Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1741 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text-to-point cloud localization | KITTI360 Pose (val) | 19 | Apr 3, 2026 | ||
| Few-shot Segmentation | Leaf diseases Agriculture | 19 | Feb 26, 2026 | ||
| Few-shot Segmentation | Steel defect Industrial | 19 | Feb 26, 2026 | ||
| Few-shot Segmentation | Road crack Industrial | 19 | Feb 26, 2026 | ||
| Gaussian Deblur | ImageNet | 19 | Mar 10, 2026 | ||
| Face Image Quality Assessment | Adience (test) | 19 | Feb 26, 2026 | ||
| Image Forgery Classification | ForenSynths | 19 | May 15, 2026 | ||
| Salient Object Detection | NEU-RSDDS-AUG | 19 | Feb 26, 2026 | ||
| Video Moment Retrieval | ActivityNet-Captions (test) | 19 | Apr 3, 2026 | ||
| 3D Point Cloud Registration | Stanford Bunny B0 | 19 | Feb 26, 2026 | ||
| Subjective Evaluation | WildBench | 19 | Apr 10, 2026 | ||
| Generalized Category Discovery | ImageNet 1k | 19 | Feb 26, 2026 | ||
| Coloring | ImageNet 1K | 19 | Mar 20, 2026 | ||
| Fake Image Detection | HPE-Bench 1.0 (Overall) | 19 | Feb 26, 2026 | ||
| Fake Image Detection | HPE-Bench Text2LIVE 1.0 | 19 | Feb 26, 2026 | ||
| Visual Perception | Blink 41 (val) | 19 | Feb 26, 2026 | ||
| Multi-Image Understanding | MMIU 106 (test) | 19 | Feb 26, 2026 | ||
| Multi-Image Understanding | MuirBench 142 (test) | 19 | Feb 26, 2026 | ||
| Multi-Task Learning | PASCAL-Context and NYUD-v2 clean and adverse conditions v1 (unseen) | 19 | Feb 26, 2026 | ||
| Human Parsing | PASCAL-Context clean and adverse conditions v1 (unseen) | 19 | Feb 26, 2026 | ||
| Saliency Detection | PASCAL-Context clean and adverse conditions v1 (unseen) | 19 | Feb 26, 2026 | ||
| Semantic Segmentation | PASCAL-Context clean and adverse conditions v1 (unseen) | 19 | Feb 26, 2026 | ||
| Document Question Answering | SlideVQA (test) | 19 | Apr 21, 2026 | ||
| Image Classification | ImageNet 1K | 19 | Feb 26, 2026 | ||
| Albedo Estimation | ARAP | 19 | Feb 26, 2026 |