Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1913 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Depth Estimation | nuScenes | 18 | Jun 16, 2026 | ||
| Hair Appearance Rendering | Synthetic Dynamic Hair Dataset (test) | 18 | Feb 26, 2026 | ||
| Survival Prediction | KIRC | 18 | Feb 26, 2026 | ||
| CT Reconstruction | AAPM 256 x 256 x 256 (test) | 18 | Feb 26, 2026 | ||
| Mosaic Segmentation | Mosaic Dataset Image IDs 7 and 11 (test) | 18 | Feb 26, 2026 | ||
| Out-of-view Understanding | OpenView-Bench Overall | 18 | Feb 26, 2026 | ||
| Out-of-view Understanding | OpenView-Bench Directional | 18 | Feb 26, 2026 | ||
| Out-of-view Understanding | OpenView-Bench Contextual | 18 | Feb 26, 2026 | ||
| Low-light Image Enhancement | MEF (test) | 18 | Jul 7, 2026 | ||
| 3D Shape Generation | ShapeNet Chair | 18 | Mar 20, 2026 | ||
| Visual Question Answering | OmniMedVQA MI | 18 | Feb 26, 2026 | ||
| Multi-class classification | DVM (test) | 18 | Feb 26, 2026 | ||
| Regression | UK Biobank (test) | 18 | Feb 26, 2026 | ||
| Multi-label classification | UK Biobank (test) | 18 | Feb 26, 2026 | ||
| Dynamic Scene Reconstruction | N3DV coffee martini (test) | 18 | Feb 26, 2026 | ||
| human-human interaction motion generation | Inter-X (Full) | 18 | Feb 26, 2026 | ||
| Segmentation | MSD Spleen | 18 | Mar 4, 2026 | ||
| Few-shot image generation | Sketches 10-shot | 18 | Feb 26, 2026 | ||
| Video Understanding | OVO (Real-Time) | 18 | Mar 16, 2026 | ||
| Few-shot Image Classification | Dogs (test) | 18 | Feb 26, 2026 | ||
| Fine-grained Image Classification | CUB (test) | 18 | Feb 26, 2026 | ||
| Visual Question Answering | UniPercept-Bench-VQA IAA 1.0 (test) | 18 | Feb 26, 2026 | ||
| Salient Object Detection | un-VT821 | 18 | Feb 26, 2026 | ||
| Salient Object Detection | un-VT1000 | 18 | Feb 26, 2026 | ||
| Salient Object Detection | un-VT5000 | 18 | Feb 26, 2026 |