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 |
|---|---|---|---|---|---|
| Image Classification | DermaMNIST (test) | 32 | Feb 26, 2026 | ||
| Image Classification | Kather (test) | 32 | Feb 26, 2026 | ||
| Classification | HANS (test) | 32 | Feb 26, 2026 | ||
| Classification | MNLI (val) | 32 | Feb 26, 2026 | ||
| Link Prediction | Wikipedia transductive | 32 | May 18, 2026 | ||
| Image Classification | CIFAR100 |
| 32 |
| Feb 27, 2026 |
| Image Classification | CIFAR-10 | 32 | Feb 26, 2026 |
|---|
| Binary Classification | adult (AD) (test) | 32 | Feb 26, 2026 |
|---|
| Video Question Answering | IVQA | 32 | Feb 27, 2026 |
|---|
| 5-way 5-shot Classification | tiered-ImageNet (test) | 32 | Feb 26, 2026 |
|---|
| Semantic Segmentation | FSS-1000 1-shot | 32 | May 20, 2026 |
|---|
| Image Classification | ImageNet and derived distribution shifts standard suite (test val) | 32 | May 18, 2026 |
|---|
| Offline Reinforcement Learning | D4RL Hopper Medium-Replay | 32 | May 8, 2026 |
|---|
| LF Mislabeling Identification | DN clipart | 32 | Feb 26, 2026 |
|---|
| LF Mislabeling Identification | DN painting | 32 | Feb 26, 2026 |
|---|
| LF Mislabeling Identification | DN quickdraw | 32 | Feb 26, 2026 |
|---|
| LF Mislabeling Identification | Youtube | 32 | Feb 26, 2026 |
|---|
| LF Mislabeling Identification | Yelp | 32 | Feb 26, 2026 |
|---|
| LF Mislabeling Identification | Spambase | 32 | Feb 26, 2026 |
|---|
| LF Mislabeling Identification | PW | 32 | Feb 26, 2026 |
|---|
| LF Mislabeling Identification | Mushroom | 32 | Feb 26, 2026 |
|---|
| LF Mislabeling Identification | Census | 32 | Feb 26, 2026 |
|---|
| Image Captioning | NoCaps 1.0 (val) | 32 | Apr 7, 2026 |
|---|
| Image Classification | CIFAR-10-LT Imbalance Ratio 100 (test) | 32 | Feb 26, 2026 |
|---|
| Image-goal navigation | MP3D (test) | 32 | Jun 30, 2026 |
|---|