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 | SVHN (test) | 30 | May 19, 2026 | ||
| Continuous Control | Mountain Car POMDP | 30 | May 19, 2026 | ||
| Hill Car POMDP | Hill Car POMDP | 30 | May 19, 2026 | ||
| POMDP Planning | 2D-Continuous Light-Dark (test) | 30 | May 19, 2026 | ||
| Planning | 3D-Continuous Light-Dark | 30 | May 19, 2026 | ||
| Two-Agent 2D-Continuous Light-Dark Navigation |
| Two-Agent 2D-Continuous Light-Dark |
| 30 |
| May 19, 2026 |
| POMDP Navigation | 4D-Continuous Light-Dark | 30 | May 19, 2026 |
|---|
| Reinforcement Learning | Lunar Lander POMDP | 30 | May 19, 2026 |
|---|
| Visual Explanation | MS-COCO | 30 | Jun 2, 2026 |
|---|
| Reinforcement Learning | the Room (test) | 30 | May 19, 2026 |
|---|
| Classification | UCI Heart Disease | 30 | Jun 1, 2026 |
|---|
| Image Classification | SVHN | 30 | May 18, 2026 |
|---|
| Image Classification | MNIST | 30 | May 18, 2026 |
|---|
| Image Classification | CIFAR-10 | 30 | May 18, 2026 |
|---|
| Multimodal Prompt Injection Attack | TextVQA | 30 | May 18, 2026 |
|---|
| Multimodal Prompt Injection Attack | ImageNet | 30 | May 18, 2026 |
|---|
| Multimodal Prompt Injection Attack | MSCOCO | 30 | May 18, 2026 |
|---|
| Camera pose estimation | Re10K | 30 | Jul 7, 2026 |
|---|
| Multi-objective Optimization | MCIMP | 30 | May 18, 2026 |
|---|
| Multi-objective Optimization | MCCP | 30 | May 18, 2026 |
|---|
| Medical Referring Image Segmentation | MosMedData+ | 30 | May 18, 2026 |
|---|
| Medical Referring Image Segmentation | QaTa-COV19 | 30 | May 18, 2026 |
|---|
| Exploitability computation | 256-Kuhn poker (full) | 30 | May 18, 2026 |
|---|
| Code Generation | AetherCode (AC) | 30 | May 18, 2026 |
|---|
| Online shopping agent navigation | WebShop 128 (val) | 30 | May 15, 2026 |
|---|