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 |
|---|---|---|---|---|---|
| Sound Classification | AudioSet (evaluation) | 39 | Feb 26, 2026 | ||
| Image Denoising | BSD200 | 39 | Feb 26, 2026 | ||
| Dialogue State Tracking | DSTC2 (test) | 39 | Feb 26, 2026 | ||
| Image Classification | OMNIGLOT (test) | 39 | Feb 26, 2026 | ||
| Salient Object Detection | SOD (test) |
| 39 |
| Feb 26, 2026 |
| Video Classification | UCF101 (averaged over three splits) | 39 | Feb 26, 2026 |
|---|
| Image Annotation | Flickr30k (test) | 39 | Feb 26, 2026 |
|---|
| Image Classification | Fashion-MNIST (val) | 39 | May 27, 2026 |
|---|
| Force Prediction | MD17 (test) | 39 | May 12, 2026 |
|---|
| HC vs. MCI classification | ADNI (five-fold cross-validation) | 39 | Jun 18, 2026 |
|---|
| Conformer Generation | GEOM-QM9 δ = 0.5Å (test) | 39 | Apr 24, 2026 |
|---|
| Initial Structure to Relaxed Energy | OC20 IS2RE (val) | 39 | Mar 25, 2026 |
|---|
| Emotion Recognition | CRM-D | 39 | Feb 26, 2026 |
|---|
| Topic Modeling | 20 Newsgroups (test) | 39 | Feb 26, 2026 |
|---|
| Person Re-identification | MSMT17 MS | 39 | Mar 17, 2026 |
|---|
| Multimodal Multilingual Reasoning | MMMB | 39 | Apr 15, 2026 |
|---|
| Fine-grained Classification | SUN397 | 39 | Mar 18, 2026 |
|---|
| MRI Super-resolution | IXI (test) | 39 | Jun 26, 2026 |
|---|
| Medical Image Classification | HAM10000 | 39 | Feb 26, 2026 |
|---|
| Surgical Phase Recognition | Autolaparo | 39 | Apr 21, 2026 |
|---|
| Anomaly Segmentation | BrainMRI | 39 | Feb 26, 2026 |
|---|
| Audio Event Tagging | AudioSet (AS-20K) | 39 | Jun 5, 2026 |
|---|
| Novel View Synthesis | Tanks&Temples | 39 | Feb 26, 2026 |
|---|
| Mean Euclidean estimation | Simulated stream data n = 3 × 10^8 | 38 | Jul 7, 2026 |
|---|
| Visual Question Answering | SimpleVQA | 38 | Jul 7, 2026 |
|---|