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 |
|---|---|---|---|---|---|
| Security Protocol Verification | Tamarin Security Protocols Suite | 127 | May 25, 2026 | ||
| Model Fingerprinting Robustness Evaluation | Pruning Robustness Evaluation Dataset | 127 | Apr 8, 2026 | ||
| Heart Rate Estimation | UBFC-rPPG | 127 | Jul 1, 2026 | ||
| Math Reasoning | MATH500 | 127 | Jun 25, 2026 | ||
| Multimodal Understanding | LLaVA Evaluation Suite 1.5 |
| 127 |
| Jul 1, 2026 |
| Image Classification | CIFAR-10-LT | 127 | May 26, 2026 |
|---|
| Image Classification | UCF-101 (test) | 127 | Jun 30, 2026 |
|---|
| 3D Dense Captioning | Scan2Cap | 127 | Jul 8, 2026 |
|---|
| Image-to-text Retrieval | MS-COCO (test) | 127 | Apr 28, 2026 |
|---|
| 3D Object Detection | ScanNet | 127 | Mar 10, 2026 |
|---|
| Knowledge Graph Completion | FB15k-237 | 127 | Jun 15, 2026 |
|---|
| Action Segmentation | Breakfast | 127 | Jun 1, 2026 |
|---|
| Pixel-level Anomaly Detection | MVTec | 127 | Feb 26, 2026 |
|---|
| Image Generation | ImageNet-64 | 127 | Jul 3, 2026 |
|---|
| Video Denoising | Set8 (test) | 127 | Feb 26, 2026 |
|---|
| Link Prediction | YAGO3-10 (test) | 127 | Feb 26, 2026 |
|---|
| Image Quality Assessment | LIVE | 127 | May 19, 2026 |
|---|
| Commonsense Question Answering | CSQA (test) | 127 | Feb 26, 2026 |
|---|
| Safety Evaluation | Harmbench | 127 | May 29, 2026 |
|---|
| Anomaly Localization | VisA | 127 | Apr 23, 2026 |
|---|
| Domain Generalization | DomainBed | 127 | Feb 26, 2026 |
|---|
| Structural Certification Error Analysis | Maze Environment 100 x 100 | 126 | Jun 24, 2026 |
|---|
| Profanity suppression | RealToxicityPrompts | 126 | May 12, 2026 |
|---|
| Multi-turn dialogue | MT-Bench | 126 | May 19, 2026 |
|---|
| Fault Diagnosis | Tennessee Eastman process (TEP) dataset (test) | 126 | Apr 23, 2026 |
|---|