Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2570 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Building Damage Assessment | xBD (test) | 15 | Feb 26, 2026 | ||
| Long-term Visual Object Tracking | OxUvA | 15 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | JTA (test) | 15 | Feb 27, 2026 | ||
| Face Alignment | AFLW Full 19 landmarks (test) | 15 | Feb 26, 2026 | ||
| Video Deblurring | Su et al. video deblurring (test) | 15 | Feb 26, 2026 | ||
| Human-Object Interaction Detection | HOI-A (test) | 15 | Feb 26, 2026 | ||
| Semantic Segmentation | ADE20K 50-50 scenario | 15 | Feb 26, 2026 | ||
| Syntactic Evaluation | Marvin and Linzen | 15 | Feb 26, 2026 | ||
| Logical Query Answering | FB15k | 15 | Feb 26, 2026 | ||
| Video Captioning | VATEX online evaluation (test) | 15 | Feb 26, 2026 | ||
| Scene Text Spotting | CTW1500 (test) | 15 | Feb 26, 2026 | ||
| Fair k-center | Adult | 15 | Feb 26, 2026 | ||
| Fair k-center | SushiB | 15 | Feb 26, 2026 | ||
| Fair k-center | SushiA | 15 | Feb 26, 2026 | ||
| Zero-Shot Learning | AWA2 (Proposed Split) | 15 | Feb 26, 2026 | ||
| Zero-Shot Learning | CUB (Proposed Split) | 15 | Feb 26, 2026 | ||
| Zero-Shot Learning | SUN (Proposed Split) | 15 | Feb 26, 2026 | ||
| Face Detection | WIDERFACE Hard | 15 | Feb 26, 2026 | ||
| Face Detection | WIDERFACE Easy | 15 | Feb 26, 2026 | ||
| Node Classification | MUTAG (Node) (test) | 15 | Feb 26, 2026 | ||
| Few-shot regression | Sinusoidal functions (test) | 15 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 (test) | 15 | Feb 26, 2026 | ||
| Machine Translation | sk-en (test) | 15 | Feb 26, 2026 | ||
| Handwritten text recognition | RIMES (test) | 15 | Feb 26, 2026 | ||
| Text Classification | AGNews, Yelp, Amazon, DBPedia, Yahoo (last epoch of last task) | 15 | Feb 26, 2026 |