Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1665 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Visual Speech Recognition | LRS3 low-resource (test) | 20 | Feb 26, 2026 | ||
| Semantic Segmentation | Cityscapes without background class | 20 | Feb 26, 2026 | ||
| 6-DoF Pose Tracking | HO3D | 20 | Jul 8, 2026 | ||
| Continual learning | VG+VAW 7-task sequence (test) | 20 | Feb 26, 2026 | ||
| 3D Whole-Body Mesh Recovery | AGORA (test) | 20 | Feb 26, 2026 | ||
| Photometric Stereo | DiLiGenT (All 96 images) | 20 | Feb 26, 2026 | ||
| Image Denoising | Man | 20 | Jun 2, 2026 | ||
| 3D Human Pose and Shape Estimation | Human3.6M 14 joints (test) | 20 | Mar 30, 2026 | ||
| Table Structure Recognition | PubTables-1M | 20 | Jul 2, 2026 | ||
| Video captioning | MSRVTT (full) | 20 | Feb 26, 2026 | ||
| 3D Object Detection | Waymo to KITTI (val) | 20 | Feb 26, 2026 | ||
| 3D Lane Detection | OpenLane (val) | 20 | Jul 1, 2026 | ||
| Glacier Front Delineation | CaFFe (test) | 20 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH | 20 | Apr 2, 2026 | ||
| Object Detection | Comic (test) | 20 | Mar 20, 2026 | ||
| Semantic Segmentation | DeLiVER | 20 | Feb 26, 2026 | ||
| 3D Object Detection (Pedestrian) | Waymo Open Dataset (WOD) v1.2 (val) | 20 | Feb 26, 2026 | ||
| Fine-grained Classification | Stanford Dogs 40% symmetric noise (test) | 20 | Feb 26, 2026 | ||
| Fine-grained Classification | Stanford Dogs 20% symmetric noise (test) | 20 | Feb 26, 2026 | ||
| Interactive environment task success | ALFWorld (test) | 20 | Feb 26, 2026 | ||
| Object Detection | nuImages | 20 | Feb 26, 2026 | ||
| Anomaly detection | RS UEA (test) | 20 | Feb 26, 2026 | ||
| Anomaly detection | CT UEA (test) | 20 | Feb 26, 2026 | ||
| Anomaly detection | SAD UEA (test) | 20 | Feb 26, 2026 | ||
| Anomaly detection | NAT UEA (test) | 20 | Feb 26, 2026 |