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 |
|---|---|---|---|---|---|
| Code Input Prediction | CRUXEval-I | 52 | May 28, 2026 | ||
| Visual Grounding | RefCOCOg | 52 | Jul 1, 2026 | ||
| Image Super-Resolution | Set14 classic (test) | 52 | Feb 26, 2026 | ||
| Mathematical Reasoning | MathQA (test) | 52 | May 12, 2026 | ||
| Code Generation | HumanEval Multilingual (test) | 52 | Feb 26, 2026 | ||
| Point Cloud Classification |
| ScanObjectNN OBJ-ONLY |
| 52 |
| Mar 27, 2026 |
| Univariate Time Series Forecasting | traffic | 52 | Jul 8, 2026 |
|---|
| Spatio-temporal video grounding | HCSTVG v2 (val) | 52 | Jun 30, 2026 |
|---|
| Hyperparameter Optimization | JAHS-C10 Bench (val) | 52 | Feb 26, 2026 |
|---|
| Compositional Zero-Shot Learning | UT-Zappos open world | 52 | Mar 18, 2026 |
|---|
| Unsupervised Domain Adaptation | UCF-HMDB | 52 | May 20, 2026 |
|---|
| Image Classification | CIFAR-20 | 52 | May 18, 2026 |
|---|
| Age Regression | UKB | 52 | Jun 26, 2026 |
|---|
| Offline Reinforcement Learning | D4RL Medium-Replay Walker2d | 52 | May 11, 2026 |
|---|
| Classification | Covertype | 52 | Jul 7, 2026 |
|---|
| Point Tracking | DAVIS TAP-Vid | 52 | Mar 27, 2026 |
|---|
| Question Answering | TriviaQA Wiki (val) | 52 | Mar 17, 2026 |
|---|
| Multi-label Graph Classification | Peptides func | 52 | May 13, 2026 |
|---|
| Full-Reference Image Quality Assessment | CSIQ-IQA | 52 | Mar 17, 2026 |
|---|
| Factual Consistency Evaluation | SummaC | 52 | Feb 26, 2026 |
|---|
| Toxicity Detection | Implicit Hate | 52 | Jun 2, 2026 |
|---|
| Audio-Visual Event Localization | AVE | 52 | May 13, 2026 |
|---|
| Image-to-Text Retrieval | MS-COCO 5K | 52 | Jul 3, 2026 |
|---|
| Image Classification | ImageNet to 10 Target Datasets (Caltech101, OxfordPets, StanfordCars, Flowers102, Food101, FGVCAircraft, SUN397, DTD, EuroSAT, UCF101) (test) | 52 | May 7, 2026 |
|---|
| Blind Face Restoration | LFW (test) | 52 | Apr 1, 2026 |
|---|