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 |
|---|---|---|---|---|---|
| Absent Keyphrase Generation | LDKP3K (test) | 44 | Feb 27, 2026 | ||
| Diagnosis Classification | ADHD-200 | 44 | Apr 24, 2026 | ||
| Medical Image Classification | OrganMNIST3D | 44 | Jun 15, 2026 | ||
| Node Classification | Film 60%/20%/20% | 44 | Mar 11, 2026 | ||
| Safety Alignment | WildJailbreak | 44 | Feb 26, 2026 | ||
| Multi-hop Question Answering |
| 2WikiMultiHopQA (val) |
| 44 |
| May 12, 2026 |
| Point Cloud Quality Assessment | SJTU WPC 2.0 (cross-dataset) | 44 | Feb 26, 2026 |
|---|
| Node Classification | Arxiv Source: 1950-2011, Target: 2014-2016 | 44 | May 12, 2026 |
|---|
| Node Classification | Arxiv Source: 1950-2007, Target: 2014-2016 | 44 | May 12, 2026 |
|---|
| Adversarial Attack | COCO (val) | 44 | Feb 26, 2026 |
|---|
| Traffic Forecasting | Tokyo JARTIC 2021 (test) | 44 | Feb 26, 2026 |
|---|
| Node Classification | Flickr | 44 | Jun 2, 2026 |
|---|
| Time Series Imputation | ETT | 44 | Feb 27, 2026 |
|---|
| Cooling load forecasting | DCData 25% training data 1.0 (test) | 44 | Feb 26, 2026 |
|---|
| Cooling load forecasting | DCData 50% train data 1.0 (test) | 44 | Feb 26, 2026 |
|---|
| Molecule Conformer Generation | GEOM-Drugs δ = 0.75Å (test) | 44 | Apr 24, 2026 |
|---|
| Text-to-Video Generation | HunyuanVideo | 44 | Jun 26, 2026 |
|---|
| Anomaly Detection | Cardiotocography | 44 | May 12, 2026 |
|---|
| Image Classification | ImageNet 20 Dp: CIFAR10 downstream (test) | 44 | Feb 26, 2026 |
|---|
| Symbolic Regression | E. coli growth LLM-SR Suite | 44 | Feb 27, 2026 |
|---|
| Document Question Answering | Qasper | 44 | Mar 12, 2026 |
|---|
| Recommendation | Movielens | 44 | Jun 11, 2026 |
|---|
| Tool Retrieval | Mixed | 44 | Feb 26, 2026 |
|---|
| Tool Retrieval | Toolink | 44 | Feb 26, 2026 |
|---|
| Tool Retrieval | Gorilla | 44 | Feb 26, 2026 |
|---|