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 |
|---|---|---|---|---|---|
| GUI Agent | AndroidWorld | 70 | Feb 26, 2026 | ||
| Code Reasoning | HumanEval | 70 | Jun 18, 2026 | ||
| Robot Manipulation | SimplerEnv Google Robot tasks Visual Matching | 70 | Jun 12, 2026 | ||
| Coarse-grained Unlearning | Imagenette | 70 | Feb 26, 2026 | ||
| Medical Image Segmentation | AMOS-CT (test) |
| 70 |
| May 7, 2026 |
| Anomaly Detection and Localization | VisA (test) | 70 | Mar 20, 2026 |
|---|
| Depth Estimation | Sintel ~50 frames | 70 | May 26, 2026 |
|---|
| Semantic Segmentation | UAVid | 70 | Apr 20, 2026 |
|---|
| Long-term forecasting | Solar | 70 | Jun 26, 2026 |
|---|
| Object Tracking | VisEvent | 70 | Jun 26, 2026 |
|---|
| Language Understanding | MMLU | 70 | Apr 6, 2026 |
|---|
| Question Answering | NQ (Natural Questions) | 70 | Apr 10, 2026 |
|---|
| Node Classification | Cora Hnode = 0.57 | 70 | Feb 26, 2026 |
|---|
| Low-light Image Enhancement | LSRW | 70 | May 11, 2026 |
|---|
| Stance Detection | SEM 16 | 70 | Jun 26, 2026 |
|---|
| Image Classification | cifar10 | 70 | May 13, 2026 |
|---|
| Fine-grained visual classification | CUB-200-2011 (test) | 70 | Feb 26, 2026 |
|---|
| Low-light image enhancement | SID | 70 | May 14, 2026 |
|---|
| 3D Object Detection | V2XSet | 70 | Mar 23, 2026 |
|---|
| Mathematical Reasoning | GSM | 70 | Jun 2, 2026 |
|---|
| Semantic Segmentation | ADE20K A-847 (val) | 70 | Feb 27, 2026 |
|---|
| Medical Image Segmentation | Pancreas-NIH | 70 | Jul 3, 2026 |
|---|
| OOD Detection | ImageNet SUN | 70 | Apr 28, 2026 |
|---|
| Locomotion | D4RL walker2d-medium | 70 | May 19, 2026 |
|---|
| Locomotion | D4RL halfcheetah-medium | 70 | May 15, 2026 |
|---|