Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1255 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image captioning | Sydney Captions | 24 | Feb 27, 2026 | ||
| In-bed human mesh recovery | SLP (test) | 24 | Feb 26, 2026 | ||
| Class-Incremental Learning | Tiny-ImageNet (test) | 24 | May 20, 2026 | ||
| Multiple Choice Question Answering | Riddle | 24 | Feb 26, 2026 | ||
| Deepfake Detection | FF++ Intra-dataset c23 | 24 | Feb 26, 2026 | ||
| Lightweight Image Super-Resolution | Manga109 | 24 | Feb 26, 2026 | ||
| 6D Object Pose Estimation | Toyota-Light (TOYL) (test) | 24 | Mar 25, 2026 | ||
| Vision Understanding | VizWiz (test) | 24 | Mar 4, 2026 | ||
| Image Classification | LADV-3D (OOD) | 24 | Feb 26, 2026 | ||
| Image Classification | LADV-3D (ID) | 24 | Feb 26, 2026 | ||
| Image Classification | LADA-Sculpture (OOD) | 24 | Feb 26, 2026 | ||
| Image Classification | LADA-Sculpture (ID) | 24 | Feb 26, 2026 | ||
| Image Classification | AwA2 clipart (OOD) | 24 | Feb 26, 2026 | ||
| Image Classification | AwA2 clipart (ID) | 24 | Feb 26, 2026 | ||
| Image Classification | CUB-Painting (OOD) | 24 | Feb 26, 2026 | ||
| Image Classification | CUB Painting (ID) | 24 | Feb 26, 2026 | ||
| LiDAR Localization | Oxford (Average) | 24 | Jun 29, 2026 | ||
| LiDAR Localization | Oxford (18-14-14-42) | 24 | Jun 29, 2026 | ||
| Conditional Image Generation | ImageNet 256x256 (train/val) | 24 | Feb 26, 2026 | ||
| Video Dialogue | AVSD DSTC8 (test) | 24 | Feb 26, 2026 | ||
| Hand-pose estimation | FreiHAND | 24 | Jun 25, 2026 | ||
| Human-Object Interaction Generation | OMOMO (test) | 24 | Apr 7, 2026 | ||
| Continual Learning | S-Tiny-ImageNet (last) | 24 | Feb 26, 2026 | ||
| Continual Learning | S-CIFAR-10 (last) | 24 | Feb 26, 2026 | ||
| Depth Completion | Indoor sequence NYUv2 → ScanNet → VOID | 24 | Feb 27, 2026 |