Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

COCO dataset and benchmarks – Page 44 · SOTA2 Research

Research Datasets

COCO

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Image Captioning

MS COCO random subset of 100 images (test)

40.7BLEU-4

5

Image-to-Image Translation

COCO Mask

15.8FID-I

5

Object Detection

COCO 20k (trainval)

9.9AP@50

5

Unconditional Generation

COCO

99.76BLEU-1

5

Instance Segmentation

COCO-OCC

32.89AP

5

Object Detection

COCO 350

32.56Precision

5

Image Deraining

COCO 350

18.23PSNR

5

Few-shot Object Detection

COCO novel categories 2014 2017 (val)

16.4novel AP

5

Text-to-image synthesis

COCO

30.49Inception Score

5

Semantic Segmentation

COCO 5-shot

51.6mIoU

5

Keypoint Detection

COCO challenge 2017 (test)

72.1AP

5

Text-driven Image Editing

COCO User Study

82.33Prompt Adherence

5

Model Distillation

COCO 10k prompts

5.9FID

4

Text-to-text intra-modality retrieval

COCO

30.69mAP

4

Text-to-Image Retrieval

COCO 100 Pairs (test)

35Recall@5

4

Image-to-Text Retrieval

COCO 100 Pairs (test)

35.8Recall@5

4

Normal-map-conditioned Image Generation

COCO 5K

18.6FID

4

Object Detection

COCO 80 images

1.27Deletion Rate

4

COCO

36.46R@1

4

COCO-TS

75.35fgIoU

4

Open Vocabulary Segmentation

COCO

48.12mIoU

4

Text-to-image generation

COCO 2017 (test)

26.07FID

4

Multi-object discovery

COCO 20k

19.8Recall

4

Text-to-Image Generation

COCO 24

38.68FID

4

Image Segmentation

MS COCO

88.9Accuracy

4

Page 44 of 57

Popular tasks

Object Detection Image Captioning Instance Segmentation Semantic segmentation Text-to-Image Generation

Follow for updates

Join SOTA2 Contact