Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2536 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multi-modal Benchmark | MMBench (dev) | 15 | Feb 26, 2026 | ||
| Topic Classification | AG News (test) | 15 | Feb 26, 2026 | ||
| Sentiment Analysis | SST-2 (test) | 15 | Feb 26, 2026 | ||
| Loosely controlled table-to-text generation | ToTTO Logic2Text-style (test) | 15 | Feb 26, 2026 | ||
| Table-to-Text Generation | ToTTo Over (test) | 15 | Feb 26, 2026 | ||
| Table-to-Text Generation | ToTTo Non (test) | 15 | Feb 26, 2026 | ||
| Table-to-Text Generation | ToTTo All (dev) | 15 | Feb 26, 2026 | ||
| Image Classification | Melanoma (test) | 15 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 (test) | 15 | Feb 26, 2026 | ||
| Image Classification | CATvsDOG (test) | 15 | Feb 26, 2026 | ||
| Node Classification | Computers (random 10/10/80) | 15 | Apr 13, 2026 | ||
| Future Pose Estimation | H3.6M | 15 | Feb 26, 2026 | ||
| Joint Completion | 3DPW | 15 | Feb 26, 2026 | ||
| Motion Prediction | AMASS | 15 | Feb 26, 2026 | ||
| Long-tail Image Classification | Places LT | 15 | Feb 26, 2026 | ||
| Entity Linking | GERBIL | 15 | Feb 26, 2026 | ||
| Depth Completion | ScanNet from VOID | 15 | Feb 26, 2026 | ||
| Depth Completion | SceneNet from VOID | 15 | Feb 26, 2026 | ||
| Depth Completion | Waymo from KITTI | 15 | Feb 26, 2026 | ||
| Depth Completion | nuScenes from KITTI | 15 | Feb 26, 2026 | ||
| Depth Completion | VKITTI FOG | 15 | Feb 26, 2026 | ||
| Depth Completion | KITTI → Virtual KITTI (test) | 15 | Feb 26, 2026 | ||
| Fake news detection | Constraint | 15 | Feb 26, 2026 | ||
| Visual Question Answering | MemeVQA 1.0 (test) | 15 | Feb 26, 2026 | ||
| Deepfake Detection | DeeperForensics (DFo) (test) | 15 | Feb 26, 2026 |