Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1512 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Counting | FSCD-147 (test) | 21 | Feb 27, 2026 | ||
| Image Classification | CIFAR100-PAM | 21 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 alpha=100 | 21 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 (alpha=0.05) | 21 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 alpha=0 | 21 | Feb 26, 2026 | ||
| Image Classification | CIFAR100 alpha=1000 | 21 | Feb 26, 2026 | ||
| Image Classification | CIFAR100 (alpha=0.5) | 21 | Feb 26, 2026 | ||
| Image Classification | CIFAR100 alpha=0 | 21 | Feb 26, 2026 | ||
| Imbalanced Image Classification | CIFAR-100 (test) | 21 | Feb 26, 2026 | ||
| Imbalanced Image Classification | CIFAR-10 (test) | 21 | Feb 26, 2026 | ||
| Many-to-one MRI Synthesis (T2, FLAIR -> T1) | BRATS (test) | 21 | Feb 26, 2026 | ||
| Many-to-one MRI Synthesis (T1, FLAIR -> T2) | BRATS (test) | 21 | Feb 26, 2026 | ||
| Instance Segmentation | COCO 2017 (train/val) | 21 | Feb 26, 2026 | ||
| Dense Anomaly Detection | SMIYC ObstacleTrack | 21 | Feb 26, 2026 | ||
| Image Classification | mini-ImageNet-Red 80% noise | 21 | Feb 26, 2026 | ||
| Image Classification | mini-ImageNet-Red 40% noise | 21 | Feb 26, 2026 | ||
| Image Classification | mini-ImageNet-Red 20% noise | 21 | Feb 26, 2026 | ||
| Panoptic Part Segmentation | Cityscapes Panoptic Parts (val) | 21 | Feb 26, 2026 | ||
| Panoptic Part Segmentation | PASCAL Panoptic Parts (PPP) (val) | 21 | Feb 26, 2026 | ||
| Video Classification | Thyroid Ultrasound Video Dataset | 21 | Apr 27, 2026 | ||
| Stock movement classification | Astock in-distribution 1.0 | 21 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 IDN-50% (test) | 21 | Feb 26, 2026 | ||
| Document-level Relation Extraction | DWIE (test) | 21 | Feb 26, 2026 | ||
| Document-level Relation Extraction | DWIE (dev) | 21 | Feb 26, 2026 | ||
| Semi-supervised graph classification | GITHUB 10-fold cross-validation | 21 | Feb 26, 2026 |