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 |
|---|---|---|---|---|---|
| Interpretation error | ImageNet (val) | 40 | Feb 26, 2026 | ||
| Multi-label Image Classification | Pascal VOC 2007 | 40 | Mar 9, 2026 | ||
| SSAD querying | Selected shapes (test) | 40 | Feb 26, 2026 | ||
| Medical Image Segmentation | ACDC 10% labeled (test) | 40 | Feb 26, 2026 | ||
| Low-Light Image Enhancement | LSRW v1 (test) | 40 | May 13, 2026 | ||
| Out-of-Distribution Detection |
|---|
| ImageNet-1k V2 (test) |
| 40 |
| Feb 26, 2026 |
| Class-Incremental Learning | Split ImageNet-R 10 incremental tasks | 40 | May 13, 2026 |
|---|
| Conversational AI Evaluation | Chatbot Arena | 40 | May 8, 2026 |
|---|
| Two-sample testing | MNIST (test) | 40 | Feb 26, 2026 |
|---|
| Action Recognition | Kinetics400 (val) | 40 | Jun 25, 2026 |
|---|
| HOI Detection | V-COCO | 40 | Feb 26, 2026 |
|---|
| Image Classification | ISEKAI-pair | 40 | Feb 26, 2026 |
|---|
| Image Classification | ISEKAI-10 | 40 | Feb 26, 2026 |
|---|
| 3D Situated Question Answering | SQA3D (test) | 40 | Feb 26, 2026 |
|---|
| Gait Recognition | OUMVLP (test) | 40 | May 15, 2026 |
|---|
| Clustering | ImageNet-Dogs (test) | 40 | Mar 26, 2026 |
|---|
| Image Denoising | McMaster (test) | 40 | Apr 23, 2026 |
|---|
| Named Entity Recognition | NER | 40 | Feb 26, 2026 |
|---|
| Image Classification | MNIST (test) | 40 | Feb 26, 2026 |
|---|
| Link Prediction | NELL (test) | 40 | Apr 2, 2026 |
|---|
| Few-Shot Image Generation | MetFaces 10-shot | 40 | Mar 19, 2026 |
|---|
| OOD Detection | iNaturalist OOD | 40 | Mar 4, 2026 |
|---|
| Image Classification | MIT Indoor | 40 | Mar 4, 2026 |
|---|
| Denoising | Spaces (val) | 40 | Feb 26, 2026 |
|---|
| Video Question Answering | TVQA | 40 | Feb 26, 2026 |
|---|