Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 707 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Online HD Mapping | nuScenes (val) | 34 | May 5, 2026 | ||
| Visual Rating (Image Aesthetic Assessment) | ArtiMuse-10K | 34 | Mar 23, 2026 | ||
| Object Hallucination Evaluation | POPE GQA (Adversarial) | 34 | May 15, 2026 | ||
| Blind Image Quality Assessment | AGIQA (test) | 34 | Feb 26, 2026 | ||
| Blind Image Quality Assessment | LIVE-W (test) | 34 | Feb 26, 2026 | ||
| Point Cloud Registration | KAIST Aeva → Avia | 34 | Feb 26, 2026 | ||
| Super-Resolution | DroneVehicle x8 2.0 (test) | 34 | Feb 26, 2026 | ||
| Super-Resolution | DroneVehicle x4 2.0 (test) | 34 | Feb 26, 2026 | ||
| Multimodal mathematical reasoning | MathVista (test) | 34 | Mar 31, 2026 | ||
| Voice recognition | Librispeech | 34 | Mar 6, 2026 | ||
| Hallucination Detection | POPE official (val) | 34 | Mar 9, 2026 | ||
| Vision-centric Evaluation | CV-Bench | 34 | Jun 18, 2026 | ||
| Semantic Segmentation | CSDD original (test) | 34 | Feb 26, 2026 | ||
| Semantic Segmentation | CSDD (test) | 34 | Feb 26, 2026 | ||
| Video-level Deepfake Detection | DFDC | 34 | Mar 26, 2026 | ||
| Multimodal Movie Genre Classification | MM-IMDB | 34 | Jun 30, 2026 | ||
| Video Reasoning | Video-Holmes | 34 | Mar 31, 2026 | ||
| Surface Reconstruction | DTU | 34 | Feb 26, 2026 | ||
| Synthetic Video Detection | GenVideo (test) | 34 | Apr 7, 2026 | ||
| Image Desnowing | Snow100K | 34 | Jun 23, 2026 | ||
| Real-World Image Super-Resolution | RealLR200 | 34 | Mar 26, 2026 | ||
| Visual Localization | 7Scenes RedKitchen | 34 | Apr 27, 2026 | ||
| Visual Localization | 7Scenes Pumpkin | 34 | Apr 27, 2026 | ||
| Visual Localization | 7Scenes Office | 34 | Apr 27, 2026 | ||
| Visual Localization | 7Scenes Heads | 34 | Apr 27, 2026 |