97/deta-resnet-50-24-epochs 49.4
  3. 3 jozhang97/deta-resnet-50 48.8
  4. 4 SenseTime/deformable-detr-with-box-refine 46.3
  5. 5 ciasimbaya/ObjectDetection 44.9
  6. 6 facebook/detr-resnet-101-dc5 44.9
  7. 7 SenseTime/deformable-detr 44.5
  8. 8 facebook/detr-resnet-101 43.5
  9. 9 jaimin/ObjectDetect 43.5
  10. 10 OverDriveLee/CoCo_Usage 43.5
  11. 11 Sembiance/detr-resnet-101-fixed 43.5
  12. 12 facebook/detr-resnet-50-dc5 43.3
  13. 13 elipark11/detr-finetune-v1 42.1
  14. 14 Eshwar14/my_resnet_model 42.1
  15. 15 facebook/detr-resnet-50 42.1
  16. 16 liaujianjie/detr-resnet-50 42.1
  17. 17 SenseTime/deformable-detr-single-scale-dc5 41.4
  18. 18 microsoft/conditional-detr-resnet-50 40.9
  19. 19 SenseTime/deformable-detr-single-scale 39.2
  20. 20 hustvl/yolos-base 38.3
  21. 21 hustvl/yolos-small-dwr 34.5
  22. 22 hustvl/yolos-small-300 33.4
  23. 23 hustvl/yolos-small 33.3
  24. 24 fcakyon/yolov5s-v7.0 32.1
  25. 25 hustvl/yolos-tiny 25.7
  26. 26 fcakyon/yolov5n-v7.0 23.9
  27. 27 wwkiyyx/yolo 16.4
  28. 28 DI-Huy/hustvl-yolos-tiny-benetech 13.7
  29. 29 gary109/STAS_detr-resnet-50 13.2
  30. 30 Batr97/DETR_coco 0.00

Source: Official Object Detection Leaderboard leaderboard

#EntryScoreSettingDateLinkSource
1 jozhang97/deta-swin-large 55.6 huggingface.co Official leaderboard
2 jozhang97/deta-resnet-50-24-epochs 49.4 huggingface.co Official leaderboard
3 jozhang97/deta-resnet-50 48.8 huggingface.co Official leaderboard
4 SenseTime/deformable-detr-with-box-refine 46.3 huggingface.co Official leaderboard
5 ciasimbaya/ObjectDetection 44.9 huggingface.co Official leaderboard
6 facebook/detr-resnet-101-dc5 44.9 huggingface.co Official leaderboard
7 SenseTime/deformable-detr 44.5 huggingface.co Official leaderboard
8 facebook/detr-resnet-101 43.5 huggingface.co Official leaderboard
9 jaimin/ObjectDetect 43.5 huggingface.co Official leaderboard
10 OverDriveLee/CoCo_Usage 43.5 huggingface.co Official leaderboard
11 Sembiance/detr-resnet-101-fixed 43.5 huggingface.co Official leaderboard
12 facebook/detr-resnet-50-dc5 43.3 huggingface.co Official leaderboard
13 elipark11/detr-finetune-v1 42.1 huggingface.co Official leaderboard
14 Eshwar14/my_resnet_model 42.1 huggingface.co Official leaderboard
15 facebook/detr-resnet-50 42.1 huggingface.co Official leaderboard
16 liaujianjie/detr-resnet-50 42.1 huggingface.co Official leaderboard
17 SenseTime/deformable-detr-single-scale-dc5 41.4 huggingface.co Official leaderboard
18 microsoft/conditional-detr-resnet-50 40.9 huggingface.co Official leaderboard
19 SenseTime/deformable-detr-single-scale 39.2 huggingface.co Official leaderboard
20 hustvl/yolos-base 38.3 huggingface.co Official leaderboard
21 hustvl/yolos-small-dwr 34.5 huggingface.co Official leaderboard
22 hustvl/yolos-small-300 33.4 huggingface.co Official leaderboard
23 hustvl/yolos-small 33.3 huggingface.co Official leaderboard
24 fcakyon/yolov5s-v7.0 32.1 huggingface.co Official leaderboard
25 hustvl/yolos-tiny 25.7 huggingface.co Official leaderboard
26 fcakyon/yolov5n-v7.0 23.9 huggingface.co Official leaderboard
27 wwkiyyx/yolo 16.4 huggingface.co Official leaderboard
28 DI-Huy/hustvl-yolos-tiny-benetech 13.7 huggingface.co Official leaderboard
29 gary109/STAS_detr-resnet-50 13.2 huggingface.co Official leaderboard
30 Batr97/DETR_coco 0.00 huggingface.co Official leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Vision

All 636 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. Qwen 3.6 Plus 86%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%

Data audit

All 8 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (30 entries).
  • Pass Models scored 30 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on huggingface.co: 30 entries at the last read, none a model we track.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check