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 | StanfordCars | 100 | May 26, 2026 | ||
| Robot Manipulation | RoboTwin Randomized 2.0 | 100 | Jul 8, 2026 | ||
| Response Harmfulness Detection | HarmBench | 100 | Jun 1, 2026 | ||
| Idiom recognition | 1,000 English idioms 1.0 (test) | 100 | Feb 26, 2026 | ||
| Reasoning | ARC Challenge |
| 100 |
| May 26, 2026 |
| Long-context language understanding | InfiniteBench | 100 | Jun 9, 2026 |
|---|
| Forecasting | Traffic | 100 | Jun 9, 2026 |
|---|
| Point Cloud Classification | ModelNet40 | 100 | Feb 26, 2026 |
|---|
| Point Cloud Classification | ScanObjectNN PB_T50_RS | 100 | Apr 14, 2026 |
|---|
| Graph regression | Peptides struct (test) | 100 | Jun 26, 2026 |
|---|
| Medical Report Generation | MIMIC-CXR (test) | 100 | Jun 1, 2026 |
|---|
| Image Retrieval | Revisited Paris (RPar) (Medium) | 100 | Feb 27, 2026 |
|---|
| Image Denoising | CBSD68 (test) | 100 | Apr 23, 2026 |
|---|
| Monocular Depth Estimation | KITTI Eigen split (test) | 100 | Apr 3, 2026 |
|---|
| Graph property prediction | SIDER | 100 | Jun 17, 2026 |
|---|
| OOD detection | Places (OOD) | 100 | Apr 28, 2026 |
|---|
| Polyp Segmentation | CVC-ColonDB | 100 | Jul 7, 2026 |
|---|
| Super-Resolution | DIV2K 1.0 (val) | 100 | Feb 26, 2026 |
|---|
| Object Detection | PASCAL VOC Novel Set 2 | 100 | Feb 27, 2026 |
|---|
| Machine Translation | WMT 2014 (test) | 100 | Feb 26, 2026 |
|---|
| Facial Expression Recognition | FERPlus (test) | 100 | Feb 26, 2026 |
|---|
| Object Detection | PASCAL VOC 2007+2012 (test) | 100 | Jun 5, 2026 |
|---|
| Semantic Segmentation | S3DIS | 100 | Jul 1, 2026 |
|---|
| 3D Hand Pose Estimation | NYU (test) | 100 | Feb 26, 2026 |
|---|
| Natural Language Generation | E2E (test) | 100 | May 12, 2026 |
|---|