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 |
|---|---|---|---|---|---|
| Multivariate long-term forecasting | ETTm1 T=96 (test) | 39 | Feb 26, 2026 | ||
| Novel View Synthesis | NeRF-DS | 39 | Mar 27, 2026 | ||
| World Knowledge | MMLU | 39 | May 26, 2026 | ||
| Pansharpening | WorldView-3 (WV3) reduced-resolution Wald's protocol (test) | 39 | Feb 26, 2026 | ||
| Hallucination assessment | Object-HalBench | 39 | Feb 26, 2026 | ||
| Image Segmentation |
|---|
| COCO |
| 39 |
| May 26, 2026 |
| Super-Resolution | BSD100 x3 (test) | 39 | May 26, 2026 |
|---|
| Visual Hallucination Evaluation | POPE MS-COCO Adversarial sampling (val) | 39 | Feb 26, 2026 |
|---|
| Traffic flow prediction | PeMS04 (test) | 39 | Jun 23, 2026 |
|---|
| Long-tailed Image Recognition | CIFAR-10 long-tailed (test) | 39 | May 14, 2026 |
|---|
| Univariate Time Series Forecasting | ETTh1 (test) | 39 | Feb 26, 2026 |
|---|
| Image Recognition | iWildCam | 39 | Apr 6, 2026 |
|---|
| Location and orientation estimation | VIGOR (Cross-Area) | 39 | Jun 11, 2026 |
|---|
| Collaborative Filtering | Amazon-Books | 39 | Feb 26, 2026 |
|---|
| Video-to-Text Retrieval | MSR-VTT 1K (test) | 39 | Feb 27, 2026 |
|---|
| Change Detection | SYSU | 39 | May 18, 2026 |
|---|
| Regression | Synthetic (weakly-periodic) Out-of-input-distribution (OOID) | 39 | Feb 26, 2026 |
|---|
| Visual Active Search | xView single-query setting with SC (Small Car) as Target (test) | 39 | Feb 26, 2026 |
|---|
| Visual Active Search | xView single-query setting Building as Target (test) | 39 | Feb 26, 2026 |
|---|
| Visual Active Search | xView single-query setting SB (Sail Boat) as Target (test) | 39 | Feb 26, 2026 |
|---|
| Prediction Interval Estimation | Sap flow | 39 | Feb 26, 2026 |
|---|
| Prediction Interval Estimation | Air 25 PM | 39 | Feb 26, 2026 |
|---|
| Prediction Interval Estimation | Air 10 PM | 39 | Feb 26, 2026 |
|---|
| Chat | AlpacaEval | 39 | Mar 4, 2026 |
|---|
| Click-through rate prediction | KDD12 | 39 | May 26, 2026 |
|---|