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 |
|---|---|---|---|---|---|
| Logical Reasoning | CLUTRR (test) | 39 | Jun 15, 2026 | ||
| Optic Cup Segmentation | Drishti-GS | 39 | Apr 24, 2026 | ||
| Optic Disc Segmentation | Drishti-GS | 39 | Apr 24, 2026 | ||
| Semi-supervised medical image segmentation | Synapse (20% labeled) | 39 | Mar 6, 2026 | ||
| Node Classification | COAUTHOR-PHY | 39 | Apr 13, 2026 | ||
| Commonsense Reasoning |
|---|
| WinoGrande standard (test) |
| 39 |
| Apr 28, 2026 |
| Text Classification | BIOS | 39 | Apr 21, 2026 |
|---|
| Factual Consistency Evaluation | QAGS-XSum | 39 | Feb 26, 2026 |
|---|
| AWGN removal | BSD68 color (test) | 39 | Feb 26, 2026 |
|---|
| Univariate long-term forecasting | ETTm1 Univariate (test) | 39 | Feb 26, 2026 |
|---|
| Image Classification | ImageNet-Adversarial | 39 | May 29, 2026 |
|---|
| Formal Theorem Proving | miniF2F Isabelle (test) | 39 | Feb 26, 2026 |
|---|
| Gaussian Denoising | BSD68 | 39 | May 8, 2026 |
|---|
| Image Classification | ImageNet-1k (val) | 39 | Mar 20, 2026 |
|---|
| Logical Reasoning | Shuffled Objects | 39 | May 14, 2026 |
|---|
| 6D Pose Estimation | BOP challenge | 39 | Feb 26, 2026 |
|---|
| Multi-class Network Intrusion Detection | CICIDS 2017 | 39 | May 19, 2026 |
|---|
| Node Classification | CiteSeer | 39 | Feb 27, 2026 |
|---|
| Local Lipschitz constant estimation | 16-dimensional synthetic dataset (test) | 39 | Feb 26, 2026 |
|---|
| Linear Classification | COVIDx (test) | 39 | Feb 27, 2026 |
|---|
| Linear Classification | RSNA (test) | 39 | Feb 27, 2026 |
|---|
| Linear Classification | CheXpert (test) | 39 | Feb 27, 2026 |
|---|
| Brain Network Classification | ABIDE | 39 | Mar 24, 2026 |
|---|
| Scene Recognition | SUN397 base-to-new | 39 | May 8, 2026 |
|---|
| Multilabel classification | mediamill (test) | 39 | May 12, 2026 |
|---|