Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1146 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Face Forgery Detection | FaceForensics++ NT (test) | 25 | Feb 26, 2026 | ||
| Face Forgery Detection | FaceForensics++ F2F (test) | 25 | Feb 26, 2026 | ||
| Unconditional Image Generation | FFHQ 256x256 (test) | 25 | Feb 26, 2026 | ||
| Class-Incremental Learning | ImageNet disjoint-CIL 800+40 | 25 | Feb 26, 2026 | ||
| Knowledge Graph Question Answering | ComplexWebQuestions (CWQ) 1.1 (test) | 25 | Feb 26, 2026 | ||
| Foreground Segmentation | Pascal-5i (3) | 25 | Apr 7, 2026 | ||
| Scene Graph Classification | VG 50 (test) | 25 | Feb 26, 2026 | ||
| Audio Tagging | AudioSet (test) | 25 | May 19, 2026 | ||
| Visual Object Tracking | NFS | 25 | Feb 26, 2026 | ||
| Unsupervised Semantic Segmentation | Cityscapes | 25 | Apr 2, 2026 | ||
| BEV segmentation | nuScenes v1.0 (val) | 25 | Feb 26, 2026 | ||
| Video Frame Interpolation | Xiph 4K (test) | 25 | Feb 26, 2026 | ||
| Semantic Segmentation | PASCAL (val) | 25 | Feb 27, 2026 | ||
| Graph property prediction | OGBG-CODE2 (val) | 25 | Feb 26, 2026 | ||
| HSI Reconstruction | KAIST 10 scenes (Scene5) | 25 | Feb 26, 2026 | ||
| Novel View Synthesis | NeRF-synthetic original (test) | 25 | Feb 26, 2026 | ||
| Classification | CheXpert | 25 | Feb 26, 2026 | ||
| Depression Detection | TRT (test) | 25 | Feb 26, 2026 | ||
| Depression Detection | RSDD (test) | 25 | Feb 26, 2026 | ||
| Change Detection | LEVIR (test) | 25 | Feb 26, 2026 | ||
| Question Answering | HeadQA English | 25 | Feb 26, 2026 | ||
| Named Entity Recognition | Wiki | 25 | Jun 8, 2026 | ||
| Code Search | Java (test) | 25 | Feb 26, 2026 | ||
| Code Search | Python (test) | 25 | Feb 26, 2026 | ||
| Continuous Control | MuJoCo HalfCheetah | 25 | Apr 13, 2026 |