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 Captioning Evaluation | Composite | 161 | Jun 30, 2026 | ||
| Video Question Answering | TGIF-QA | 161 | Jun 23, 2026 | ||
| Traffic Forecasting | PEMS-BAY | 161 | Jun 16, 2026 | ||
| 3D Reconstruction | 7-Scenes | 161 | Jul 7, 2026 | ||
| Low-light image enhancement | LOL (test) |
| 161 |
| May 21, 2026 |
| Object Detection | Foggy Cityscapes (test) | 161 | Jul 1, 2026 |
|---|
| Summarization | arXiv (test) | 161 | Feb 26, 2026 |
|---|
| Scene Text Recognition | IIIT5k | 161 | Mar 20, 2026 |
|---|
| Offline Reinforcement Learning | D4RL hopper-medium-expert | 161 | May 11, 2026 |
|---|
| Low-light Image Enhancement | LOL syn v2 | 161 | Jun 18, 2026 |
|---|
| Time Series Forecasting | Electricity | 161 | Jun 19, 2026 |
|---|
| Image Classification | OfficeHome | 161 | Jun 15, 2026 |
|---|
| Adversarial Detection | CIFAR-10 (test) | 160 | Jun 29, 2026 |
|---|
| Statistical Adversarial Detection | ImageNet-1K (test) | 160 | Jun 29, 2026 |
|---|
| Credit Card Fraud Detection | BankSim | 160 | May 13, 2026 |
|---|
| Image Classification | 14 Vision Tasks | 160 | Jun 23, 2026 |
|---|
| Vertex normal prediction | Thingi10K | 160 | Feb 26, 2026 |
|---|
| Concept Attribution | CLEVR (test) | 160 | Feb 26, 2026 |
|---|
| Math Reasoning | MATH | 160 | May 26, 2026 |
|---|
| Mathematical Reasoning | AIME24 | 160 | Mar 10, 2026 |
|---|
| Graph Classification | HIV | 160 | Jun 17, 2026 |
|---|
| Multivariate Time Series Forecasting | ETTh1 (test) | 160 | May 26, 2026 |
|---|
| Speaker Verification | VoxCeleb1 (Vox1-O) | 160 | Jul 9, 2026 |
|---|
| Temporal Video Understanding | TempCompass | 160 | Jul 9, 2026 |
|---|
| Sentiment Analysis | MR | 160 | Mar 5, 2026 |
|---|