Research
Benchmarks for “coco”
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
3,140 benchmarksPage 68 of 126
Search results
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Visual Grounding | RefCOCO+ B (test) | 8 | Feb 26, 2026 | ||
| Visual Grounding | RefCOCO+ (test A) | 8 | Feb 26, 2026 | ||
| Text-to-Image Generation | COCO 10k-sample 2017 | 8 | Feb 26, 2026 | ||
| Generalized Referring Expression Segmentation | GRES gRefCOCO (test) | 8 | Feb 26, 2026 | ||
| Object Detection | COCO 5k | 8 | Feb 26, 2026 | ||
| Concept Erasure | COCO | 8 | Feb 26, 2026 | ||
| Watermark Extraction | COCO, DIV2K, and Chameleon averaged (test) | 8 | Feb 26, 2026 | ||
| Watermark Extraction | COCO, DIV2K, and Chameleon averaged | 8 | Feb 26, 2026 | ||
| Image Reconstruction | MS-COCO 2017 (full set) | 8 | Feb 26, 2026 | ||
| Image-Text Retrieval | COCO & Flickr30k Retrieval (test) | 8 | Feb 26, 2026 | ||
| Image-Language Understanding | COCO | 8 | Feb 26, 2026 | ||
| Captioning | MS-COCO | 8 | Feb 26, 2026 | ||
| AIGI detection | DDA-COCO | 8 | Feb 26, 2026 | ||
| Text-to-Image Generation | COCO 5K | 8 | Feb 26, 2026 | ||
| Watermark Extraction | MS-COCO 2017 (test) | 8 | Feb 26, 2026 | ||
| Bounding box detection | RefCOCOg (val) | 8 | Feb 26, 2026 | ||
| Object presence hallucination evaluation | POPE MS-COCO 2014 (Random) | 8 | Feb 26, 2026 | ||
| Grounding & counting | RefCOCO avg | 8 | Mar 19, 2026 | ||
| Panoptic Segmentation | COCO-C level 5 | 8 | Feb 26, 2026 | ||
| panoptic segmentation | COCO-C | 8 | Feb 26, 2026 | ||
| Out-of-distribution object detection | MS-COCO | 8 | Feb 27, 2026 | ||
| Semantic Segmentation | COCO-Stuff-15 (val) | 8 | Feb 26, 2026 | ||
| Panoptic Segmentation | COCO Panoptic 2017 (val) | 8 | Feb 26, 2026 | ||
| Text-to-Image Generation | COCO 5k SDXL 1024px 2017 (val) | 8 | Feb 26, 2026 | ||
| Grounding | MS-COCO 2014 | 8 | Feb 26, 2026 |