Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2094 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Deepfake Detection | UADFV | 17 | Apr 24, 2026 | ||
| Image Classification | CIFAR-LT-100 Imbalance Factor 100 (test) | 17 | Feb 26, 2026 | ||
| Action Segmentation | YouTube Instructions (test) | 17 | Feb 26, 2026 | ||
| Part Segmentation | ShapeNet | 17 | May 7, 2026 | ||
| Scene Parsing | Cityscapes (test) | 17 | Feb 26, 2026 | ||
| 3D Object Detection | KITTI (val1) | 17 | Feb 26, 2026 | ||
| Disentanglement | SmallNORB (test) | 17 | Feb 26, 2026 | ||
| Semantic Segmentation | Potsdam (val) | 17 | Feb 26, 2026 | ||
| Semantic Segmentation | Vaihingen (val) | 17 | Feb 26, 2026 | ||
| Heart Rate estimation | AFRL All Tasks | 17 | Feb 26, 2026 | ||
| Bird-Eye-View (BEV) Object Detection | KITTI official (test) | 17 | Feb 26, 2026 | ||
| 3D Object Detection | KITTI official (test) | 17 | Feb 26, 2026 | ||
| Image Classification | CIFAR-FS 5-shot | 17 | Feb 26, 2026 | ||
| Text-to-Video Retrieval | MSR-VTT 1k-Miech (test) | 17 | Feb 26, 2026 | ||
| Video-to-Text Retrieval | MSR-VTT Official full-size (test) | 17 | Feb 26, 2026 | ||
| Time Series Classification | FordB (test) | 17 | Jun 1, 2026 | ||
| Time Series Classification | FordA (test) | 17 | Jun 1, 2026 | ||
| Mesh Reconstruction | Thingi32 | 17 | Feb 26, 2026 | ||
| Monocular 3D Object Detection | KITTI (val) | 17 | Apr 3, 2026 | ||
| Temporal Action Localization (Noun) | EPIC-Kitchens 100 (val) | 17 | Feb 26, 2026 | ||
| Machine Translation | WMT En-Tr 17 | 17 | Feb 27, 2026 | ||
| Table-to-text generation | WebNLG | 17 | Feb 26, 2026 | ||
| Image Classification | ImageNet 100% labels 1.0 (val) | 17 | Feb 26, 2026 | ||
| 3D Shape Classification | Cube Engraving (test) | 17 | Mar 4, 2026 | ||
| Knowledge Tracing | EdNet 1.0 (test) | 17 | Feb 26, 2026 |