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 |
|---|---|---|---|---|---|
| Multimodal Question Answering | WebQA Average | 32 | Jun 11, 2026 | ||
| Membership Inference | Enron (canary-audit) | 32 | Jun 11, 2026 | ||
| Crack Segmentation | Concrete3k Facade390 Road420 Zero-shot | 32 | Jun 11, 2026 | ||
| Crack Segmentation | OmniCrack (test) | 32 | Jun 11, 2026 | ||
| Image Reconstruction | CelebA-HQ | 32 | Jun 11, 2026 | ||
| Anomaly Detection |
|---|
| MVTec FS |
| 32 |
| Jun 9, 2026 |
| robot manipulation | LIBERO | 32 | Jun 19, 2026 |
|---|
| Visual Question Answering | RealWorldQA xAI 2024 (test) | 32 | Jun 9, 2026 |
|---|
| Visual Question Answering | MMMB (test) | 32 | Jun 9, 2026 |
|---|
| Image Classification | CIFAR-10 | 32 | Jun 9, 2026 |
|---|
| Paraphrase Identification | PPDB | 32 | Jun 5, 2026 |
|---|
| Natural Language Inference | MNLI | 32 | Jun 5, 2026 |
|---|
| Logical Reasoning | AutoLogi | 32 | Jun 30, 2026 |
|---|
| Sorting | Sorted arrays | 32 | Jun 5, 2026 |
|---|
| Hyperspectral Image Completion | Scene8 | 32 | Jun 5, 2026 |
|---|
| Hyperspectral Image Completion | Scene7 | 32 | Jun 5, 2026 |
|---|
| Hyperspectral Image Completion | Scene6 | 32 | Jun 5, 2026 |
|---|
| Hyperspectral Image Completion | Scene5 | 32 | Jun 5, 2026 |
|---|
| Hyperspectral Image Completion | Scene4 | 32 | Jun 5, 2026 |
|---|
| Hyperspectral Image Completion | Scene3 | 32 | Jun 5, 2026 |
|---|
| Hyperspectral Image Completion | Scene2 | 32 | Jun 5, 2026 |
|---|
| Hyperspectral Image Completion | Scene1 | 32 | Jun 5, 2026 |
|---|
| Robot position estimation | M2 simulation map | 32 | Jun 5, 2026 |
|---|
| Robot position estimation | M1 simulation map | 32 | Jun 5, 2026 |
|---|
| Image Classification | SynDigits-LT gamma=10 | 32 | Jun 4, 2026 |
|---|