Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2712 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Planning | nuPlan Hard (test) | 14 | Mar 18, 2026 | ||
| Novel View Synthesis | DL3DV Large-viewpoint set (D) | 14 | Mar 17, 2026 | ||
| Novel View Synthesis | DL3DV Large-viewpoint set (S) | 14 | Mar 17, 2026 | ||
| 6-DoF rigid pose estimation | ETH Office & Trees | 14 | Mar 17, 2026 | ||
| 6-DoF rigid pose estimation | ETH Courtyard | 14 | Mar 17, 2026 | ||
| 6-DoF rigid pose estimation | ETH Arch & Facade | 14 | Mar 17, 2026 | ||
| Clustering | yale | 14 | May 15, 2026 | ||
| Machine Translation (En to Zh) | WMT 20 | 14 | Mar 17, 2026 | ||
| Machine Translation (Zh to En) | WMT 20 | 14 | Mar 17, 2026 | ||
| Machine Translation (En to Zh) | WMT 18 | 14 | Mar 17, 2026 | ||
| Machine Translation (Zh to En) | WMT 18 | 14 | Mar 17, 2026 | ||
| Binary intent classification | MALINT | 14 | Mar 17, 2026 | ||
| Multilabel Intent Classification | MALINT | 14 | Mar 17, 2026 | ||
| Pansharpening | WV2 (test) | 14 | Mar 17, 2026 | ||
| Pansharpening | WV3 (test) | 14 | Mar 17, 2026 | ||
| Pansharpening | GF2 (test) | 14 | Mar 17, 2026 | ||
| End-to-End Autonomous Driving | Bench2Drive v1.0 (Full-data) | 14 | Mar 17, 2026 | ||
| Humanoid Motion Tracking | OmniBench Walk (Slow) | 14 | Mar 17, 2026 | ||
| Loco-Manip | OmniBench Low 1.0 (test) | 14 | Mar 17, 2026 | ||
| Loco-Manip | OmniBench Medium 1.0 (test) | 14 | Mar 17, 2026 | ||
| Loco-Manip | OmniBench High 1.0 (test) | 14 | Mar 17, 2026 | ||
| Anomaly Detection | ADBench 38 real-world datasets (clean-context) | 14 | Mar 17, 2026 | ||
| Amodal 3D object generation | GSO | 14 | Mar 17, 2026 | ||
| Recurrence Core Coverage Prediction | PREDICT-GBM | 14 | Mar 17, 2026 | ||
| Recurrence Core Coverage Prediction | LUMIERE | 14 | Mar 17, 2026 |