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 37 of 126

Reset

Search results

TaskDatasetDomainTrendResultsLast update
Semantic SegmentationCOCOcomputer vision15May 26, 2026
Text-to-Image GenerationMS-COCO FLUX.1-dev (test)image generation editing15Mar 19, 2026
Hallucination EvaluationMS-COCOllm chat instructionnlp15Mar 18, 2026
Object DetectionCOCOcomputer vision15Jun 4, 2026
Controllable Image Generation (Counting)COCO-Count Single Categoryimage generation editing15Mar 18, 2026
Object ConcealmentCOCO subsetcomputer vision15Mar 18, 2026
Referring Expression GroundingRefCOCOgcomputer visionnlp15Jun 8, 2026
Multi-label ClassificationMS COCO 2017computer visionnlp+215Mar 9, 2026
Text-to-ImageMS-COCO 5k image-text pairsimage generation editing15Mar 4, 2026
Machine TranslationMulti30K MSCOCO (eng → fra)nlp15Mar 4, 2026
Machine TranslationMulti30K MSCOCO eng → deunlp15Mar 4, 2026
Image CaptioningM3IT COCOmultimodalcomputer vision+115Mar 4, 2026
Open-ended Generation (CHAIR Metric)MSCOCO (Subset)llm chat instruction15Mar 4, 2026
Concept ErasureConcept prompts (Snoopy, Mickey, Spongebob, Pikachu, Hello Kitty) and MS-COCOcomputer visionnlp15Mar 4, 2026
Object DetectionCOCO Base Categories 2014 (test)computer vision15Feb 26, 2026
Object DetectionCOCO Novel Categories 2014 (test)computer vision15Feb 26, 2026
Object DetectionCOCO novel categories 2014computer vision15Feb 26, 2026
Instance SegmentationCOCOcomputer vision15Feb 26, 2026
Sketch-to-Image GenerationFS-COCO 2022 (test)image generation editingcomputer vision15Feb 26, 2026
Hallucination EvaluationPOPE MSCOCO, A-OKVQA, GQA average (Adversarial)llm chat instructionnlp15Feb 26, 2026
Hallucination EvaluationPOPE Popular MSCOCO, A-OKVQA, GQA averagellm chat instructionnlp15Feb 26, 2026
Hallucination EvaluationPOPE MSCOCO, A-OKVQA, GQA average (Random)llm chat instructionnlp15Feb 26, 2026
Text-guided image inpaintingMSCOCO with layout masks (test)image generation editingcomputer vision+115Feb 26, 2026
SegmentationCOCO LQ-1 (unseen)computer vision15Feb 26, 2026
SegmentationCOCO LQ-2 (unseen)computer vision15Feb 26, 2026