List your company

Research

Benchmarks for “coco”

Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.

3,140 benchmarksPage 77 of 126

Reset

Search results

TaskDatasetDomainTrendResultsLast update
Pose EstimationCOCOcomputer vision7Feb 26, 2026
Region DescriptionRefCOCO+ (test-B)computer visionnlp7Feb 26, 2026
Region DescriptionRefCOCO (test-B)computer visionnlp7Feb 26, 2026
Text-to-3D GenerationCOCO (val)image generation editing3d vision geometry7Feb 26, 2026
Text-guided Image GenerationMS-COCO (test)image generation editing7Feb 26, 2026
Referring Expression GroundingRefCOCO-g (Google)computer visionnlp7Feb 26, 2026
Image-to-Text RetrievalCOCO-CN Chinese 1K (test)multimodalretrieval search rag7Feb 26, 2026
Instance SegmentationCOCO 10% labels (val)computer vision7Feb 26, 2026
Instance SegmentationCOCO 5% labels (val)computer vision7Feb 26, 2026
Instance SegmentationCOCO 2% labels (val)computer vision7Feb 26, 2026
Instance SegmentationCOCO 1% labels (val)computer vision7Feb 26, 2026
Image CaptioningCOCO (test)multimodalcomputer vision+17Feb 26, 2026
Image CaptioningCOCO (val)multimodalcomputer vision+17Feb 26, 2026
Visual GroundingRefCOCOg umd (test)multimodalcomputer vision7Feb 26, 2026
OOD DetectionNUS-WIDE In-distribution MS-COCO Out-of-distribution original (test)computer visiontabular time series7Feb 26, 2026
Image-Description CorrespondenceExtended COCO-Stuff (test)computer visionnlp7Feb 26, 2026
Controllable Image Generation (Depth)COCO 2017 (val)image generation editingcomputer vision7Feb 26, 2026
Interactive SegmentationCOCO (unseen)computer vision7Feb 26, 2026
Object DetectionCOCO-Full 2017 (train)computer vision7Feb 26, 2026
Visual GroundingReferCOCO+ v1 (testB)multimodalcomputer vision7Feb 26, 2026
Visual GroundingReferCOCO v1 (testA)multimodalcomputer vision7Feb 26, 2026
Cross-lingual Image CaptioningCOCO-CN Zh (test)multimodalnlp7Feb 26, 2026
Image CaptioningCOCO Captioning (val)multimodalcomputer vision+17Feb 26, 2026
Text-to-image generationCOCO caption (val)image generation editing7Feb 26, 2026
Layout-to-image synthesisCOCO-Stuffimage generation editingcomputer vision7Feb 26, 2026