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 |
|---|---|---|---|---|---|
| Object Detection | S-DGOD (test) | 43 | Jun 9, 2026 | ||
| Visual Question Answering | WSI-VQA | 43 | Jun 9, 2026 | ||
| Generative Hallucination | Object HalBench | 43 | Jun 1, 2026 | ||
| Audio Question Answering | MUSIC-AVQA 1.0 (test) | 43 | Feb 26, 2026 | ||
| Visual Odometry | TUM RGBD | 43 | Apr 27, 2026 | ||
| GaoFen-2 reduced-resolution |
| 43 |
| Apr 15, 2026 |
| 3D Anomaly Detection | Real3D-AD (test) | 43 | Jun 25, 2026 |
|---|
| Referring 3D Instance Segmentation | ScanRefer (val) | 43 | Jun 5, 2026 |
|---|
| Time Series Forecasting | ETTh1 -> ETTm2 | 43 | Mar 17, 2026 |
|---|
| Node Classification | Chameleon (filtered splits) | 43 | Feb 26, 2026 |
|---|
| Anomaly Detection | MVTec-AD | 43 | Feb 26, 2026 |
|---|
| Event Relation Extraction | Causal-TimeBank 1.0 (test) | 43 | Feb 26, 2026 |
|---|
| Reasoning | GSM8K (test) | 43 | Jun 24, 2026 |
|---|
| Action Unit Detection | BP4D | 43 | Feb 26, 2026 |
|---|
| Image Clustering | CIFAR-20 | 43 | Mar 17, 2026 |
|---|
| Medical Image Classification | ISIC | 43 | May 7, 2026 |
|---|
| Person Re-identification | PRCC (standard split) | 43 | Mar 4, 2026 |
|---|
| Regression | PovertyMap (test) | 43 | Feb 26, 2026 |
|---|
| Multi-label Classification | Corel5k | 43 | May 12, 2026 |
|---|
| Deepfake Detection | DeepfakeDetection (DFD) (test) | 43 | Mar 26, 2026 |
|---|
| Commonsense Reasoning | Commonsense Reasoning Suite BoolQ, PIQA, HellaSwag, WinoGrande, ARC-e, ARC-c | 43 | Mar 27, 2026 |
|---|
| Video Grounding | ActivityNet Captions | 43 | Feb 26, 2026 |
|---|
| Open Domain Generalization | OfficeHome | 43 | Feb 26, 2026 |
|---|
| Machine Translation | FLORES | 43 | Feb 26, 2026 |
|---|
| Audio recognition | Speech Commands V2 | 43 | Feb 26, 2026 |
|---|