Research
Benchmarks for “coco”
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
3,140 benchmarksPage 82 of 126
Search results
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Referring Image Object Grounding | RefCOCO+ MS-COCO (testB) | 6 | Apr 14, 2026 | ||
| Referring Image Object Grounding | RefCOCO+ MS-COCO (val) | 6 | Apr 14, 2026 | ||
| Referring Image Object Grounding | RefCOCO MS-COCO (testB) | 6 | Apr 14, 2026 | ||
| Referring Image Object Grounding | RefCOCO MS-COCO (testA) | 6 | Apr 14, 2026 | ||
| Multi-task Average | COCO subset | 6 | Apr 13, 2026 | ||
| Keypoint Detection | COCO subset | 6 | Apr 13, 2026 | ||
| Instance Segmentation | COCO subset | 6 | Apr 13, 2026 | ||
| Object Detection | COCO subset | 6 | Apr 13, 2026 | ||
| Harmful prompt detection | COCO | 6 | Apr 9, 2026 | ||
| Failure Discovery | COCO | 6 | Apr 7, 2026 | ||
| Instance Segmentation | COCO_exc Small 2017 (val) | 6 | Apr 6, 2026 | ||
| Instance Segmentation | COCO_exc Medium 2017 (val) | 6 | Apr 6, 2026 | ||
| Instance Segmentation | COCO_exc Large 2017 (val) | 6 | Apr 6, 2026 | ||
| Unsupervised Semantic Segmentation | COCO-Stuff | 6 | Apr 2, 2026 | ||
| Unsupervised Semantic Segmentation | COCO Object | 6 | Apr 2, 2026 | ||
| Image Captioning | COCO | 6 | Mar 31, 2026 | ||
| Text-to-Image Generation (Stable Diffusion 3.5 Medium Comparison) | COCO 10K prompts 2014 (Karpathy) | 6 | Mar 31, 2026 | ||
| Gemini-3 Pro Evaluation | MSCOCO (val) | 6 | Mar 31, 2026 | ||
| Cross Decoding | COCO | 6 | Mar 25, 2026 | ||
| Imperceptibility | COCO | 6 | Mar 25, 2026 | ||
| Referring Expression Segmentation | RefCOCO classic RES settings (val) | 6 | Mar 20, 2026 | ||
| Backdoor Defense | COCO long prompts (EE attack) | 6 | Mar 19, 2026 | ||
| Backdoor Defense | COCO long prompts TI attack | 6 | Mar 19, 2026 | ||
| Backdoor Defense | COCO long prompts (RR attack) | 6 | Mar 19, 2026 | ||
| Hallucination Analysis | COCO Captioning (val) | 6 | Mar 16, 2026 |