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 |
|---|---|---|---|---|---|
| Clustering | Online News Popularity | 48 | Mar 19, 2026 | ||
| Clustering | MiniBooNE Particle Identification m = 130,064, n = 50 (full) | 48 | Mar 19, 2026 | ||
| Clustering | EEG Eye State | 48 | Mar 19, 2026 | ||
| Clustering | Gas Sensor Array Drift | 48 | Mar 19, 2026 | ||
| Clustering | D15112 | 48 | Mar 19, 2026 | ||
| Action Recognition |
| UCF101 |
| 48 |
| Mar 19, 2026 |
| Machine Unlearning | TOFU Forget01 (1% authors) | 48 | Mar 19, 2026 |
|---|
| Video Generation | VBench | 48 | Jun 16, 2026 |
|---|
| Node Classification | Flickr | 48 | Mar 18, 2026 |
|---|
| Node Classification | Cora-CA | 48 | May 14, 2026 |
|---|
| Fact Verification | FEVER (val) | 48 | Mar 17, 2026 |
|---|
| Video Question Answering | Video-MME | 48 | Mar 30, 2026 |
|---|
| Ocular Authentication | GazePro | 48 | Mar 17, 2026 |
|---|
| Cross-view Geo-localization (Drone to Satellite) | SUES-200 300m altitude | 48 | May 12, 2026 |
|---|
| Safety Evaluation | Harmful | 48 | Jun 11, 2026 |
|---|
| Private Inference Efficiency | In-queue inputs WAN2 Online phase | 48 | Mar 16, 2026 |
|---|
| Private Inference Efficiency | In-queue inputs LAN Online phase | 48 | Mar 16, 2026 |
|---|
| Mathematical Reasoning | AIME 25 | 48 | Jun 17, 2026 |
|---|
| Chemistry | USPTO | 48 | Mar 13, 2026 |
|---|
| Writing | ROCStories | 48 | Mar 13, 2026 |
|---|
| Label Projection | XQuAD | 48 | Mar 13, 2026 |
|---|
| Text-to-Image Generation | WISE | 48 | May 13, 2026 |
|---|
| Monocular Depth Estimation | TUM RGB-D (test) | 48 | May 13, 2026 |
|---|
| Image Classification | CIFAR100 (test) | 48 | Jun 9, 2026 |
|---|
| Channel prediction | Stochastic Velocity [20, 30) m/s | 48 | Mar 12, 2026 |
|---|