Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1673 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Facial Landmark Localization | 300W (Common) | 20 | Feb 26, 2026 | ||
| Inpainting | Places wide masks 512 x 512 | 20 | Feb 26, 2026 | ||
| Inpainting | Places narrow masks 512 x 512 | 20 | Feb 26, 2026 | ||
| Generative Modeling | kmnist (test) | 20 | Feb 26, 2026 | ||
| Generative Modeling | letters (test) | 20 | Feb 26, 2026 | ||
| Density Estimation | KMNIST (test) | 20 | Feb 26, 2026 | ||
| Node Classification | ogbn-products official (test) | 20 | Feb 26, 2026 | ||
| Emotion Recognition | RAVDESS (val) | 20 | Feb 26, 2026 | ||
| Point Cloud Classification | ModelNet40 raw (test) | 20 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K (val) | 20 | Feb 26, 2026 | ||
| Node Classification | ogbn-arxiv transductive official (test) | 20 | Feb 26, 2026 | ||
| Macroscopic time series forecasting | Wiki | 20 | Feb 26, 2026 | ||
| Macroscopic time series forecasting | M5 | 20 | Feb 26, 2026 | ||
| Macroscopic time series forecasting | Rossmann | 20 | Feb 26, 2026 | ||
| Poisson Image Denoising | Set12 | 20 | Feb 26, 2026 | ||
| Language Modeling | WikiText-103 small setting (test) | 20 | Jun 1, 2026 | ||
| Language Modeling | WikiText-103 small setting (val) | 20 | Jun 1, 2026 | ||
| Emotion recognition | AffectNet 8 classes (test val) | 20 | Feb 26, 2026 | ||
| Node Classification | PubMed dense | 20 | Feb 26, 2026 | ||
| Node Classification | Citeseer dense | 20 | Feb 26, 2026 | ||
| Node Classification | Cora dense | 20 | Feb 26, 2026 | ||
| Image Classification | ImageNet 20 | 20 | Feb 26, 2026 | ||
| Spatio-temporal Action Localization | UCF101 24 | 20 | Apr 6, 2026 | ||
| Single Image Reflection Separation | SIR2 Wild (test) | 20 | Feb 26, 2026 | ||
| Single Image Reflection Separation | SIR2 Postcard (test) | 20 | Feb 26, 2026 |