Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 514 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Machine Translation | English-French | 42 | Feb 27, 2026 | ||
| Visual Question Answering | ScienceQA (SQAI) | 42 | Jul 7, 2026 | ||
| Image Inpainting | CelebA-HQ | 42 | Feb 26, 2026 | ||
| Backdoor Re-activation Attack | CIFAR-10 | 42 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K (val) | 42 | Jun 5, 2026 | ||
| Point Cloud Filtering | PCNet (test) | 42 | Feb 26, 2026 | ||
| Point Cloud Filtering | PUNet (test) | 42 | Feb 26, 2026 | ||
| Point Cloud Filtering | PCNet synthetic (test) | 42 | Feb 26, 2026 | ||
| Point Cloud Filtering | PUNet synthetic (test) | 42 | Feb 26, 2026 | ||
| Uncertainty estimation | CoQA (test) | 42 | Feb 26, 2026 | ||
| Image Super-Resolution | Set5 x4 scale (test) | 42 | May 26, 2026 | ||
| Image Super-Resolution | Set5 x2 scale (test) | 42 | May 26, 2026 | ||
| Marine Animal Segmentation | RMAS | 42 | Mar 16, 2026 | ||
| Marine Animal Segmentation | MAS3K | 42 | Mar 16, 2026 | ||
| Image Classification | ImageNet-127 (test) | 42 | May 19, 2026 | ||
| Novel View Synthesis | D-NeRF synthetic (test) | 42 | Feb 26, 2026 | ||
| Backlight Image Enhancement | BAID | 42 | May 13, 2026 | ||
| Robotic Image Segmentation | OCID | 42 | May 26, 2026 | ||
| 3D Classification | ScanObjectNN OBJ-BG | 42 | Jun 2, 2026 | ||
| Recognition | ImageNet-1K | 42 | Mar 19, 2026 | ||
| Class-incremental Learning | ImageNet-100 B=50, C=10 1.0 | 42 | Feb 27, 2026 | ||
| Image Classification | CIFAR-10 Long-Tailed (test) | 42 | Feb 26, 2026 | ||
| Near-isometric shape matching | SCAPE (test) | 42 | Jun 30, 2026 | ||
| Text-to-Image Generation | MS-COCO 30k (val) | 42 | Mar 13, 2026 | ||
| 3D Molecule Generation | QM9 unconditional generation | 42 | Jun 2, 2026 |