Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 986 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video Object Segmentation | DAVIS (val) | 28 | Feb 26, 2026 | ||
| Clustering | COIL-100 | 28 | Feb 26, 2026 | ||
| Character-level Language Modeling | Hutter Prize Wikipedia (test) | 28 | Feb 26, 2026 | ||
| Graph Classification | 28 | Jun 30, 2026 | |||
| Semantic Segmentation | SUN-RGBD 37 classes (test) | 28 | Feb 26, 2026 | ||
| Visual Tracking | OTB 2013 (50 videos) | 28 | Feb 26, 2026 | ||
| Domain Adaptation | Office+Caltech DeCAF6 features (various pairs) | 28 | Feb 26, 2026 | ||
| Clustering | COIL20 | 28 | Feb 26, 2026 | ||
| Code Generation | Django (test) | 28 | Feb 26, 2026 | ||
| Abnormal Event Detection | UCSD Ped1 | 28 | Feb 26, 2026 | ||
| Visual Question Answering | VQA 1 (test-standard) | 28 | Feb 26, 2026 | ||
| Optical Flow | KITTI (test) | 28 | Feb 26, 2026 | ||
| Scene Text Recognition | IIIT5K | 28 | Feb 26, 2026 | ||
| Text Localization | ICDAR 2013 (test) | 28 | Feb 26, 2026 | ||
| Image Clustering | COIL-100 | 28 | Feb 26, 2026 | ||
| Speech Recognition | Hub5'00 CH (test) | 28 | Feb 26, 2026 | ||
| Articulated Human Pose Estimation | LSP (test) | 28 | Feb 26, 2026 | ||
| Component estimation | Simulated dataset one level | 28 | Feb 26, 2026 | ||
| EEG emotion recognition | SEED-IV (Subject-independent) | 28 | Feb 26, 2026 | ||
| Image Generation | CelebA 64x64 discrete-time model (test) | 28 | Feb 26, 2026 | ||
| Operator learning | Darcy Flow 512x512 grid sub-sampled (test) | 28 | Feb 26, 2026 | ||
| Natural Language Inference | ANLI (test) | 28 | Feb 26, 2026 | ||
| 20-way 1-shot Classification | Omniglot (test) | 28 | Feb 26, 2026 | ||
| Binary Segmentation | PSVFM | 28 | Feb 26, 2026 | ||
| Binary Segmentation | GLAS | 28 | Feb 26, 2026 |