Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 428 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Out-of-Distribution Detection | CIFAR100 ID Dnear OOD | 47 | Feb 26, 2026 | ||
| Social Interaction | SOTOPIA all social scenarios | 47 | Apr 23, 2026 | ||
| Mathematical Reasoning | SAT-Math | 47 | Mar 20, 2026 | ||
| Marine Animal Segmentation | RMAS (test) | 47 | Feb 26, 2026 | ||
| Satellite Image Classification | EuroSAT | 47 | May 8, 2026 | ||
| Low-light Image Enhancement | LOL Real_captured v2 | 47 | Feb 26, 2026 | ||
| Novel View Synthesis | Neural 3D Video Dataset Standard (All six scenes) | 47 | May 12, 2026 | ||
| Explicit Content Removal | I2P | 47 | Jun 2, 2026 | ||
| Image Classification | SST2 Rendered | 47 | Mar 4, 2026 | ||
| Multimodal Reasoning | MMBench (dev) | 47 | Feb 26, 2026 | ||
| Temporal Action Localization | ActivityNet v1.3 (test) | 47 | Feb 26, 2026 | ||
| Continual Learning | ImageNet tiny | 47 | Jun 12, 2026 | ||
| Highlight Detection | TVSum | 47 | Jun 2, 2026 | ||
| CTR Prediction | Industrial | 47 | Jun 9, 2026 | ||
| Polyp Segmentation | ColonDB (test) | 47 | Feb 26, 2026 | ||
| No-Reference Video Quality Assessment | YouTube-UGC | 47 | Feb 26, 2026 | ||
| Single Object Tracking | COESOT (test) | 47 | Feb 26, 2026 | ||
| Visual Question Answering | DocVQA (val) | 47 | Mar 30, 2026 | ||
| Compositional Reasoning | VL-Checklist | 47 | Jun 12, 2026 | ||
| Long-tailed Image Classification | CIFAR-100 LT (Imbalance ratio 100) | 47 | Feb 26, 2026 | ||
| Facial Action Unit Detection | DISFA | 47 | Feb 26, 2026 | ||
| Scene flow estimation | FT3Ds (test) | 47 | Feb 26, 2026 | ||
| Video Object Segmentation | YouTube-VOS 2018 | 47 | Feb 26, 2026 | ||
| Image Classification | Food101 Base-to-new generalization | 47 | Feb 26, 2026 | ||
| Multimodal Emotion Recognition | CMU-MOSI (test) | 47 | Mar 17, 2026 |