Loading the SOTA2 catalog…
SOTA2 Research · benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
| Task | Dataset | Domain | Trend | Results | Last Update |
|---|---|---|---|---|---|
| Multivariate Time Series Forecasting | ECL | 89 | Jun 11, 2026 | ||
| Future Link Prediction | SocialEvolution inductive | 89 | Jul 7, 2026 | ||
| Image Classification | STL | 89 | May 19, 2026 | ||
| Camouflaged Object Detection | NC4K (test) | 89 | May 26, 2026 | ||
| 3D Human Mesh Recovery | 3DPW |
| 89 |
| Jun 29, 2026 |
| Classification | MNIST | 89 | May 12, 2026 |
|---|
| Out-of-Distribution Detection | Average (iNaturalist, SUN, Places, Textures) | 89 | May 27, 2026 |
|---|
| Image Classification | ImageNet Robustness Suite | 89 | Jun 24, 2026 |
|---|
| Univariate long sequence time-series forecasting | ETTm2 (test) | 89 | Feb 26, 2026 |
|---|
| Paraphrase Detection | MRPC | 89 | Feb 26, 2026 |
|---|
| Natural Language Inference | MedNLI (test) | 89 | Feb 26, 2026 |
|---|
| Video Super-Resolution | REDS (val) | 89 | Mar 6, 2026 |
|---|
| Emotion Recognition | MELD (test) | 89 | Jun 15, 2026 |
|---|
| Image Classification | Oxford-Flowers | 89 | Jun 24, 2026 |
|---|
| 3D Object Classification | ModelNet40 | 89 | Jun 18, 2026 |
|---|
| Machine Translation | WMT En-De '14 | 89 | Feb 26, 2026 |
|---|
| Video saliency prediction | DHF1K (test) | 89 | Feb 26, 2026 |
|---|
| Scene Text Detection | Total-Text | 89 | Jun 29, 2026 |
|---|
| Facial Attribute Classification | CelebA (test) | 89 | Feb 26, 2026 |
|---|
| Video Question Answering | TGIF-QA (test) | 89 | Feb 27, 2026 |
|---|
| Gaussian Denoising | BSD68 | 89 | Feb 26, 2026 |
|---|
| Image Generation | Cifar10 | 89 | Feb 26, 2026 |
|---|
| Referring Image Segmentation | RefCOCO+ (test A) | 89 | Feb 27, 2026 |
|---|
| Object Detection | FLIR | 89 | Jul 1, 2026 |
|---|
| Mathematical Reasoning | MathVerse mini | 89 | Jul 7, 2026 |
|---|