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 |
|---|---|---|---|---|---|
| Graph property prediction | ClinTox | 102 | Apr 14, 2026 | ||
| Semantic Segmentation | BDD-100K (val) | 102 | Feb 26, 2026 | ||
| Object Detection | Objects365 (val) | 102 | Jun 9, 2026 | ||
| Named Entity Recognition | BC5CDR | 102 | May 21, 2026 | ||
| Video Prediction | KTH 10 -> 20 steps (test) |
| 102 |
| Jul 1, 2026 |
| RGBD Saliency Detection | DES | 102 | Feb 26, 2026 |
|---|
| Image Denoising | SIDD (test) | 102 | Apr 8, 2026 |
|---|
| Multi-turn response selection | Ubuntu Dialogue Corpus V1 (test) | 102 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR-10 (test) | 102 | Feb 26, 2026 |
|---|
| Skeleton-based Action Recognition | Kinetics-Skeleton | 102 | Mar 23, 2026 |
|---|
| Human Pose Estimation | LSP (test) | 102 | Feb 26, 2026 |
|---|
| Medical Image Segmentation | MosMedData+ | 102 | Jun 29, 2026 |
|---|
| Image Classification | VTAB-1K 1.0 (test) | 102 | Feb 26, 2026 |
|---|
| Medical Image Segmentation | ISIC 2017 | 102 | Jun 2, 2026 |
|---|
| Over-refusal | XSTest | 102 | Jun 25, 2026 |
|---|
| Linear Regression | Linear Regression (synthetic) | 101 | Jul 7, 2026 |
|---|
| Node Classification | WikiCS | 101 | Jul 3, 2026 |
|---|
| Instruction Following | IFEval | 101 | Jun 4, 2026 |
|---|
| Video Reasoning | VSI-Bench | 101 | Jul 7, 2026 |
|---|
| Medical Image Segmentation | AMOS 2022 | 101 | May 7, 2026 |
|---|
| Long-context Reasoning | LongBench | 101 | Apr 28, 2026 |
|---|
| Image Editing | ImgEdit | 101 | Jun 26, 2026 |
|---|
| Visual Question Answering | MMMU | 101 | Jun 11, 2026 |
|---|
| Question Answering | NQ | 101 | May 22, 2026 |
|---|
| Video Understanding | LVB | 101 | Jun 16, 2026 |
|---|