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 |
|---|---|---|---|---|---|
| Classification | Retina | 43 | May 27, 2026 | ||
| Scientific Reasoning | GPQA | 43 | May 15, 2026 | ||
| Medical Question Answering | MedQA US | 43 | May 19, 2026 | ||
| Classification | IMDB (test) | 43 | Apr 7, 2026 | ||
| AI-Generated Video Detection | GenVideo | 43 | Jul 7, 2026 | ||
| Information Retrieval |
| TREC DL 2019 |
| 43 |
| Jul 2, 2026 |
| Action Recognition | PKU-MMD 46/5 I (Xsub) | 43 | Apr 2, 2026 |
|---|
| Science Question Answering | ARC-C | 43 | Jun 1, 2026 |
|---|
| Backdoor Attack in Dataset Condensation | FMNIST | 43 | Apr 1, 2026 |
|---|
| Backdoor Attack in Dataset Condensation | SVHN | 43 | Apr 1, 2026 |
|---|
| Backdoor Attack in Dataset Condensation | CIFAR10 | 43 | Apr 1, 2026 |
|---|
| Backdoor Attack in Dataset Condensation | Tiny ImageNet | 43 | Apr 1, 2026 |
|---|
| Classification | ImageNet | 43 | Jun 26, 2026 |
|---|
| Logical Reasoning | ProofWriter | 43 | May 26, 2026 |
|---|
| Sequential Recommendation | Beauty | 43 | Apr 16, 2026 |
|---|
| Medication Recommendation | eICU | 43 | Apr 29, 2026 |
|---|
| Image Classification | CIFAR-10 uniform label noise, η=0.5 (test) | 43 | Mar 19, 2026 |
|---|
| Image Classification | CIFAR-10 uniform label noise, η=0.3 (test) | 43 | Mar 19, 2026 |
|---|
| Image Classification | CIFAR-10 uniform label noise, η=0.1 (test) | 43 | Mar 19, 2026 |
|---|
| Image Classification | Fashion-MNIST uniform noise η=0.5 (7-fold CV) | 43 | Mar 19, 2026 |
|---|
| Image Classification | Fashion-MNIST uniform noise η=0.4 (7-fold CV) | 43 | Mar 19, 2026 |
|---|
| Image Classification | Fashion-MNIST uniform noise η=0.3 (7-fold CV) | 43 | Mar 19, 2026 |
|---|
| Image Classification | Fashion-MNIST uniform noise η=0.2 (7-fold CV) | 43 | Mar 19, 2026 |
|---|
| Image Classification | Fashion-MNIST uniform noise η=0.1 (7-fold CV) | 43 | Mar 19, 2026 |
|---|
| Long-video understanding | LVBench (test) | 43 | Mar 19, 2026 |
|---|