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 |
|---|---|---|---|---|---|
| Online Class-Incremental Learning | CIFAR-100 10 tasks (test) | 115 | May 29, 2026 | ||
| Modulation Classification | IEEE Dataport IQ (test) | 115 | May 6, 2026 | ||
| Mathematical Reasoning | HMMT25 | 115 | May 20, 2026 | ||
| Image Classification | GTSRB | 115 | May 19, 2026 | ||
| 6DoF Pose Estimation |
| DTTD-Mobile |
| 115 |
| Feb 27, 2026 |
| Compressive Sensing Reconstruction | General100 | 115 | May 12, 2026 |
|---|
| Robotic Manipulation | RoboTwin 2.0 | 115 | Jun 9, 2026 |
|---|
| Online Shopping | Webshop | 115 | Jul 8, 2026 |
|---|
| General Reasoning | MMLU-Pro | 115 | Jun 23, 2026 |
|---|
| Scientific Reasoning | GPQA Main | 115 | Jun 5, 2026 |
|---|
| Generalized Category Discovery | FGVC-Aircraft | 115 | May 12, 2026 |
|---|
| Mathematical Reasoning | Olympiad Bench | 115 | Feb 26, 2026 |
|---|
| Jailbreak Defense | AdvBench | 115 | Jun 1, 2026 |
|---|
| OOD detection | CIFAR-10 (test) | 115 | May 12, 2026 |
|---|
| Traveling Salesman Problem | TSPLIB (test) | 115 | Feb 26, 2026 |
|---|
| Image Classification | 11 Downstream Classification Datasets (ImageNet, Flowers102, DTD, OxfordPets, StanfordCars, UCF101, Caltech101, Food101, SUN397, FGVC-Aircraft, EuroSAT) standard (test) | 115 | Feb 27, 2026 |
|---|
| Visual Question Answering | ScienceQA (test) | 115 | May 15, 2026 |
|---|
| Mathematical Reasoning | GSM8K (val) | 115 | Jun 17, 2026 |
|---|
| 3D Object Detection | View-of-Delft (VoD) Entire Annotated Area (val) | 115 | Apr 7, 2026 |
|---|
| Image Retrieval | Revisited Paris (RPar) (Hard) | 115 | Feb 27, 2026 |
|---|
| Text Retrieval | Flickr30K 1K (test) | 115 | Jun 4, 2026 |
|---|
| Image Super-Resolution | Set14 | 115 | Feb 26, 2026 |
|---|
| Image Captioning | nocaps (val) | 115 | Apr 2, 2026 |
|---|
| Image Classification | ImageNet (val) | 115 | Feb 26, 2026 |
|---|
| Clustering | Fashion-MNIST | 115 | Jul 9, 2026 |
|---|