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 |
|---|---|---|---|---|---|
| QA Answer Selection | TREC Answer Selection (test) | 33 | Feb 26, 2026 | ||
| Object Detection | PASCAL VOC 2012 (val) | 33 | Mar 16, 2026 | ||
| Classification | N-MNIST | 33 | Jun 24, 2026 | ||
| Property Optimization | ZINC250K (test) | 33 | Feb 26, 2026 | ||
| Function Approximation | F3(ξ) | 33 | Feb 26, 2026 | ||
| Regression |
| UCI YACHT (test) |
| 33 |
| Feb 26, 2026 |
| Traveling Salesperson Problem | TSP N=100 (test) | 33 | Mar 27, 2026 |
|---|
| Point cloud registration | ModelNet 40 (test) | 33 | Apr 8, 2026 |
|---|
| Classification | TEXTURE | 33 | Jul 7, 2026 |
|---|
| Constitutive modeling | hyperelasticity (test) | 33 | Feb 26, 2026 |
|---|
| Retrosynthesis | USPTO-50K | 33 | Feb 26, 2026 |
|---|
| Speaker Identification | VC1 | 33 | Feb 26, 2026 |
|---|
| Machine Translation | 49 low-performing Closely-Related Languages (CRLs) (test) | 33 | Feb 26, 2026 |
|---|
| Novel View Synthesis | iPhone dataset | 33 | May 13, 2026 |
|---|
| Knowledge Distillation | CIFAR-10 (test) | 33 | Jul 8, 2026 |
|---|
| Image Classification | ImageNet 1.0 (10% labeled) | 33 | Feb 26, 2026 |
|---|
| Multilingual Mathematical Reasoning | MSVAMP | 33 | Feb 26, 2026 |
|---|
| Topic Modeling | 20NG | 33 | Apr 1, 2026 |
|---|
| Jailbreak Defense Performance | Jailbreak Attack Dataset | 33 | Feb 26, 2026 |
|---|
| Multimodal Understanding | RealWorldQA | 33 | Apr 24, 2026 |
|---|
| Recommendation | Amazon-Book IID (test) | 33 | Feb 26, 2026 |
|---|
| Image Editing | GEdit-Bench-CN (Full set) | 33 | Jun 11, 2026 |
|---|
| Image Classification | STL-10 Clean (test) | 33 | Feb 26, 2026 |
|---|
| Reasoning | Reasoning Evaluation Suite Math, Symbolic, and Commonsense (test) | 33 | Feb 26, 2026 |
|---|
| Harmful Meme Detection | MAMI | 33 | May 6, 2026 |
|---|