Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1515 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Head Pose Estimation | AFLW | 21 | Jun 18, 2026 | ||
| Image Classification | iNaturalist 2017 | 21 | Feb 27, 2026 | ||
| Caption-level correlation with human judgment | Composite (test) | 21 | Feb 26, 2026 | ||
| Entity Extraction | Kleister-NDA (val) | 21 | Feb 26, 2026 | ||
| Time Series Classification | UCR 30 | 21 | Apr 13, 2026 | ||
| Node classification | Freebase (test) | 21 | Feb 26, 2026 | ||
| Multiple Object Tracking | MOT20 | 21 | Feb 26, 2026 | ||
| Object Detection | SESYD Floorplans (test) | 21 | Feb 26, 2026 | ||
| Single-view depth estimation | NYU official 654 images v2 (test) | 21 | Feb 26, 2026 | ||
| Single-view depth estimation | NYUv2 36 (test) | 21 | Feb 26, 2026 | ||
| Real Noise Removal | DND (val) | 21 | Mar 4, 2026 | ||
| Image Classification | WebVision | 21 | May 28, 2026 | ||
| Adversarial Attack | MNIST (test) | 21 | Feb 26, 2026 | ||
| Facial Landmark Detection | 300W Fullset 2013 (test) | 21 | Feb 26, 2026 | ||
| Classification | Connect-4 (test) | 21 | May 11, 2026 | ||
| Recourse Cost Evaluation | German Credit | 21 | May 11, 2026 | ||
| Pathology detection from ECG data | PTB-XL (test) | 21 | Mar 23, 2026 | ||
| Node Classification | Cornell (fixed) | 21 | Feb 26, 2026 | ||
| Node Classification | Wisconsin (fixed) | 21 | Feb 26, 2026 | ||
| Node Classification | Texas (fixed splits) | 21 | Feb 26, 2026 | ||
| Video Classification | UCF-101 (split-1) | 21 | Feb 26, 2026 | ||
| Long-tailed Image Classification | CIFAR-10 LT gamma=100, beta=20% (test) | 21 | Mar 4, 2026 | ||
| Shape Classification | ScanObjectNN OBJ_ONLY (test) | 21 | Jun 11, 2026 | ||
| Anomaly Detection | Fishyscapes Lost & Found (val) | 21 | Feb 26, 2026 | ||
| Image Classification | ImageNet 1k (v2) | 21 | Feb 26, 2026 |