Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1967 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Offline Task-Incremental Learning | S-CIFAR-100 (test) | 18 | Feb 26, 2026 | ||
| Offline Task-Incremental Learning | S-Cifar-10 (test) | 18 | Feb 26, 2026 | ||
| Offline Class-Incremental Learning | S-Cifar-100 (test) | 18 | Feb 26, 2026 | ||
| Offline Class-Incremental Learning | S-Cifar-10 (test) | 18 | Feb 26, 2026 | ||
| Continual Learning | S-Cifar-100 streaming (test) | 18 | Feb 26, 2026 | ||
| Continual Learning | S-Cifar-10 streaming (test) | 18 | Feb 26, 2026 | ||
| Monocular Depth Estimation | NYU Depth V2 | 18 | Feb 26, 2026 | ||
| Image Classification | Split MNIST S (test) | 18 | Feb 26, 2026 | ||
| Dynamic Human Body Modeling | D-FAUST 5 (Seen Individual) | 18 | Feb 26, 2026 | ||
| Face Alignment | 300W | 18 | Feb 26, 2026 | ||
| Image Classification | ADP (test) | 18 | Feb 26, 2026 | ||
| Speaker Diarization | AliMeeting (test) | 18 | Jun 24, 2026 | ||
| Continuous Control | MuJoCo Reacher | 18 | Apr 13, 2026 | ||
| Depth Estimation | KITTI Eigen split 80m cap | 18 | Feb 26, 2026 | ||
| Document Dewarping | DocUNet (test) | 18 | Feb 26, 2026 | ||
| Entity Linking | CORD (test) | 18 | Feb 26, 2026 | ||
| Action Detection | Charades | 18 | Jun 23, 2026 | ||
| Sketch-based Few-Shot Class-Incremental Learning | Sketchy | 18 | Feb 26, 2026 | ||
| 3D point cloud deformation | DFAUST (test) | 18 | Feb 26, 2026 | ||
| 2D-to-3D Reconstruction | ShapeNet 1 (test) | 18 | Feb 26, 2026 | ||
| Depth Completion | SUN RGB-D (test) | 18 | Feb 26, 2026 | ||
| Vulnerability Detection | CodeXGLUE (test) | 18 | Feb 26, 2026 | ||
| Semantic Segmentation | Stanford2D3D Pinhole (fold-1) | 18 | Feb 26, 2026 | ||
| Natural Language Inference | NLI adversarial benchmark (test) | 18 | Feb 26, 2026 | ||
| Sentiment Classification | Amazon (OOD) | 18 | Feb 26, 2026 |