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 |
|---|---|---|---|---|---|
| Deep Metric Learning | CARS196 (test) | 56 | Feb 26, 2026 | ||
| Image Classification | Office-Home (leave-one-domain-out) | 56 | Feb 26, 2026 | ||
| Link Prediction | UMLS | 56 | Feb 26, 2026 | ||
| Image Classification | Imbalanced CIFAR-100 (val) |
| 56 |
| Feb 26, 2026 |
| Link prediction | YAGO3-10 | 56 | Jun 9, 2026 |
|---|
| Text classification | R8 (test) | 56 | Feb 26, 2026 |
|---|
| Saliency Prediction | MIT300 (test) | 56 | Feb 26, 2026 |
|---|
| Semantic Segmentation | Foggy Driving (FD) (test) | 56 | Feb 26, 2026 |
|---|
| Out-of-distribution Detection | SVHN CIFAR-10 in-distribution out-of-distribution (test) | 56 | Feb 26, 2026 |
|---|
| Multi-Object Tracking | KITTI Tracking (test) | 56 | Feb 26, 2026 |
|---|
| Multimodal Emotion Recognition | IEMOCAP | 56 | Jul 3, 2026 |
|---|
| Facial Attribute Classification | LFWA (test) | 56 | Feb 26, 2026 |
|---|
| Face Restoration | VggFace2 (test) | 56 | Feb 26, 2026 |
|---|
| Multivariate Time Series Forecasting | Solar-Energy (test) | 56 | Feb 26, 2026 |
|---|
| Scene Text Recognition | SVT-Perspective (test) | 56 | Feb 26, 2026 |
|---|
| Story Cloze Test | Story Cloze (test) | 56 | Mar 4, 2026 |
|---|
| Image Retrieval | CARS 196 (test) | 56 | Feb 26, 2026 |
|---|
| Node Classification | Cora 1% label rate | 56 | Feb 26, 2026 |
|---|
| Node Classification | Cora (0.5% label rate) | 56 | Feb 26, 2026 |
|---|
| Natural Language Inference | MultiNLI mismatched (test) | 56 | Feb 26, 2026 |
|---|
| Image Retrieval | CARS196 | 56 | Feb 26, 2026 |
|---|
| Image Geolocation | Im2GPS (test) | 56 | Apr 29, 2026 |
|---|
| Phrase-structure parsing | PTB (§23) | 56 | Feb 26, 2026 |
|---|
| Machine Comprehension | CBT-CN (test) | 56 | Feb 26, 2026 |
|---|
| Machine Comprehension | CBT NE (test) | 56 | Feb 26, 2026 |
|---|