Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1682 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Reinforcement Learning | Atari 2600 57 games | 20 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | Human3.6M Protocol-III (test) | 20 | Feb 26, 2026 | ||
| Single Image Super-Resolution | Urban100 scale 4 | 20 | Feb 26, 2026 | ||
| Hash Learning | CIFAR10 (test) | 20 | Feb 26, 2026 | ||
| Single Image De-raining | Real-world rainy images (test) | 20 | Feb 26, 2026 | ||
| Relationship phrase detection | VRD | 20 | Feb 27, 2026 | ||
| Visual Object Tracking | OTB50 (test) | 20 | Feb 26, 2026 | ||
| Visual Tracking | VOT 2015 (test) | 20 | Feb 26, 2026 | ||
| Viewpoint Estimation | PASCAL3D+ | 20 | Feb 26, 2026 | ||
| Word Prediction | LAMBADA CONTROL (all) | 20 | Feb 26, 2026 | ||
| Language Modeling | LAMBADA (dev) | 20 | Apr 1, 2026 | ||
| Activity Recognition | MPII (test) | 20 | Feb 26, 2026 | ||
| Link Prediction | arXiv 14 (test) | 20 | Feb 26, 2026 | ||
| Link Prediction | PPI 5 (test) | 20 | Feb 26, 2026 | ||
| Phoneme Recognition | TIMIT core (test) | 20 | Feb 26, 2026 | ||
| Molecular Conformation Generation | GEOM-Drugs | 20 | Jun 5, 2026 | ||
| molecule description generation | ChEBI-20 2022 (test) | 20 | Feb 26, 2026 | ||
| Protein-Ligand Binding Affinity Prediction | PDBbind | 20 | May 11, 2026 | ||
| Transcriptomic Class Prediction | Multiple Animals Extended Transcriptomic Dataset | 20 | Feb 26, 2026 | ||
| Transcriptomic Subclass Prediction | Multiple Animals Extended Transcriptomic Dataset | 20 | Feb 26, 2026 | ||
| Molecular property prediction | QM9 2014 (test) | 20 | Feb 26, 2026 | ||
| Amyloid Positive vs. Negative | OASIS 3 (five-fold cross-validation) | 20 | Feb 26, 2026 | ||
| AD conversion prediction | OASIS-3 (five-fold cross-validation) | 20 | Feb 26, 2026 | ||
| Classification | MoleculeNet Tox21 (test) | 20 | Feb 26, 2026 | ||
| Reproducibility | Simulated dataset k2=6 | 20 | Feb 26, 2026 |