Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1766 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Regression | ELEVATORS (test) | 19 | Feb 26, 2026 | ||
| Novel View Synthesis | Synthetic dynamic scenes | 19 | Feb 26, 2026 | ||
| Urban Localization | RobotCar Seasons v2 | 19 | Feb 26, 2026 | ||
| Visual Place Recognition | MSLS (test) | 19 | Feb 26, 2026 | ||
| Object Discovery | COCO 20k 2014 (train val) | 19 | Feb 26, 2026 | ||
| Object Discovery | PASCAL VOC 12 (trainval) | 19 | Feb 26, 2026 | ||
| Video Prediction | UCF-101 (test) | 19 | Apr 28, 2026 | ||
| 3D Object Detection | Waymo to nuScenes (val) | 19 | Feb 26, 2026 | ||
| 3D Semantic Segmentation | ScanNet | 19 | Apr 8, 2026 | ||
| Pedestrian Path Prediction | ZARA1 (test) | 19 | May 19, 2026 | ||
| Pedestrian Path Prediction | UNIV (test) | 19 | May 19, 2026 | ||
| Robot Pose Estimation | DREAM-real Panda 3CAM-AK | 19 | Apr 16, 2026 | ||
| Sign Language Recognition | CSL-Daily (test) | 19 | Feb 26, 2026 | ||
| Emotion Recognition | CMU-MOSEI | 19 | Feb 26, 2026 | ||
| Video Compression | HEVC RGB | 19 | Feb 26, 2026 | ||
| Scene Graph Classification (SGCls) | Visual Genome | 19 | Feb 26, 2026 | ||
| Generalized Few-Shot Object Detection | MS-COCO 10-shot (test) | 19 | Feb 26, 2026 | ||
| Few-shot classification | ISIC | 19 | Feb 26, 2026 | ||
| Relation Extraction | TACRED-Revisit (test) | 19 | Feb 26, 2026 | ||
| Zero-shot Image Classification | ImageNet-Sketch (test) | 19 | Feb 26, 2026 | ||
| Zero-shot Image Classification | ImageNet-A (test) | 19 | Feb 26, 2026 | ||
| Zero-shot Image Classification | ImageNet V2 (test) | 19 | Feb 26, 2026 | ||
| Attribute Detection | OVAD zero-shot cross-dataset transfer | 19 | Feb 26, 2026 | ||
| One-shot Skeleton-based Action Recognition | NTU-120 SOAR One-shot protocol | 19 | Feb 26, 2026 | ||
| Instance Segmentation | ADE20K | 19 | Mar 5, 2026 |