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 |
|---|---|---|---|---|---|
| Image Denoising | Salinas Valley multispectral image (AVIRIS) | 45 | Jun 5, 2026 | ||
| Image Denoising | IRIS Lab database Subject4 | 45 | Jun 5, 2026 | ||
| Image Denoising | IRIS Lab database Subject3 | 45 | Jun 5, 2026 | ||
| AI-generated video detection | GenBuster | 45 | Jun 4, 2026 | ||
| Convex Regression | Power Modeling Data Section 5.3 (test) |
| 45 |
| Jun 4, 2026 |
| Convex Regression | Synthetic Prediction Data Section 4.1 (test) | 45 | Jun 4, 2026 |
|---|
| Inference Cost Attack | Natural Questions (NQ) | 45 | Jun 4, 2026 |
|---|
| Regression | RN | 45 | Jun 2, 2026 |
|---|
| Network Pruning | Glycolytic Dataset | 45 | Jun 2, 2026 |
|---|
| Knowledge Conflict Resolution | PAVE (test) | 45 | Jun 2, 2026 |
|---|
| Video-LLM performance calibration | Eval-OOD (EgoSchema & LongVideoBench) | 45 | Jun 2, 2026 |
|---|
| Mathematical Reasoning | AIME24 | 45 | Jun 9, 2026 |
|---|
| LLM Alignment | OpenAssistant | 45 | Jun 1, 2026 |
|---|
| Watermarking | Natural Questions (NQ) (test) | 45 | May 29, 2026 |
|---|
| Theory-of-Mind reasoning | MuMA-ToM | 45 | Jun 9, 2026 |
|---|
| Image Classification | CIFAR-10 | 45 | May 26, 2026 |
|---|
| Image Classification | CIFAR-100 LT IF=0.01 (test) | 45 | May 25, 2026 |
|---|
| Image Classification | Caltech-101 naturally imbalanced (test) | 45 | May 25, 2026 |
|---|
| Image Classification | CIFAR-100-LT balanced imbalance factor 0.1 (test) | 45 | May 25, 2026 |
|---|
| Image Classification | Tiny-ImageNet-C 30% corrupted (test) | 45 | May 25, 2026 |
|---|
| Image Classification | CIFAR-100-C 30% corrupted (test) | 45 | May 25, 2026 |
|---|
| Coefficient Learning | Feynman Symbolic Regression 5x extrapolation | 45 | May 22, 2026 |
|---|
| Coefficient Learning | Feynman Symbolic Regression in-distribution | 45 | May 22, 2026 |
|---|
| Question Answering | HotpotQA PoisonedRAG (test) | 45 | May 20, 2026 |
|---|
| Question Answering | HotpotQA Clean (test) | 45 | May 20, 2026 |
|---|