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 |
|---|---|---|---|---|---|
| Stereo Matching | ETH3D (non-occluded) | 52 | Jul 1, 2026 | ||
| 3D semantic occupancy prediction | Occ3D | 52 | May 7, 2026 | ||
| Image Classification | DTD | 52 | May 18, 2026 | ||
| Speculative Decoding | HumanEval | 52 | Jun 4, 2026 | ||
| Mathematical Reasoning | GK 2023 | 52 | Feb 26, 2026 | ||
| Retrieval-Augmented Generation |
| HotpotQA |
| 52 |
| Jun 4, 2026 |
| Speech Processing | SUPERB | 52 | Jun 30, 2026 |
|---|
| Text-to-Image Retrieval | ShareGPT4V | 52 | May 26, 2026 |
|---|
| Generalized Category Discovery | Herbarium19 (test) | 52 | May 12, 2026 |
|---|
| Anomaly Localization | VisA | 52 | Feb 26, 2026 |
|---|
| Commonsense Reasoning | CommonsenseQA (val) | 52 | Feb 26, 2026 |
|---|
| Referring Expression Segmentation | RefCOCOg UMD (val) | 52 | May 28, 2026 |
|---|
| Counterfactual Reasoning | Counterfactual Eval (dev) | 52 | Feb 26, 2026 |
|---|
| Instruction Following | MT-bench v1.0 (test) | 52 | Feb 26, 2026 |
|---|
| Multiple Choice Question Answering | MMLU | 52 | May 19, 2026 |
|---|
| Multivariate time series prediction | PEMS08 | 52 | Feb 26, 2026 |
|---|
| Multivariate time series prediction | PEMS07 | 52 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR100 UnSeen-Domain (US) | 52 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR100 UnLabel-Domain (UL) | 52 | Feb 26, 2026 |
|---|
| Image Classification | CIFAR100 Labeled-Domain (L) | 52 | Feb 26, 2026 |
|---|
| Deepfake Detection | CelebDF (CDF) v2 (test) | 52 | Apr 7, 2026 |
|---|
| Medical Image Segmentation | REFUGE | 52 | Jun 1, 2026 |
|---|
| Text-based Person Re-identification | RSTPReid (test) | 52 | Feb 27, 2026 |
|---|
| Gait Recognition | SUSTech1K (test) | 52 | Jun 1, 2026 |
|---|
| Code Output Prediction | CRUXEval-O | 52 | May 28, 2026 |
|---|