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 |
|---|---|---|---|---|---|
| Reinforcement Learning | Walker | 38 | Feb 26, 2026 | ||
| Anomaly Detection | CiteSeer | 38 | May 27, 2026 | ||
| Node Classification | Computers | 38 | Feb 26, 2026 | ||
| Node Classification | Photo | 38 | Feb 26, 2026 | ||
| Maximum Clique | COLLAB | 38 | Mar 13, 2026 | ||
| Maximum Clique | RB200 MC instances (static) |
| 38 |
| Feb 26, 2026 |
| Maximum Clique | Twitter MC instances (static) | 38 | Feb 26, 2026 |
|---|
| Scaling Law Validation | Scaling Law (val) | 38 | Feb 26, 2026 |
|---|
| Long-context understanding | RULER | 38 | Jul 7, 2026 |
|---|
| Traveling Salesman Problem | TSP-500 | 38 | May 26, 2026 |
|---|
| Traveling Salesperson Problem | TSP-1k | 38 | Jun 4, 2026 |
|---|
| Retrieval | TREC-DL aggregate (test) | 38 | Feb 26, 2026 |
|---|
| Spatial Reasoning | RefSpatial | 38 | May 5, 2026 |
|---|
| Novel View Synthesis | SmallCity | 38 | Jul 7, 2026 |
|---|
| Raw-to-sRGB mapping | Zurich Raw-to-sRGB (test) | 38 | Feb 26, 2026 |
|---|
| Hyperspectral Unmixing | Jasper Ridge | 38 | May 7, 2026 |
|---|
| Respiratory Rate Estimation | COHFACE | 38 | Jun 23, 2026 |
|---|
| Fine-grained classification | Flower102 | 38 | Jun 8, 2026 |
|---|
| Multimodal Understanding | MME-RealWorld Lite | 38 | Jun 24, 2026 |
|---|
| Novel-view synthesis | RE10K Small | 38 | Mar 27, 2026 |
|---|
| Pose Estimation | Bonn | 38 | Mar 17, 2026 |
|---|
| Multi-Object Tracking | nuScenes (val) | 38 | Jul 7, 2026 |
|---|
| Remote Sensing Image Dehazing | SateHaze1k Thick | 38 | Jun 18, 2026 |
|---|
| Remote Sensing Image Dehazing | SateHaze1k Thin | 38 | Jun 18, 2026 |
|---|
| Multi-image Reasoning | Mantis | 38 | Apr 21, 2026 |
|---|