Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1140 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Dehazing | RESIDE | 25 | Mar 10, 2026 | ||
| Open-QA Evaluation | EVOUNA-TriviaQA | 25 | Feb 26, 2026 | ||
| Object Detection | COCO 70+10 scenario 2017 (val) | 25 | Mar 4, 2026 | ||
| Object Detection | COCO 40+40 scenario 2017 (val) | 25 | Mar 4, 2026 | ||
| Subject-driven Generation | DreamBench (test) | 25 | Feb 26, 2026 | ||
| Density Classification | VinDr | 25 | Feb 26, 2026 | ||
| Mass Classification | VinDr | 25 | Feb 26, 2026 | ||
| Calcification Classification | VinDr | 25 | Feb 26, 2026 | ||
| Point Tracking | TAP-Vid-Kinetics (val) | 25 | Feb 26, 2026 | ||
| Motion-to-text retrieval | KIT-ML | 25 | Mar 11, 2026 | ||
| Text-to-motion retrieval | KIT-ML | 25 | Mar 11, 2026 | ||
| Multimodal Visual Pattern Understanding | MMVP | 25 | Mar 31, 2026 | ||
| Super-resolution | ImageNet 1K (test) | 25 | Jul 2, 2026 | ||
| Scene Flow | KITTI Scene Flow (test) | 25 | Apr 23, 2026 | ||
| Cross-modal Retrieval | Flickr30k (test) | 25 | Mar 6, 2026 | ||
| Object Recognition | Objaverse-LVIS | 25 | Feb 27, 2026 | ||
| Image Classification | ImageNet-1K original (val) | 25 | Feb 26, 2026 | ||
| Example-based Segmentation | PASCAL-5i (val) | 25 | Jun 29, 2026 | ||
| Point Cloud Registration | 3DLoMatch (low-overlap) | 25 | Apr 21, 2026 | ||
| Abstract Visual Reasoning | Raven | 25 | Apr 30, 2026 | ||
| Image Classification | CIFAR-100 LT IF=10 | 25 | Jul 8, 2026 | ||
| Region-level captioning | RefCOCOg | 25 | Apr 28, 2026 | ||
| Face Anti-Spoofing | PS -> CW (PADISI-USC, CASIA-SURF to CASIA-CeFA, WMCA) Protocol 3 (Cross-dataset) | 25 | Jul 7, 2026 | ||
| Face Anti-Spoofing | CASIA-CeFA, WMCA, PADISI-USC, CASIA-SURF CW -> PS Protocol 3 (Cross-dataset) | 25 | Jul 7, 2026 | ||
| Image Classification | CIFAR-100 50+50 | 25 | Feb 26, 2026 |