Research
Benchmarks for “coco”
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
3,140 benchmarksPage 55 of 126
Search results
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text-to-image generation | MS-COCO prompts 2014 (test) | 10 | May 26, 2026 | ||
| Jigsaw Puzzle Solving | MS COCO Jigsaw | 10 | May 25, 2026 | ||
| Semantic Segmentation | COCO | 10 | May 22, 2026 | ||
| Locality Evaluation | COCO 3K | 10 | May 19, 2026 | ||
| Adversarial attack on image explanations | COCO 2017 (test) | 10 | May 19, 2026 | ||
| General model utility | MS-COCO 30K samples | 10 | May 18, 2026 | ||
| Saliency Map Evaluation | MS-COCO (train) | 10 | May 18, 2026 | ||
| Saliency Prediction | COCO-Freeview (holdout) | 10 | Jul 3, 2026 | ||
| Object Detection | COCO 48/17 open-vocabulary split 2017 | 10 | May 6, 2026 | ||
| Text-to-Image Generation | COCO | 10 | Apr 23, 2026 | ||
| Visual Question Answering | VQAv2 3K curated MS COCO (test) | 10 | Apr 21, 2026 | ||
| Jailbreak Attack | COCO-Jailbreak | 10 | Apr 15, 2026 | ||
| Watermark Extraction | COCO 5,000 images (test) | 10 | Apr 7, 2026 | ||
| Paired Perceptual Deviation | COCO | 10 | Mar 31, 2026 | ||
| Object Erasure | COCO | 10 | Mar 31, 2026 | ||
| Image Captioning | COCO Adversarial, epsilon_a = 4/255 | 10 | Mar 31, 2026 | ||
| Image Captioning | COCO Clean (test) | 10 | Mar 31, 2026 | ||
| Referring Image Segmentation | RefCOCO+ UNC+ (testB) | 10 | Mar 19, 2026 | ||
| Referring Image Segmentation | RefCOCO+ UNC+ (testA) | 10 | Mar 19, 2026 | ||
| Referring Image Segmentation | RefCOCO+ UNC+ (val) | 10 | Mar 19, 2026 | ||
| Referring Image Segmentation | RefCOCO UNC (testB) | 10 | Apr 6, 2026 | ||
| Referring Image Segmentation | RefCOCO UNC (testA) | 10 | Apr 6, 2026 | ||
| Referring Image Segmentation | RefCOCO UNC (val) | 10 | Apr 6, 2026 | ||
| Image Generation | COCO | 10 | Mar 17, 2026 | ||
| Object Detection | COCO (val) | 10 | Mar 17, 2026 |