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 |
|---|---|---|---|---|---|
| Machine Unlearning | Tiny-ImageNet 20 classes | 48 | Apr 10, 2026 | ||
| Machine Unlearning | CIFAR-100 1 class | 48 | Apr 10, 2026 | ||
| Machine Unlearning | CIFAR-10 3 classes | 48 | Apr 10, 2026 | ||
| Machine Unlearning | CIFAR-10 1 class | 48 | Apr 10, 2026 | ||
| Machine Unlearning | Tiny-ImageNet 1 class (forget) | 48 | May 12, 2026 |
| Synthetic Time Series Generation | MetroPT3 | 48 | Apr 10, 2026 |
|---|
| Synthetic Time Series Generation | Sine | 48 | Apr 10, 2026 |
|---|
| Synthetic Time Series Generation | ETT | 48 | Apr 10, 2026 |
|---|
| Synthetic Time Series Generation | ECG | 48 | Apr 10, 2026 |
|---|
| Synthetic Time Series Generation | Electric Motor | 48 | Apr 10, 2026 |
|---|
| Zero-shot Question Answering and Commonsense Reasoning | Zero-shot Downstream Tasks (ARC, HellaSwag, WinoGrande, BoolQ, PiQA) | 48 | May 19, 2026 |
|---|
| Fruit Re-identification | Strawberry dataset | 48 | Apr 10, 2026 |
|---|
| Robotic Manipulation | RoboTwin 1.0 | 48 | Apr 8, 2026 |
|---|
| Multi-hop Reasoning | MuSiQue | 48 | Jun 2, 2026 |
|---|
| Deepfake Detection | CDF v2 | 48 | May 12, 2026 |
|---|
| Chart Question Answering | ChartQA | 48 | Jun 5, 2026 |
|---|
| DAG structure recovery | non-linear-1 5000 samples | 48 | Apr 7, 2026 |
|---|
| Optimal Circuit Synthesis | Final Cryptographic Circuits | 48 | Apr 7, 2026 |
|---|
| View-Conditioned Spatial Reasoning | ViewBench Shape | 48 | Apr 6, 2026 |
|---|
| View-Conditioned Spatial Reasoning | ViewBench Text | 48 | Apr 6, 2026 |
|---|
| Membership Inference Attack | CIFAR-10 | 48 | Apr 15, 2026 |
|---|
| Parametric estimation of confining and interaction potentials | Boundary (test) | 48 | Apr 6, 2026 |
|---|
| Commonsense Reasoning | Commonsense Reasoning Suite | 48 | Apr 3, 2026 |
|---|
| Semantic Segmentation | DLRSD | 48 | Apr 20, 2026 |
|---|
| Ultrasound Image Classification | GIST514-DB | 48 | Apr 3, 2026 |
|---|