Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1937 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Machine Translation | Fr-En document-level translation | 18 | Feb 26, 2026 | ||
| Machine Translation | Translation Ru-En document-level | 18 | Feb 26, 2026 | ||
| Machine Translation | Es-En document-level translation | 18 | Feb 26, 2026 | ||
| Machine Translation | 10-language machine translation evaluation suite (test) | 18 | Feb 26, 2026 | ||
| Machine Translation | Document-level Translation Suite | 18 | Feb 26, 2026 | ||
| Time Series Forecasting | ETTm2 zero-shot transfer from ETTh2 | 18 | Apr 15, 2026 | ||
| Image Reconstruction | Image Fitting (test) | 18 | Feb 26, 2026 | ||
| Video Representation Generalization | SEVERE benchmark | 18 | Mar 31, 2026 | ||
| 3D Lane Detection | OpenLane 1.2 (test) | 18 | Feb 26, 2026 | ||
| Domain Adaptive Object Detection | Foggy Cityscapes (val) | 18 | Feb 26, 2026 | ||
| Image Generation | Stable Diffusion (SD) 1.4 | 18 | Mar 17, 2026 | ||
| Video Generation | DAVIS (val) | 18 | Feb 26, 2026 | ||
| Video Question Answering | VideoMME (long split) | 18 | Feb 26, 2026 | ||
| Novel View Synthesis | Synthetic Data | 18 | Jun 16, 2026 | ||
| 3D Point Cloud Classification | ScanObjectNN PB_50_RS 51 | 18 | Feb 26, 2026 | ||
| Palmprint Verification | CASIA, PolyU, TongJi, MPD, XJTU-UP (test) | 18 | Feb 26, 2026 | ||
| Rendering | Replica and ScanNet++ | 18 | Feb 26, 2026 | ||
| Scene Reconstruction | Replica and ScanNet++ | 18 | Feb 26, 2026 | ||
| Outdoor Semantic Segmentation | Waymo (val) | 18 | Apr 14, 2026 | ||
| Image Synthesis | CIFAR-100 (train test) | 18 | Feb 26, 2026 | ||
| Image Synthesis | CIFAR-10 (train test) | 18 | Feb 26, 2026 | ||
| Novel View Synthesis | HyperNeRF (test) | 18 | Feb 26, 2026 | ||
| Open-ended Video Question Answering | ActNet-QA | 18 | Mar 18, 2026 | ||
| Depth Completion | Outdoor sequence KITTI → Waymo → VKITTI | 18 | Feb 27, 2026 | ||
| Semantic Segmentation | Replica (novel views) | 18 | Jun 9, 2026 |