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 |
|---|---|---|---|---|---|
| EEG Seizure Classification | Bonn University EEG dataset O vs S | 42 | Feb 26, 2026 | ||
| Binary EEG Seizure Detection | Bonn University dataset (Z vs S) | 42 | Feb 26, 2026 | ||
| Untargeted Attack | ImageNet (test) | 42 | Feb 26, 2026 | ||
| Image Classification | TALL-20 | 42 | Jun 8, 2026 | ||
| Clustering | ProteinFold | 42 | Feb 26, 2026 |
| Multiple Choice | COPA | 42 | Jun 5, 2026 |
|---|
| Time Series Forecasting | Tourism Monthly | 42 | Feb 26, 2026 |
|---|
| Time Series Forecasting | M3 Quarterly | 42 | Feb 26, 2026 |
|---|
| Time Series Forecasting | M3 Monthly | 42 | Feb 26, 2026 |
|---|
| Debugging | OR-Debug-Bench (450 stratified samples) | 42 | Feb 26, 2026 |
|---|
| Reinforcement Learning | Acrobot v1 | 42 | May 19, 2026 |
|---|
| Knowledge Recovery | TOFU 10% (400 samples) 1.0 (forget) | 42 | Feb 26, 2026 |
|---|
| Offline Reinforcement Learning | Walker2d medium-expert | 42 | May 29, 2026 |
|---|
| Reasoning | DROP | 42 | Jun 19, 2026 |
|---|
| Node classification | Social domains Blog2 to Blog1 | 42 | Feb 26, 2026 |
|---|
| Multimodal Robotic Control | Fetch-PickAndPlace Patch corruptions (test) | 42 | Feb 26, 2026 |
|---|
| Sequential Recommendation | Toys | 42 | Mar 17, 2026 |
|---|
| Sequential Recommendation | Beauty | 42 | Feb 26, 2026 |
|---|
| Recommendation | Epinions (test) | 42 | Jun 23, 2026 |
|---|
| Infrared Small Target Detection | IRSTD-1k (800:201) (test) | 42 | Feb 26, 2026 |
|---|
| Infrared Small Target Detection | NUDT-SIRST 663:664 (test) | 42 | Feb 26, 2026 |
|---|
| Infrared Small Target Detection | NUAA-SIRST (213:214) (test) | 42 | Feb 26, 2026 |
|---|
| AI-generated image detection | WildRF | 42 | Jun 16, 2026 |
|---|
| Visual Reasoning | HR-Bench 8K | 42 | May 13, 2026 |
|---|
| Multimodal Reasoning | HallusionBench | 42 | Mar 30, 2026 |
|---|