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 |
|---|---|---|---|---|---|
| Deraining | Rain100L (test) | 103 | Mar 5, 2026 | ||
| Commonsense Reasoning | Winogrande | 103 | May 12, 2026 | ||
| Image Classification | EMNIST Balanced | 103 | Feb 26, 2026 | ||
| Speaker Verification | VoxCeleb1 (Vox1-H) | 103 | Jul 9, 2026 | ||
| Image Retrieval | Flickr30K 1K (test) | 103 | Jun 4, 2026 | ||
| Question Answering | ARC Challenge (test) |
| 103 |
| May 19, 2026 |
| Semantic Segmentation | ACDC (test) | 103 | Jun 2, 2026 |
|---|
| Vision-and-Language Navigation | R2R-CE (val-seen) | 103 | Jul 3, 2026 |
|---|
| Node Classification | Cora (semi-supervised) | 103 | Feb 26, 2026 |
|---|
| Image Generation | CelebA-64 | 103 | May 19, 2026 |
|---|
| Unsupervised Domain Adaptation | VisDA unsupervised domain adaptation 2017 | 103 | Apr 30, 2026 |
|---|
| Recommendation | Amazon-Book | 103 | May 26, 2026 |
|---|
| Video Semantic Segmentation | Cityscapes (val) | 103 | Apr 14, 2026 |
|---|
| Link Prediction | FB15k | 103 | May 13, 2026 |
|---|
| Neural Architecture Search | NAS-Bench-201 CIFAR-100 (test) | 103 | May 19, 2026 |
|---|
| Factuality Evaluation | TruthfulQA | 103 | May 19, 2026 |
|---|
| Hyperspectral Image Classification | Pavia University (test) | 103 | Apr 28, 2026 |
|---|
| Question Answering | MMLU-Pro | 103 | Jul 8, 2026 |
|---|
| Visual Question Answering | A-OKVQA (test) | 103 | May 19, 2026 |
|---|
| Semantic Segmentation | Pascal VOC 21 classes (val) | 103 | Feb 26, 2026 |
|---|
| Local prediction | HAR (20% train) | 102 | Jul 7, 2026 |
|---|
| Linear Regression | Synthetic Multi-task Dataset d=50, K=20, epsilon=0.2 (test) | 102 | Jul 7, 2026 |
|---|
| Multi-task Linear Regression (Local Parameter Estimation) | Synthetic Multi-task Linear Regression (n=d=50, ε=0.2) (test) | 102 | Jul 7, 2026 |
|---|
| Local Prediction | HAR 60% (train) | 102 | Jul 7, 2026 |
|---|
| Multi-task Logistic Regression | Synthetic Multi-task Logistic Regression (n=d=50, epsilon=0.2) | 102 | Jul 7, 2026 |
|---|