Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 886 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Best Arm Identification | Linear instances K=50, d=20 Appendix G (randomly generated) | 30 | Feb 26, 2026 | ||
| Language Modeling | (val) | 30 | May 12, 2026 | ||
| Image Classification | CIFAR-10 corrupted (test) | 30 | Feb 26, 2026 | ||
| Speech Recognition | MuST-C (test) | 30 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Gym v2 (test) | 30 | May 29, 2026 | ||
| Classification | Temporal heterogeneity synthetic datasets | 30 | Feb 26, 2026 | ||
| Image Generation | Cats base model (test) | 30 | Feb 26, 2026 | ||
| Scene Text Visual Question Answering | ST-VQA (val) | 30 | Feb 27, 2026 | ||
| Recommendation | Netflix (test) | 30 | Mar 9, 2026 | ||
| Color Classification | ColorMNIST | 30 | Feb 26, 2026 | ||
| Digit Classification | ColorMNIST | 30 | Feb 26, 2026 | ||
| Class-incremental Learning | Mini-Imagenet (test) | 30 | Mar 4, 2026 | ||
| Scene Text Recognition | IIIT (test) | 30 | Feb 26, 2026 | ||
| Articulated Mesh Reconstruction | DFaust Out of Distribution 6 (unseen pose) | 30 | Feb 26, 2026 | ||
| Articulated Mesh Reconstruction | DFaust Within Distribution 6 (train/test) | 30 | Feb 26, 2026 | ||
| Machine Translation | FLORES-101 (devtest) | 30 | Feb 27, 2026 | ||
| Dense Anomaly Detection | SMIYC AnomalyTrack | 30 | Feb 26, 2026 | ||
| Automatic Speech Recognition | TED-LIUM (test) | 30 | Mar 9, 2026 | ||
| Hyperspectral Image Reconstruction | KAIST 10 simulation scenes (test) | 30 | Feb 26, 2026 | ||
| Shape Classification | ALAN (test) | 30 | Feb 26, 2026 | ||
| Retrosynthetic Planning | USPTO-EXT (test) | 30 | Feb 26, 2026 | ||
| Image Classification | ImageNet Distribution Shifts Summary | 30 | Feb 26, 2026 | ||
| Video Super-resolution | Vimeo-90K-T BI degradation, Y channel (test) | 30 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL HalfCheetah Medium | 30 | May 8, 2026 | ||
| Space-Time Video Super-Resolution | GoPro | 30 | Feb 26, 2026 |