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 |
|---|---|---|---|---|---|
| Time Series Forecasting | IaaS | 40 | Jun 5, 2026 | ||
| Image-Text Retrieval | Flickr30K | 40 | May 1, 2026 | ||
| Open-Set Multi-Target Domain Adaptation | DomainNet Mini 60/66 (test) | 40 | Feb 26, 2026 | ||
| Open-Set Multi-Target Domain Adaptation | Office-Home 15/50 (test) | 40 | Feb 26, 2026 | ||
| OOD Detection | CoComageNet mono |
| 40 |
| Feb 26, 2026 |
| OOD Detection | CoComageNet | 40 | Feb 26, 2026 |
|---|
| Error Detection | Average All shifts (test) | 40 | Feb 26, 2026 |
|---|
| Error Detection | Corruptions (test) | 40 | Feb 26, 2026 |
|---|
| Error Detection | Adversarial Attacks (test) | 40 | Feb 26, 2026 |
|---|
| Error Detection | In-distribution (test) | 40 | Feb 26, 2026 |
|---|
| Distribution Shift Detection | BROAD (test) | 40 | Feb 26, 2026 |
|---|
| Dense Video Captioning | YouCook2 | 40 | Apr 21, 2026 |
|---|
| Open-vocabulary Segmentation | COCO Object | 40 | May 20, 2026 |
|---|
| Multiple-choice task | ECARE KRE | 40 | Feb 26, 2026 |
|---|
| Multiple-choice task | COSE_KRE | 40 | Feb 26, 2026 |
|---|
| Time Series Imputation | Electricity | 40 | Jul 9, 2026 |
|---|
| Fine-Grained Visual Categorization | FGVC | 40 | Feb 26, 2026 |
|---|
| Common Sense Reasoning | NoRa Irrelevant Rationales | 40 | Feb 26, 2026 |
|---|
| Video Generation | MSRVTT (val) | 40 | Feb 26, 2026 |
|---|
| State Forecasting | CAISO | 40 | Feb 26, 2026 |
|---|
| Multimodal Reasoning | MMBench EN | 40 | May 19, 2026 |
|---|
| Faithfulness evaluation | MDACE (test) | 40 | Feb 27, 2026 |
|---|
| Table Structure Recognition | FinTabNet | 40 | Apr 20, 2026 |
|---|
| Visual Reasoning | MM-Vet | 40 | Apr 3, 2026 |
|---|
| Sound Probing | Sound Probing v1 (test) | 40 | Feb 26, 2026 |
|---|