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 |
|---|---|---|---|---|---|
| Classification | AV-MNIST | 46 | Jul 1, 2026 | ||
| Univariate Time-series Forecasting | Exchange (test) | 46 | Mar 17, 2026 | ||
| Natural Language Understanding | AGIEval | 46 | Jul 3, 2026 | ||
| Classification | GLIOMA | 46 | Mar 31, 2026 | ||
| Shape Matching | SCAPE remeshed (test) | 46 | Feb 26, 2026 | ||
| Traveling Salesman Problem |
| TSP-200 |
| 46 |
| Jun 15, 2026 |
| Image Classification | 11 fine-grained classification datasets average | 46 | Feb 26, 2026 |
|---|
| Image Denoising | CBSD68 sigma=25 (test) | 46 | Feb 26, 2026 |
|---|
| Automatic Diagnosis | Dxy | 46 | Feb 26, 2026 |
|---|
| Membership Inference Attack | CIFAR-100 | 46 | May 29, 2026 |
|---|
| Instance Segmentation | MS COCO 2014 2017 (val) | 46 | Mar 20, 2026 |
|---|
| Commonsense Reasoning | CommonsenseQA (CSQA) v1.0 (test) | 46 | Feb 26, 2026 |
|---|
| Out-of-Distribution Detection | FashionMNIST (In-Distribution) vs EMNIST (Out-of-Distribution) (test) | 46 | May 21, 2026 |
|---|
| OOD Detection | CIFAR-10 OOD (test) | 46 | Mar 30, 2026 |
|---|
| Panoptic Segmentation | COCO | 46 | Jun 16, 2026 |
|---|
| Video Instance Segmentation | YTVIS 2019 (test val) | 46 | Apr 2, 2026 |
|---|
| Semantic Segmentation | Pascal VOC 10-1 protocol 2012 (val) | 46 | Feb 26, 2026 |
|---|
| Few-shot classification | ChestX (test) | 46 | Feb 26, 2026 |
|---|
| Motion Forecasting | Argoverse 1 (test) | 46 | Mar 12, 2026 |
|---|
| Time Series Forecasting | Wind | 46 | Apr 21, 2026 |
|---|
| Semantic Segmentation | PASCAL VOC 2012 original (val) | 46 | Feb 26, 2026 |
|---|
| Argument Classification | ERE-EN (test) | 46 | Feb 26, 2026 |
|---|
| Text-to-Image Generation | COCO 30k subset 2014 (val) | 46 | Feb 26, 2026 |
|---|
| Offline Reinforcement Learning | D4RL walker2d medium-replay v2 | 46 | Jun 2, 2026 |
|---|
| Natural Language Inference | E-SNLI | 46 | Feb 27, 2026 |
|---|