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 |
|---|---|---|---|---|---|
| Regression | Vascular flow | 40 | Mar 24, 2026 | ||
| Token Attribution Faithfulness | Known 1000 | 40 | Mar 23, 2026 | ||
| Component-level attribution | Known 1000 | 40 | Mar 23, 2026 | ||
| Simulation Throughput | NASim | 40 | Mar 23, 2026 | ||
| Perceptual Quality Assessment | TIEdit 1.0 (test) | 40 | Mar 23, 2026 | ||
| Out-of-Distribution Detection | Core50 ID |
| 40 |
| Mar 20, 2026 |
| Out-of-Distribution Detection | CLEAR10 ID | 40 | Mar 20, 2026 |
|---|
| Out-of-Distribution Detection | CLEAR100 ID | 40 | Mar 20, 2026 |
|---|
| Mathematical Reasoning | BrUMO '25 | 40 | Mar 20, 2026 |
|---|
| Mathematical Reasoning | HMMT '25 | 40 | Mar 20, 2026 |
|---|
| Mathematical Reasoning | AIME 24 | 40 | Mar 20, 2026 |
|---|
| Mathematical Reasoning | AIME '25 | 40 | Mar 20, 2026 |
|---|
| Instance Segmentation | SSDD | 40 | Jun 25, 2026 |
|---|
| Point cloud classification attack | ScanObjectNN (test) | 40 | Mar 20, 2026 |
|---|
| Code Generation | BigCode | 40 | Apr 30, 2026 |
|---|
| Action Recognition | HMDB51 | 40 | May 14, 2026 |
|---|
| Desnowing | CSD | 40 | Jun 23, 2026 |
|---|
| Class Unlearning | CIFAR-10 | 40 | Mar 18, 2026 |
|---|
| Image-text understanding | MMBench | 40 | Jun 4, 2026 |
|---|
| Referring Video Object Segmentation | YoURVOS (test) | 40 | Mar 17, 2026 |
|---|
| Attribution Localization | ImageNet-1K ILSVRC2012 (val) | 40 | Mar 17, 2026 |
|---|
| Attribution Faithfulness | ImageNet-1K ILSVRC2012 (val) | 40 | Mar 17, 2026 |
|---|
| Unconditional Image Generation | CIFAR-10 32x32 (EDM) (50k samples) | 40 | Mar 17, 2026 |
|---|
| Image Generation | FFHQ 64x64 (EDM) 50k samples | 40 | Mar 17, 2026 |
|---|
| Image Classification | ImageNet | 40 | Apr 6, 2026 |
|---|