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 |
|---|---|---|---|---|---|
| Reasoning | CALI OOD (test) | 32 | Mar 4, 2026 | ||
| Ethical Reasoning | ETHICS (test) | 32 | Mar 4, 2026 | ||
| Reasoning | GLOQA (test) | 32 | Mar 4, 2026 | ||
| Reasoning | BBQ (test) | 32 | Mar 4, 2026 | ||
| Shortest Path | Shortest Path Degree 2, 4, 6, 8 (test) | 32 | Mar 4, 2026 | ||
| Knapsack Problem | Knapsack Degree 2, 4, 6, 8 (test) |
| 32 |
| Mar 4, 2026 |
| Portfolio Optimization | Portfolio Degree 2, 4, 6, 8 (test) | 32 | Mar 4, 2026 |
|---|
| Recommendation | Yelp Set-up (S) | 32 | Mar 4, 2026 |
|---|
| Recommendation | MovieLens 10M (test) | 32 | Jun 11, 2026 |
|---|
| Recommendation | MovieLens 10M (Set-up (S)) | 32 | Mar 4, 2026 |
|---|
| Node classification | House | 32 | May 14, 2026 |
|---|
| Logical Reasoning | ListOps | 32 | Mar 4, 2026 |
|---|
| Evidence Span Extraction | PV Miner | 32 | Jun 16, 2026 |
|---|
| Mathematics | AIME 24 | 32 | Mar 4, 2026 |
|---|
| Scholarly Title Generation | Scholarly Title | 32 | Mar 4, 2026 |
|---|
| Chemistry | SciBench | 32 | Mar 4, 2026 |
|---|
| Time Series Imputation | Weather | 32 | Feb 27, 2026 |
|---|
| Time Series Imputation | ETT | 32 | Feb 27, 2026 |
|---|
| Machine Translation | WMT En-Fr 14 | 32 | Apr 21, 2026 |
|---|
| Video-to-audio generation | VGGSound | 32 | Jun 12, 2026 |
|---|
| Edge Detection | BSDS v1 (test) | 32 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR100 (test) | 32 | Feb 26, 2026 |
|---|
| Tampered Text Localization | TFR (test) | 32 | Feb 26, 2026 |
|---|
| Tampered Text Classification | TFR (test) | 32 | Feb 26, 2026 |
|---|
| Image Classification | Tiny-ImageNet Dirichlet-0.05 (test) | 32 | Feb 26, 2026 |
|---|