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 |
|---|---|---|---|---|---|
| Video Understanding | Video-MME Long | 32 | Feb 26, 2026 | ||
| Classification | PneumoniaMNIST MedMNIST v2 (test) | 32 | Feb 26, 2026 | ||
| Few-shot Semantic Segmentation | ISIC | 32 | Feb 26, 2026 | ||
| General Visual Question Answering | RealWorldQA | 32 | Jul 7, 2026 | ||
| Image Classification | ImageNet-1k (val) |
| 32 |
| Feb 26, 2026 |
| Multimodal Spatial Intelligence | EASI (In-Domain) | 32 | Feb 26, 2026 |
|---|
| Computer-Aided Diagnosis (CAD) | VinDr | 32 | Feb 26, 2026 |
|---|
| CT Reconstruction | Jaw | 32 | Jun 23, 2026 |
|---|
| CT Reconstruction | Head | 32 | Jun 23, 2026 |
|---|
| CT Reconstruction | Foot | 32 | Jun 23, 2026 |
|---|
| CT Reconstruction | Box | 32 | Jun 23, 2026 |
|---|
| CT Reconstruction | AAPM L096 | 32 | Jun 23, 2026 |
|---|
| CT Reconstruction | AAPM L067 | 32 | Jun 23, 2026 |
|---|
| Nearest POI Spatial Grounding | PA | 32 | Feb 26, 2026 |
|---|
| Nearest POI Spatial Grounding | BJ | 32 | Feb 26, 2026 |
|---|
| Nearest POI Spatial Grounding | SG | 32 | Feb 26, 2026 |
|---|
| Geolocation Ranking | New York | 32 | Feb 26, 2026 |
|---|
| Multi-image Spatial Reasoning | SPAR-Bench-MV + MindCube-Tiny + MMSI-Bench (test) | 32 | Jul 2, 2026 |
|---|
| Video Anomaly Detection | UCF-Crime (frame-level) | 32 | Feb 26, 2026 |
|---|
| Decision Fusion | Distributed Sensor Network (n=20, m=10, ε=0.1) | 32 | Feb 26, 2026 |
|---|
| System call detection | IoTOwl 0.005 contamination level | 32 | Feb 26, 2026 |
|---|
| Secure Inference (AlexNet) | CIFAR-10 (test) | 32 | Feb 26, 2026 |
|---|
| Secure Inference (LeNet) | MNIST (test) | 32 | Feb 26, 2026 |
|---|
| Threat Risk Assessment | O-RAN Alliance Generic Threat Classes Manual vs Automated Analysis 1.0 | 32 | Feb 26, 2026 |
|---|
| Training Data Reconstruction | RT | 32 | Feb 26, 2026 |
|---|