Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 621 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Boundary Detection | BSDS500 | 37 | Feb 26, 2026 | ||
| Trajectory Prediction | UNIV v1.0 (test) | 37 | Feb 26, 2026 | ||
| Digit Classification | SVHN → MNIST target (test) | 37 | Feb 27, 2026 | ||
| Machine Translation | WMT Ro-En '16 | 37 | Apr 8, 2026 | ||
| Sentiment Classification | SST (test) | 37 | Feb 26, 2026 | ||
| Node Classification | CiteSeer (fixed split) | 37 | Mar 31, 2026 | ||
| Node Classification | PubMed (random) | 37 | Feb 26, 2026 | ||
| Image Generation | SVHN | 37 | Apr 28, 2026 | ||
| Shadow Detection | ISTD (test) | 37 | May 13, 2026 | ||
| AMR Generation | LDC2015E86 (test) | 37 | Feb 26, 2026 | ||
| Image Classification | ImageCLEF-DA | 37 | Feb 26, 2026 | ||
| Face Verification | IJB-A (test) | 37 | Feb 26, 2026 | ||
| Group Activity Recognition | Collective Activity (test) | 37 | Feb 26, 2026 | ||
| Group activity recognition | Volleyball dataset (test) | 37 | Feb 26, 2026 | ||
| Optical Flow | Sintel clean (test) | 37 | Jun 30, 2026 | ||
| Facial Landmark Detection | 300-W Common Subset | 37 | Feb 26, 2026 | ||
| Word Alignment | English-French (test) | 37 | Feb 26, 2026 | ||
| Machine Comprehension | CBT-CN (val) | 37 | Feb 26, 2026 | ||
| Machine Comprehension | CBT-NE (val) | 37 | Feb 26, 2026 | ||
| Sentiment Classification | Yelp Polarity (test) | 37 | Feb 26, 2026 | ||
| Super-Resolution | Set14 | 37 | Feb 26, 2026 | ||
| Molecular Optimization | Practical Molecular Optimization (PMO) | 37 | Mar 4, 2026 | ||
| Binary classification (ASD vs. HC) | ABIDE (test) | 37 | Mar 23, 2026 | ||
| Regression | MoleculeNet Lipophilicity (test) | 37 | May 21, 2026 | ||
| Regression | Energy UCI (test) | 37 | Apr 30, 2026 |