Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2320 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Out-of-Distribution Detection | LSUNr | 16 | Feb 26, 2026 | ||
| Image Classification | Kather | 16 | Feb 26, 2026 | ||
| Unsupervised object segmentation | CUB | 16 | Feb 26, 2026 | ||
| No-Reference Image Quality Assessment | Psychophysical experiment dataset (12 images) | 16 | Feb 26, 2026 | ||
| Image Dehazing | RS-Haze (test) | 16 | Feb 26, 2026 | ||
| Point cloud completion | ShapeNet-ViPC supervised (test) | 16 | Feb 26, 2026 | ||
| Data-to-Text Generation | DART | 16 | Feb 26, 2026 | ||
| Graph Classification | MolHIV v1 (test) | 16 | Feb 26, 2026 | ||
| Moment Query | Ego4D (test) | 16 | Jun 5, 2026 | ||
| BCI classification | Hinss inter-subject 2021 | 16 | Feb 26, 2026 | ||
| BCI classification | Hinss2021 (inter-session) | 16 | Feb 26, 2026 | ||
| Few-shot classification | Cars cross-domain from tiered-ImageNet | 16 | Feb 26, 2026 | ||
| Few-shot classification | CUB cross-domain from tiered-ImageNet | 16 | Feb 26, 2026 | ||
| Few-shot classification | Cars cross-domain from mini-ImageNet | 16 | Feb 26, 2026 | ||
| Recommendation | Steam-200k 1.0 (test) | 16 | Feb 26, 2026 | ||
| Recommendation | CiteULike | 16 | Feb 26, 2026 | ||
| Semantic Segmentation | Taskonomy (test) | 16 | Feb 26, 2026 | ||
| Image Classification | Sports | 16 | Jun 5, 2026 | ||
| Commonsense Reasoning | CSQA (dev) | 16 | Feb 26, 2026 | ||
| Vital Signs Prediction | BIDMC Vital Signs (test) | 16 | Feb 26, 2026 | ||
| Foreground Segmentation | Pascal-5i (1) | 16 | Feb 26, 2026 | ||
| Zero-Shot Object Classification | aPY | 16 | Feb 26, 2026 | ||
| Novel View Synthesis | ShapeNet (test) | 16 | Feb 26, 2026 | ||
| Behavioral stylometry | Lichess High-ranked subsets | 16 | Feb 26, 2026 | ||
| Common Sense Reasoning | WinoGrande (dev) | 16 | Apr 1, 2026 |