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 |
|---|---|---|---|---|---|
| Few-shot node classification | CoraFull | 68 | May 1, 2026 | ||
| Paraphrase Detection | MRPC | 68 | Jun 4, 2026 | ||
| Multi-Hop Reasoning | LoCoMo | 68 | May 14, 2026 | ||
| Scientific Reasoning | TheoremQA | 68 | May 1, 2026 | ||
| Image Classification | Caltech101 | 68 | May 26, 2026 | ||
| Translation Attack | 17 supported languages LLaMA-3.2 1B |
| 68 |
| Mar 26, 2026 |
| Web Browsing | BrowseComp | 68 | May 18, 2026 |
|---|
| Classification | MNIST (test) | 68 | May 12, 2026 |
|---|
| Mobile GUI Automation | AndroidWorld | 68 | May 21, 2026 |
|---|
| Mathematical Reasoning | AIME 24 | 68 | Jun 17, 2026 |
|---|
| Question Answering | Bamboogle | 68 | May 11, 2026 |
|---|
| Mathematical Reasoning | MATH | 68 | Jun 19, 2026 |
|---|
| Radiology Question Answering | RadQA and Board-RadQA Combined (test) | 68 | Mar 9, 2026 |
|---|
| Image Classification | TinyImageNet-200 | 68 | Mar 30, 2026 |
|---|
| Out-of-Distribution Detection | African Big Five (test) | 68 | Mar 4, 2026 |
|---|
| Vision-centric Reasoning | RealWorldQA | 68 | Jun 26, 2026 |
|---|
| Deep Research | BrowseComp | 68 | Jun 9, 2026 |
|---|
| Robust Image Classification | CIFAR-10 | 68 | May 27, 2026 |
|---|
| Adversarial Purification | CIFAR-10 | 68 | Jul 7, 2026 |
|---|
| SIR dynamics forecasting | Erdős-Rényi graphs (out-of-sample) | 68 | Feb 27, 2026 |
|---|
| Safety Alignment | Salad Bench | 68 | Mar 10, 2026 |
|---|
| Safety Alignment | HH-RLHF | 68 | Mar 10, 2026 |
|---|
| Mathematical Reasoning | MATH 500 | 68 | May 8, 2026 |
|---|
| Robotic Manipulation | RoboCasa | 68 | Jul 7, 2026 |
|---|
| 3D point cloud semantic segmentation | ScanNet official (fold S1) | 68 | Jul 1, 2026 |
|---|