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 |
|---|---|---|---|---|---|
| Cross-View Object Geo-Localization (Drone → Satellite) | CVOGL R (val) | 35 | Mar 17, 2026 | ||
| Anomaly Detection | Synthetic Gaussian mixture datasets global anomalies | 35 | Mar 17, 2026 | ||
| Multi-dimensional image inpainting | Light field data Greek, Origami 128×128×240 | 35 | Mar 17, 2026 | ||
| Multi-dimensional image inpainting | Videos (Foreman, Carphone) 144×176×150 | 35 | Mar 17, 2026 | ||
| Multi-dimensional image inpainting | MSIs Toys, Painting 256×256×31 |
| 35 |
| Mar 17, 2026 |
| Image Classification | CIFAR-100 Pathological | 35 | Jul 9, 2026 |
|---|
| Task goal completion | AppWorld (test challenge) | 35 | Jun 16, 2026 |
|---|
| Text-to-image generation | Short-DrawBench 1k prompts Stable Diffusion v1.5 base (test) | 35 | Mar 13, 2026 |
|---|
| Gender bias evaluation | Pronoun Change | 35 | Mar 12, 2026 |
|---|
| Bias classification | BiasBios | 35 | Mar 12, 2026 |
|---|
| Image Reconstruction | Kodak | 35 | Jun 19, 2026 |
|---|
| Hate speech detection | SBIC | 35 | Jun 18, 2026 |
|---|
| Image Classification | CIFAR100 | 35 | Apr 24, 2026 |
|---|
| Question Answering | SQuAD | 35 | May 6, 2026 |
|---|
| Image Classification | ImageNet-C blind-spot subset level 5 | 35 | Mar 11, 2026 |
|---|
| 4D Panoptic Occupancy Tracking | Occ3D Waymo | 35 | Jul 1, 2026 |
|---|
| Aspect-Based Sentiment Analysis | 35 | May 22, 2026 |
|---|
| Table Mathematical Reasoning | TabMWP (test) | 35 | Jun 11, 2026 |
|---|
| Mathematics Reasoning | MathVision mini | 35 | May 4, 2026 |
|---|
| Binary Classification | fertility | 35 | Apr 10, 2026 |
|---|
| Skeleton-based Temporal Action Segmentation | PKU-MMD (X-sub) | 35 | Mar 26, 2026 |
|---|
| Segmentation | UBB (UDIAT + BREASTUSG + BUSUCLM) (test) | 35 | Mar 9, 2026 |
|---|
| Spatial Reasoning | ViewSpatial-Bench | 35 | May 20, 2026 |
|---|
| Intellectual Property Protection | Office Home 65 | 35 | Mar 6, 2026 |
|---|
| Acoustic Scene Classification | TUT Acoustic Scenes | 35 | Mar 25, 2026 |
|---|