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 20 · SOTA2 Research

Research Datasets

COCO

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Open-vocabulary Object Detection

COCO (val)

67.23AP50 (All)

13

Text-to-Image Synthesis

MS COCO 256x256

6.95FID

13

Image Captioning

COCO (test)

140.9CIDEr

13

Multi-label classification

COCO-MLT (test)

53.55mAP (Overall)

13

Image Retrieval

MS COCO 1K

62.8R@1

13

Image-to-Video Generation

COCO 2017

0.79VBench-Q

12

Caption token attribution

COCO

64.05Insertion Score

12

Image-Text Reranking

COCO (reranking)

0.89Delta H@1

12

Targeted Adversarial Attack

COCO

100Attack Success Rate

12

Multi-Label Recognition

COCO 2014 (test)

67.37mAP

12

Diverse Image Generation

COCO

8.42Time / prompt (s)

12

COCO subset

81.77mIoU

12

Image Captioning

COCO Caption

0.758BLEU-1

12

Object Detection

COCO 2017

65.3tSucDet

12

Text-to-Image Retrieval

COCO 2014 (test)

56.78Accuracy

12

Text-to-text retrieval

COCO

31.9mAP

12

Vehicle Detection

COCO

91.4AP50

12

Object Detection

COCO-OVD

54.7Novel AP50

12

Object Detection

COCO (val)

18.5mAP (10-shot)

12

2D Pose Evaluation

COCO

86.5PCK @0.05

12

Semantic Segmentation

MS-COCO

59.1mIoU (Real+Syn)

12

COCO Robustseg-Style Degradation (unseen)

70.3IoU

12

Frame Reconstruction

COCO (val)

36.05PSNR

12

Spatial Reasoning

COCO 2017 (val)

83Alignment Accuracy

12

Point-Prompted Segmentation

COCO

75.5mIoU

12

Page 20 of 57

Popular tasks

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

Follow for updates

Join SOTA2 Contact