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 |
|---|---|---|---|---|---|
| Reasoning | BIG-Bench Hard (BBH) (test) | 62 | May 19, 2026 | ||
| Image Classification | Office-Home v1.0 (test) | 62 | Apr 30, 2026 | ||
| Low-light image enhancement | SDSD-out | 62 | Jun 30, 2026 | ||
| Multi-hop Question Answering | Bamboogle | 62 | Mar 11, 2026 | ||
| Semantic Segmentation | PASCAL Context |
| 62 |
| Jun 16, 2026 |
| Image Classification | CIFAR-100-N | 62 | May 28, 2026 |
|---|
| Object Detection | DIOR | 62 | Apr 21, 2026 |
|---|
| Medical Image Segmentation | QaTa-COV19 (test) | 62 | Jul 7, 2026 |
|---|
| Image Classification | MNIST NN (test) | 62 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | ASDiv (test) | 62 | Apr 23, 2026 |
|---|
| Node Classification | Texas (60% 20% 20% random splits) | 62 | Mar 11, 2026 |
|---|
| Image Classification | DermaMNIST | 62 | Jun 24, 2026 |
|---|
| End-to-End Text Spotting | ICDAR 2015 (test) | 62 | Feb 26, 2026 |
|---|
| Image Classification | CelebA | 62 | Jun 2, 2026 |
|---|
| 3D Reconstruction | ShapeNet | 62 | Feb 26, 2026 |
|---|
| Node Classification | ogbn-proteins (test) | 62 | Mar 11, 2026 |
|---|
| Named Entity Recognition | Few-NERD INTER 1.0 (test) | 62 | Feb 26, 2026 |
|---|
| Image Denoising | Kodak (test) | 62 | Apr 29, 2026 |
|---|
| Video Quality Assessment | KoNViD 1k (test) | 62 | Feb 26, 2026 |
|---|
| Speech Separation | WHAMR! (test) | 62 | May 8, 2026 |
|---|
| Multivariate Time-series Forecasting | ETTh2 hourly (test) | 62 | Feb 26, 2026 |
|---|
| Anomaly Detection | satellite | 62 | May 12, 2026 |
|---|
| Retrieval | Natural Questions (test) | 62 | Feb 26, 2026 |
|---|
| Information Extraction | SROIE (test) | 62 | Mar 5, 2026 |
|---|
| Nuclei Segmentation | MoNuSeg | 62 | Jun 9, 2026 |
|---|