Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1919 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Object Detection | KITTI | 18 | Mar 30, 2026 | ||
| Mobile GUI Agents | AndroidWorld 138 tasks (test) | 18 | Feb 26, 2026 | ||
| Optic Disc and Optic Cup Segmentation | OD/OC (Domain B) | 18 | Mar 13, 2026 | ||
| Fine-grained visual understanding | V* Bench | 18 | Feb 26, 2026 | ||
| Open-Vocabulary Segmentation | Natural-scene (NS) benchmark suite V21, PC60, COCO-O, V20, PC59, COCO-S, City, ADE | 18 | Feb 26, 2026 | ||
| Spatial Reasoning | STI-Bench | 18 | Feb 26, 2026 | ||
| Deepfake Detection | DeepfakeBench Cross Domain multiple (test) | 18 | Feb 26, 2026 | ||
| Medical Visual Question Answering | Medical VQA Suite (MMMU-Med, VQA-RAD, SLAKE, PathVQA, PMC-VQA, OmniMedVQA, MedXpertQA) | 18 | Feb 26, 2026 | ||
| Monocular Visual Odometry | VIVID in_rob_local | 18 | Feb 26, 2026 | ||
| Retrieval | THINGS-EEG (test) | 18 | Feb 26, 2026 | ||
| Brain disorder classification | Mātai | 18 | Feb 26, 2026 | ||
| Brain disorder classification | ABIDE-120 Five-fold (cross-val) | 18 | Feb 26, 2026 | ||
| Brain disorder classification | TaoWu Five-fold (cross-val) | 18 | Feb 26, 2026 | ||
| Brain disorder classification | ABIDE-300 (Five-fold cross-val) | 18 | Feb 26, 2026 | ||
| Brain disorder classification | ABIDE-240 (Five-fold cross-validation) | 18 | Feb 26, 2026 | ||
| Brain disorder classification | ABIDE 180 (Five-fold cross-validation) | 18 | Feb 26, 2026 | ||
| Text-to-motion generation | SnapMoGen (test) | 18 | May 13, 2026 | ||
| Low-Light Video Enhancement | SMID | 18 | Feb 26, 2026 | ||
| Grounding | UI-Vision | 18 | Feb 26, 2026 | ||
| Grounding | MMbench | 18 | Feb 26, 2026 | ||
| Grounding | VenusBench GD | 18 | Feb 26, 2026 | ||
| Watermarking | AMBER | 18 | Feb 26, 2026 | ||
| Smoke Segmentation | Hyperspectral Smoke Segmentation Dataset Total (test) | 18 | Feb 26, 2026 | ||
| Smoke Segmentation | Hyperspectral Smoke Segmentation Dataset Large (test) | 18 | Feb 26, 2026 | ||
| Smoke Segmentation | Hyperspectral Smoke Segmentation Dataset Small (test) | 18 | Feb 26, 2026 |