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 |
|---|---|---|---|---|---|
| Temporal Knowledge Graph Reasoning | ICEWS05-15 (test) | 41 | Feb 26, 2026 | ||
| Code generation | CodeAlpaca | 41 | Feb 26, 2026 | ||
| Ripple Effect Prediction | CAPM residuals various LLMs | 41 | Feb 26, 2026 | ||
| Tracking | TUM RGB-D 44 (various sequences) | 41 | Mar 20, 2026 | ||
| Brain Tumor Segmentation | BraTS PED 2023 (test) | 41 | Jun 15, 2026 | ||
| VideoPhy |
| 41 |
| Jul 7, 2026 |
| Aerial Image Classification | AIDER v2 (test) | 41 | Feb 27, 2026 |
|---|
| Sequential Recommendation | MovieLens | 41 | Feb 26, 2026 |
|---|
| Gaussian Deblurring | ImageNet | 41 | May 14, 2026 |
|---|
| Audio Classification | SHD (test) | 41 | Apr 20, 2026 |
|---|
| Multi-hop Reasoning | MuSiQue | 41 | Feb 26, 2026 |
|---|
| Commonsense Reasoning | BoolQ | 41 | May 13, 2026 |
|---|
| Web navigation | Mind2Web | 41 | Jun 24, 2026 |
|---|
| Traffic Forecasting | GBA | 41 | Jun 30, 2026 |
|---|
| RGB-Thermal tracking | RGBT234 (test) | 41 | Feb 26, 2026 |
|---|
| Figure-ground motion segmentation | Random dot stimuli zero-shot | 41 | Feb 26, 2026 |
|---|
| Figure-ground motion segmentation | i.i.d. Original videos (test) | 41 | Feb 26, 2026 |
|---|
| Building Extraction | WHUAerial | 41 | Apr 20, 2026 |
|---|
| Classification | fourier | 41 | Feb 26, 2026 |
|---|
| 3D Object Detection | nuScenes | 41 | Jul 8, 2026 |
|---|
| GUI Navigation and Action | OS World (test) | 41 | May 11, 2026 |
|---|
| Privacy Measurement | CIFAR-10 | 41 | Feb 26, 2026 |
|---|
| Natural Language Understanding | GLUE | 41 | Feb 26, 2026 |
|---|
| Causal Discovery | Sachs real-world data protein signaling network | 41 | Jun 5, 2026 |
|---|
| Frame-level Deepfake Detection | DFDC-P | 41 | Apr 21, 2026 |
|---|