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 |
|---|---|---|---|---|---|
| Semantic Segmentation | Pascal Context 59 (val) | 38 | Feb 26, 2026 | ||
| Accuracy Estimation | Nonliving-26 | 38 | Jun 5, 2026 | ||
| Camera tracking | BONN dynamic sequences | 38 | May 14, 2026 | ||
| Semantic Segmentation | OpenEarthMap | 38 | Apr 10, 2026 | ||
| Long-context Question Answering | NarrativeQA | 38 | Feb 27, 2026 | ||
| CWQ Freebase (test) |
| 38 |
| Jun 2, 2026 |
| OOD Detection | CIFAR100 ID TImageNet OOD | 38 | May 26, 2026 |
|---|
| Semantic Segmentation | LVIS 92^i | 38 | Mar 31, 2026 |
|---|
| Infrared Small Target Detection | IRSTD-1K (test) | 38 | Jun 2, 2026 |
|---|
| Stereo Matching | KITTI 15 | 38 | May 13, 2026 |
|---|
| Visual Question Answering | LLaVA-Bench-In-The-Wild | 38 | Feb 26, 2026 |
|---|
| Generalized OOD Detection | CIFAR-10 with Places365 (semantic OOD) and CIFAR-10-C (covariate OOD) (test) | 38 | Feb 26, 2026 |
|---|
| Out-of-Distribution Detection and Generalization | CIFAR-10 ID Textures semantic OOD CIFAR-10-C covariate OOD | 38 | Feb 26, 2026 |
|---|
| Out-of-Distribution Detection and Generalization | CIFAR-10 ID SVHN semantic OOD CIFAR-10-C covariate OOD | 38 | Feb 26, 2026 |
|---|
| Single Image Super-Resolution | Set5 x2 (test) | 38 | Mar 10, 2026 |
|---|
| Multi-page Document Question Answering | MP-DocVQA | 38 | Apr 28, 2026 |
|---|
| Classification | RSNA | 38 | Apr 13, 2026 |
|---|
| Time Series Forecasting | Illness (ILI) (test) | 38 | Feb 26, 2026 |
|---|
| Repo-level code generation | CODEAGENTBENCH | 38 | Feb 26, 2026 |
|---|
| Anomaly Localization | VisA | 38 | Jun 15, 2026 |
|---|
| Pointwise Grading | AlignBench | 38 | Feb 26, 2026 |
|---|
| Video Generation | UCF-101 | 38 | Jun 5, 2026 |
|---|
| Causal Structure Learning | Sachs | 38 | May 28, 2026 |
|---|
| Ranking | BEIR selected subset v1.0.0 (test) | 38 | Feb 26, 2026 |
|---|
| Bot Detection | Twibot-22 | 38 | Feb 26, 2026 |
|---|