Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1632 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Action Recognition | HMDB51-DVS | 20 | Apr 14, 2026 | ||
| Visual Geolocation | IM2GPS3K | 20 | Jul 3, 2026 | ||
| Image Classification | Animals | 20 | Feb 26, 2026 | ||
| Composition Image Generation | GenEval | 20 | Feb 26, 2026 | ||
| RGB-D Salient Object Detection | DUTLF-D | 20 | Jun 26, 2026 | ||
| Monocular Depth Estimation | CityScapes v1 (test) | 20 | Feb 26, 2026 | ||
| Human/Part Parsing | PASCAL-Context (test) | 20 | Feb 26, 2026 | ||
| Online Video Question Answering | StreamingBench | 20 | Feb 26, 2026 | ||
| Visual Reasoning | Vision-Centric Benchmarks | 20 | Feb 26, 2026 | ||
| Fine-Grained Open-Vocabulary Object Detection | FG-OVD | 20 | Feb 26, 2026 | ||
| Image Generation | AnimalFace Dog standard (train) | 20 | Feb 26, 2026 | ||
| Image Generation | AnimalFace Cat standard (train) | 20 | Feb 26, 2026 | ||
| Visual Place Recognition | Amstertime-La | 20 | Feb 26, 2026 | ||
| Visual Place Recognition | MSLS Weather | 20 | Feb 26, 2026 | ||
| Visual Place Recognition | MSLS Blur | 20 | Feb 26, 2026 | ||
| Open-ended caption generation | MSCOCO 2014 (val) | 20 | Feb 26, 2026 | ||
| Geometric diagram generation | GenExam-Math (test) | 20 | Feb 26, 2026 | ||
| 2D Object Detection | COCO 2014 (val) | 20 | Feb 26, 2026 | ||
| Image Captioning | ROCO v2 | 20 | Feb 26, 2026 | ||
| Utility Preservation | COCO-10K (val) | 20 | Mar 27, 2026 | ||
| OOD Detection | SUN | 20 | Apr 28, 2026 | ||
| Visual Spatial Intelligence Reasoning | VSI | 20 | Feb 26, 2026 | ||
| Building Change Detection | DSIFN (test) | 20 | Jun 19, 2026 | ||
| Monocular Visual Odometry | VIVID Mean over sequences | 20 | Feb 26, 2026 | ||
| Vision-Language Compositionality | SugarCrepe | 20 | Feb 27, 2026 |