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 |
|---|---|---|---|---|---|
| Tabular Anomaly Detection | Vowels | 30 | Feb 26, 2026 | ||
| Tabular Anomaly Detection | Thyroid | 30 | May 12, 2026 | ||
| Tabular Anomaly Detection | Satimage-2 | 30 | May 12, 2026 | ||
| Tabular Anomaly Detection | Satellite | 30 | May 12, 2026 | ||
| Tabular Anomaly Detection | Musk | 30 | Feb 26, 2026 | ||
| Tabular Anomaly Detection | Mammography |
| 30 |
| May 12, 2026 |
| Tabular Anomaly Detection | Glass | 30 | May 12, 2026 |
|---|
| Tabular Anomaly Detection | Annthyroid | 30 | Feb 26, 2026 |
|---|
| Tabular Anomaly Detection | Seismic | 30 | Feb 26, 2026 |
|---|
| Tabular Anomaly Detection | Lymphography | 30 | Feb 26, 2026 |
|---|
| Correctness detection | TruthfulQA | 30 | Mar 18, 2026 |
|---|
| Mathematical Reasoning | GSM8K | 30 | Mar 4, 2026 |
|---|
| General Knowledge (STEM) | MMLU STEM | 30 | Mar 17, 2026 |
|---|
| Long-context understanding | LongBench English | 30 | Mar 20, 2026 |
|---|
| Classification | Mutagenicity M0→M2 | 30 | Jun 2, 2026 |
|---|
| Graph Classification | FRANKENSTEIN node density F0→F2 shift | 30 | Feb 26, 2026 |
|---|
| Graph Classification | FRANKENSTEIN node density F0→F1 shift | 30 | Jun 2, 2026 |
|---|
| Mathematical Reasoning | MATH 500 | 30 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | AIME 24 | 30 | Feb 26, 2026 |
|---|
| Time Series Forecasting | Traffic | 30 | May 19, 2026 |
|---|
| Common Sense Reasoning | Common Sense Reasoning Suite (PIQA, ARC-Easy, ARC-Challenge, BoolQ, HellaSwag, Winogrande) zero-shot (test dev) | 30 | Feb 26, 2026 |
|---|
| Mutual Information Estimation | High-dimensional image benchmark 32x32 (val) | 30 | Feb 26, 2026 |
|---|
| Mutual Information Estimation | Low-Dimensional Benchmark S=2 to 50, D=10 (test) | 30 | Feb 26, 2026 |
|---|
| Mutual Information Estimation | Low-dimensional benchmark S=10 (test) | 30 | Feb 26, 2026 |
|---|
| Participatory Budgeting Rule Evaluation | Pabulib large (test) | 30 | Feb 26, 2026 |
|---|