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 |
|---|---|---|---|---|---|
| Camera pose estimation | ACID | 30 | Mar 31, 2026 | ||
| Scene Classification | WHU-RS19 | 30 | Jun 11, 2026 | ||
| Vertical Perception | NavSpace | 30 | Mar 11, 2026 | ||
| Long-term forecasting | Traffic | 30 | Jun 4, 2026 | ||
| Long-term forecasting | Electricity | 30 | Jun 4, 2026 | ||
| Time Series Classification |
| BME |
| 30 |
| Jun 4, 2026 |
| Time Series Classification | CBF | 30 | Jun 4, 2026 |
|---|
| Memory-bandwidth efficiency measurement | Autoregressive decoding workload | 30 | Mar 11, 2026 |
|---|
| Investment Sequencing | Regional Investment Instances 7-9 regions k = 3, 4, 5 (test) | 30 | Mar 10, 2026 |
|---|
| Personalized Federated Learning | DRAKE (Self) | 30 | Mar 10, 2026 |
|---|
| Node Classification Robustness Certification | Cora | 30 | Mar 10, 2026 |
|---|
| Video Understanding | Video Benchmarks Aggregate | 30 | Apr 7, 2026 |
|---|
| Epidemic Forecasting | Japan TB medium-term (test) | 30 | Mar 10, 2026 |
|---|
| Object Navigation | HM3D v2 | 30 | Jul 1, 2026 |
|---|
| Molecular Inverse Design | QM9 | 30 | Mar 10, 2026 |
|---|
| Safety Evaluation | AdvBench | 30 | May 7, 2026 |
|---|
| Sound Source Localization | VGG-SS (test) | 30 | Mar 25, 2026 |
|---|
| SAE Activation | Gemma and Llama Scope SAE features 3-9 cross-entropy range | 30 | Mar 9, 2026 |
|---|
| SAE Activation | Neuronpedia SAE features entropy 3-9 | 30 | Mar 9, 2026 |
|---|
| SAE Feature Activation | GemmaScope 102 features | 30 | Mar 9, 2026 |
|---|
| Label Purity | Open Images | 30 | Mar 9, 2026 |
|---|
| Node classification | Arts | 30 | Jun 11, 2026 |
|---|
| 5-way classification | CropDisease (test) | 30 | Mar 6, 2026 |
|---|
| 5-way classification | EuroSAT (test) | 30 | Mar 6, 2026 |
|---|
| 5-way classification | ISIC (test) | 30 | Mar 6, 2026 |
|---|