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 |
|---|---|---|---|---|---|
| Anomaly Detection | SWaT (test) | 49 | May 18, 2026 | ||
| Grammatical Error Correction | NLPCC-18 Chinese GEC (test) | 49 | Feb 26, 2026 | ||
| Image Classification | AWA2 GZSL | 49 | Apr 21, 2026 | ||
| Zero-Shot Learning | CUB (unseen) | 49 | Feb 27, 2026 | ||
| Machine Reading Comprehension | Molweni (test) | 49 | Feb 26, 2026 | ||
| Multiview Pedestrian Detection |
| MultiviewX (test) |
| 49 |
| Jul 2, 2026 |
| Cuboid layout estimation | Stanford 2D-3D (test) | 49 | Feb 26, 2026 |
|---|
| Face Recognition | AgeDB 30 | 49 | Apr 13, 2026 |
|---|
| Salient Object Detection | RGBD135 (test) | 49 | Feb 26, 2026 |
|---|
| Semantic Segmentation | Cityscapes GTA5 source 1.0 (val) | 49 | Feb 26, 2026 |
|---|
| Image Classification | ImageNet original (val) | 49 | Feb 26, 2026 |
|---|
| Partial Person Re-identification | Partial-REID (test) | 49 | Feb 26, 2026 |
|---|
| Facial Landmark Detection | WFLW Blur | 49 | Feb 26, 2026 |
|---|
| Facial Landmark Detection | WFLW Make-up | 49 | Feb 26, 2026 |
|---|
| Keyword Spotting | Google Speech Commands V2 (test) | 49 | Jun 18, 2026 |
|---|
| Data-to-Text Generation | E2E (test) | 49 | Jun 1, 2026 |
|---|
| Architecture Performance Prediction | NAS-Bench-101 (test) | 49 | May 12, 2026 |
|---|
| Violence Detection | XD-Violence (test) | 49 | May 14, 2026 |
|---|
| Fine-grained Image Classification | Oxford Flowers | 49 | Feb 26, 2026 |
|---|
| Image Classification | Split MNIST | 49 | Feb 26, 2026 |
|---|
| Logical Query Answering | NELL995 (test) | 49 | Mar 18, 2026 |
|---|
| Image Dehazing | SOTS indoor RESIDE (test) | 49 | Apr 28, 2026 |
|---|
| Video Retrieval | HMDB51 (first split) | 49 | Feb 27, 2026 |
|---|
| Semantic Segmentation | Pascal VOC | 49 | Apr 23, 2026 |
|---|
| Semantic Image Synthesis | COCO-Stuff | 49 | Mar 24, 2026 |
|---|