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 |
|---|---|---|---|---|---|
| Face Forgery Detection | DFDCP | 74 | Apr 24, 2026 | ||
| Robot Manipulation | RoboTwin Clean 2.0 | 74 | Jul 8, 2026 | ||
| Mathematics | AIME 2025 | 74 | Jun 9, 2026 | ||
| Time Series Forecasting | ETTh1 -> ETTh2 | 74 | Mar 17, 2026 | ||
| Open-Domain Question-Answering | NQ | 74 | Jun 11, 2026 | ||
| Anomaly Segmentation |
| MPDD |
| 74 |
| Jul 2, 2026 |
| Multivariate Long-term Time Series Forecasting | Weather | 74 | Feb 26, 2026 |
|---|
| Multivariate Long-term Time Series Forecasting | ETTm2 | 74 | Feb 26, 2026 |
|---|
| Out-of-Distribution Detection and Generalization | CIFAR-10 ID LSUN-C semantic OOD & CIFAR-10-C covariate OOD | 74 | Feb 26, 2026 |
|---|
| Refusal Rate Evaluation | OK (test) | 74 | Apr 21, 2026 |
|---|
| Science Question Answering | ScienceQA IMG (test) | 74 | Apr 7, 2026 |
|---|
| Node Classification | ogbn-arxiv | 74 | Feb 26, 2026 |
|---|
| Multimodal Understanding | MME Perception | 74 | Jun 16, 2026 |
|---|
| Image Classification | BreastMNIST | 74 | Apr 21, 2026 |
|---|
| Fine-Grained Visual Categorization | FGVCAircraft | 74 | Mar 18, 2026 |
|---|
| Anomaly Detection | MVTec AD | 74 | May 25, 2026 |
|---|
| Question Answering | StrategyQA (test) | 74 | May 15, 2026 |
|---|
| Image Classification | iNaturalist | 74 | Apr 28, 2026 |
|---|
| Semantic Scene Completion | SemanticKITTI (test) | 74 | Jun 23, 2026 |
|---|
| Semantic Segmentation | SYNTHIA-to-Cityscapes 16 categories (val) | 74 | Feb 26, 2026 |
|---|
| Image Generation | ImageNet 512x512 (test) | 74 | May 18, 2026 |
|---|
| Image Classification | ImageNet-W | 74 | Feb 26, 2026 |
|---|
| Video Compression | HEVC Class D | 74 | Feb 26, 2026 |
|---|
| Long-tailed Image Classification | Places-LT (test) | 74 | May 26, 2026 |
|---|
| Image Captioning | COCO (Karpathy split) | 74 | Feb 27, 2026 |
|---|