Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 692 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Emotion Recognition | M3ED (test) | 35 | Feb 26, 2026 | ||
| Emotion Recognition | M3ED (val) | 35 | Feb 26, 2026 | ||
| Out-of-distribution detection | CIFAR10 ID Place365 OOD (test) | 35 | Feb 27, 2026 | ||
| Object Detection | Cityscapes (val) | 35 | Jun 11, 2026 | ||
| Joint Demosaicking and Denoising | REDS4 High Noise | 35 | Feb 26, 2026 | ||
| Joint Demosaicking and Denoising | REDS4 Low Noise | 35 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K V1 | 35 | Feb 26, 2026 | ||
| Gait Recognition | GREW (test) | 35 | Mar 26, 2026 | ||
| Stereo Matching | HCI (test) | 35 | Feb 26, 2026 | ||
| Gaze Following | GazeFollowing | 35 | May 27, 2026 | ||
| Gesture Recognition | SHREC'17 1.0 (test) | 35 | Jun 24, 2026 | ||
| Face Recognition | CFP | 35 | Feb 26, 2026 | ||
| Image Generation | Tiny-ImageNet (test) | 35 | Feb 26, 2026 | ||
| Visual Odometry | KITTI Seq. 10 | 35 | Jun 5, 2026 | ||
| Graph Classification | IMDB-BIN | 35 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 Corrupted | 35 | Jun 23, 2026 | ||
| Node classification | twitch-gamers 50/25/25 (test) | 35 | Feb 26, 2026 | ||
| Few-shot classification | CUB meta (test) | 35 | Feb 26, 2026 | ||
| Sequence Classification | ListOps | 35 | Jun 9, 2026 | ||
| Image Classification Calibration | ImageNet 16H 1.0 (test) | 35 | Feb 26, 2026 | ||
| Video Summarization | SumMe | 35 | Mar 4, 2026 | ||
| Road Segmentation | Massachusetts Road Dataset | 35 | Feb 26, 2026 | ||
| Image Classification | CIFAR100 LT-100 1.0 (test) | 35 | Feb 26, 2026 | ||
| Lung cancer risk estimation | NLST MCAR mechanism (30% factors missing, 50% TP1 images missing) (test (791 subjects)) | 35 | Feb 26, 2026 | ||
| Video Panoptic Segmentation | VIPER (val) | 35 | Feb 26, 2026 |