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 |
|---|---|---|---|---|---|
| Multilingual Language Understanding | MMMLU (test) | 52 | May 6, 2026 | ||
| Robot Manipulation | SimplerEnv WidowX Visual Matching | 52 | Jul 7, 2026 | ||
| Zero-shot Text Classification | B2MWT-10C (test) | 52 | May 1, 2026 | ||
| Text Classification | N24News (test) | 52 | May 1, 2026 | ||
| 3D Object Detection | V2X-Sim |
| 52 |
| Apr 28, 2026 |
| Group Attack | MovieLens Unpopular items 1M | 52 | Apr 27, 2026 |
|---|
| Group Attack | MovieLens Popular items 1M | 52 | Apr 27, 2026 |
|---|
| Science Reasoning | GPQA-D | 52 | May 26, 2026 |
|---|
| Super Resolution | FFHQ 256 x 256 | 52 | May 22, 2026 |
|---|
| Molecular Property Prediction | Polaris & MoleculeACE Aggregate (58 tasks) | 52 | Apr 20, 2026 |
|---|
| Mathematical Reasoning | BRUMO 2025 | 52 | May 26, 2026 |
|---|
| Science Question Answering | SQA | 52 | Jun 18, 2026 |
|---|
| Overall Reasoning (Average) | LoCoMo | 52 | Apr 23, 2026 |
|---|
| Question Answering | TruthfulQA | 52 | Apr 10, 2026 |
|---|
| Knowledge-Based Visual Question Answering | E-VQA Single-Hop | 52 | May 6, 2026 |
|---|
| Image Quality Assessment Correlation | RealEstate10K | 52 | Apr 7, 2026 |
|---|
| Clustering | CIFAR-10 | 52 | Jun 2, 2026 |
|---|
| Anomaly Detection | MVTec-AD | 52 | Apr 7, 2026 |
|---|
| Constrained Clustering | COL1 | 52 | Mar 31, 2026 |
|---|
| Model Fingerprinting | CIFAR-100 | 52 | Mar 27, 2026 |
|---|
| Mathematical Reasoning | Minerva | 52 | May 26, 2026 |
|---|
| Image Classification | CIFAR-10 20% uniform noise (test) | 52 | Mar 19, 2026 |
|---|
| Image Classification | ImageSquawk | 52 | May 21, 2026 |
|---|
| Language Modeling | Wiki, C4, and Pile | 52 | Mar 18, 2026 |
|---|
| Robotic Manipulation | LIBERO-PLUS (test) | 52 | Jun 17, 2026 |
|---|