Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1662 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Question Answering | ScanQA (test) | 20 | Feb 26, 2026 | ||
| Visual Reasoning | NLVR2 v2 (dev) | 20 | Feb 26, 2026 | ||
| Human Judgment Correlation | VATEX EVAL (val) | 20 | Feb 26, 2026 | ||
| Low-light Image Enhancement | RLE (test) | 20 | May 22, 2026 | ||
| Event Argument Extraction | ACE05-E (test) | 20 | Feb 26, 2026 | ||
| 6DoF Face Pose Estimation | ARKitFace (test) | 20 | Feb 26, 2026 | ||
| Novel View Synthesis | ShapeNet cars category | 20 | Feb 26, 2026 | ||
| Relative Pose Estimation | Scannet | 20 | Feb 26, 2026 | ||
| 5-way few-shot text classification | 20 Newsgroups (test) | 20 | Feb 26, 2026 | ||
| 5-way few-shot text classification | Reuters (test) | 20 | Feb 26, 2026 | ||
| 5-way few-shot text classification | Amazon (test) | 20 | Feb 26, 2026 | ||
| 5-way few-shot text classification | HuffPost (test) | 20 | Feb 26, 2026 | ||
| Graph Anomaly Detection | MMP | 20 | Mar 4, 2026 | ||
| Anomaly Detection | Backdoor | 20 | Mar 17, 2026 | ||
| Speech Translation | MuST-C (tst-COMMON) | 20 | Feb 26, 2026 | ||
| English-German document-level translation | Europarl English-German (test) | 20 | Feb 26, 2026 | ||
| English-German document-level translation | News English-German (test) | 20 | Feb 26, 2026 | ||
| English-German document-level translation | TED English-German (test) | 20 | Feb 26, 2026 | ||
| Adversarial Transfer Attack | Adversarially trained CNNs Target Models (test) | 20 | Feb 26, 2026 | ||
| Adversarial Transfer Attack | CNNs Target Models (test) | 20 | Feb 26, 2026 | ||
| Adversarial Transfer Attack | ViTs Target Models (test) | 20 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 | 20 | Feb 26, 2026 | ||
| Movie Scene Segmentation | MovieNet 1.0 (test) | 20 | Feb 26, 2026 | ||
| Nuclei Segmentation | GLySAC | 20 | Mar 10, 2026 | ||
| Lip-Reading | LRS3 (test) | 20 | Jun 2, 2026 |