Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1916 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Retrieval | Cars196 Ext. Real to Watercolor | 18 | Feb 26, 2026 | ||
| Image Retrieval | Cars196 Real to Oil-painting Ext. | 18 | Feb 26, 2026 | ||
| Image Retrieval | CUB-200 Ext. Real to Watercolor 2011 | 18 | Feb 26, 2026 | ||
| Image Retrieval | CUB-200-2011 Ext. Real to Oil-painting | 18 | Feb 26, 2026 | ||
| Burn scar mapping | FLOGA (test) | 18 | Feb 26, 2026 | ||
| Privacy Classification | VISPR (test) | 18 | Jun 25, 2026 | ||
| Survival Prediction | NSCLC natural missingness patterns (5-fold CV) | 18 | Feb 26, 2026 | ||
| Surface Normal Estimation | NYUD clean and adverse conditions v2 v1 (unseen) | 18 | Feb 26, 2026 | ||
| 3D Graphic Editing | BlenderGym | 18 | Feb 26, 2026 | ||
| Image Classification | USPS | 18 | Jun 5, 2026 | ||
| Robot Manipulation | Adroit | 18 | Feb 26, 2026 | ||
| CAFO Classification | CAFO dataset (spatial) | 18 | Feb 26, 2026 | ||
| CAFO Classification | CAFO dataset (random 80-20) | 18 | Feb 26, 2026 | ||
| Fake News Video Detection | FakeTT → FakeSV | 18 | Feb 26, 2026 | ||
| Patch-level histology classification | BACH | 18 | Feb 26, 2026 | ||
| Behavior Classification | VOICES (test) | 18 | Feb 26, 2026 | ||
| VAD Regression | VOICES (test) | 18 | Feb 26, 2026 | ||
| Object Detection | Cityscapes → BDD100k | 18 | Feb 26, 2026 | ||
| Erythrocyte Classification | Isolated Erythrocytes | 18 | Feb 27, 2026 | ||
| Object Hallucination Evaluation | CHAIR MS COCO based (test) | 18 | Feb 26, 2026 | ||
| Image Reconstruction | ImageNet-1k 512x512 resolution (val) | 18 | Jun 1, 2026 | ||
| Change Detection | LEVIR-CD, WHU-CD, HTCD, MT-Wuhan, XiongAn Average | 18 | Feb 26, 2026 | ||
| Change Detection | XiongAn | 18 | Feb 26, 2026 | ||
| Change Detection | MT-Wuhan | 18 | Feb 26, 2026 | ||
| Change Detection | HTCD | 18 | Feb 26, 2026 |