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 |
|---|---|---|---|---|---|
| 2D Medical Image Segmentation | BUSI | 41 | Jul 7, 2026 | ||
| Camera Pose Estimation | Sintel 50 frames | 41 | May 27, 2026 | ||
| Camouflaged Object Segmentation | NC4K | 41 | Mar 10, 2026 | ||
| Medical Reasoning | HealthBench Hard | 41 | Jun 9, 2026 | ||
| Traveling Salesman Problem | Uniform-TSP100 | 41 | May 26, 2026 | ||
| 3D Semantic Segmentation |
| S3DIS Area5 |
| 41 |
| Apr 7, 2026 |
| Multi-choice Question Answering | LongBench v2 | 41 | Mar 4, 2026 |
|---|
| Image Classification | MNIST DIRICHLET partition (test) | 41 | Jun 30, 2026 |
|---|
| Image Classification | CIFAR-100 Dirichlet-0.1 (test) | 41 | May 29, 2026 |
|---|
| Multiclass Classification | cmc | 41 | May 12, 2026 |
|---|
| Geometry problem solving | Geometry3K | 41 | Apr 21, 2026 |
|---|
| Video Person Re-Identification | MARS v1 (test) | 41 | Apr 10, 2026 |
|---|
| Remaining Useful Life prediction | NASA C-MAPSS FD001 (test) | 41 | Jun 1, 2026 |
|---|
| Prompt harmfulness detection | AegisSafety (test) | 41 | Jun 1, 2026 |
|---|
| Disease Diagnosis | Open-I | 41 | May 19, 2026 |
|---|
| Classification | AwA2 | 41 | Jun 26, 2026 |
|---|
| Graph Clustering | Wiki | 41 | Jun 23, 2026 |
|---|
| Precipitation Nowcasting | SEVIR | 41 | May 14, 2026 |
|---|
| Novel View Synthesis | Waymo | 41 | Jun 30, 2026 |
|---|
| Generated Image Detection | Wukong | 41 | Mar 4, 2026 |
|---|
| Robot Manipulation | LIBERO Spatial | 41 | May 20, 2026 |
|---|
| Natural Language Understanding | NLP Suite (BoolQ, RTE, HellaSwag, WinoG, ARC-E, ARC-C, OpenBookQA) zero-shot | 41 | Mar 26, 2026 |
|---|
| Knowledge-Intensive Reasoning | HotpotQA | 41 | Jun 11, 2026 |
|---|
| Classification | sonar | 41 | May 8, 2026 |
|---|
| Time Series Forecasting | ECL | 41 | Feb 26, 2026 |
|---|