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 |
|---|---|---|---|---|---|
| Optical Flow | Sintel Clean (train) | 104 | May 11, 2026 | ||
| Neural Architecture Search | ImageNet16-120 NAS-Bench-201 (val) | 104 | May 19, 2026 | ||
| Salient Object Detection | ECSSD (test) | 104 | Feb 26, 2026 | ||
| Person Re-identification | Occluded-REID (test) | 104 | May 8, 2026 | ||
| Face Verification | AgeDB |
| 104 |
| Jun 1, 2026 |
| Object Detection | Sim10K → Cityscapes (test) | 104 | Feb 27, 2026 |
|---|
| Few-shot classification | CUB | 104 | Jul 7, 2026 |
|---|
| Image Classification | CIFAR-10 (test) | 104 | Feb 26, 2026 |
|---|
| Node Classification | Coauthor Physics | 104 | Jun 23, 2026 |
|---|
| Multi-Object Tracking | MOT17 | 104 | Apr 2, 2026 |
|---|
| Image Retrieval | NUS-WIDE (test) | 104 | Jun 2, 2026 |
|---|
| Explainability | ImageNet (val) | 104 | Feb 26, 2026 |
|---|
| End-to-End Text Spotting | ICDAR 2015 | 104 | Apr 23, 2026 |
|---|
| Clustering | USPS | 104 | Apr 7, 2026 |
|---|
| Image Classification | FEMNIST (test) | 104 | Apr 2, 2026 |
|---|
| Anomaly Detection | MPDD (test) | 104 | May 28, 2026 |
|---|
| Long Video Understanding | LongVideoBench | 103 | Jul 2, 2026 |
|---|
| Open-domain Question Answering | HotpotQA | 103 | Jun 11, 2026 |
|---|
| Medical Visual Question Answering | PathVQA | 103 | Jul 1, 2026 |
|---|
| Mathematics | AIME25 | 103 | Jun 2, 2026 |
|---|
| Clustering | Scene-15 | 103 | Jun 4, 2026 |
|---|
| Image Classification | Food | 103 | Jun 4, 2026 |
|---|
| Medical Visual Question Answering | PMC-VQA | 103 | May 28, 2026 |
|---|
| Long-context Memory Evaluation | LongMemEval | 103 | Jun 2, 2026 |
|---|
| Video Anomaly Detection | ShanghaiTech (SHT) (test) | 103 | May 26, 2026 |
|---|