Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 734 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Editing Alignment Assessment | HPE-Bench 1.0 (test) | 33 | Feb 26, 2026 | ||
| Referring Video Object Segmentation | Ref-Davis (val) | 33 | Mar 31, 2026 | ||
| Edge Detection | NYUD v2 | 33 | May 8, 2026 | ||
| Image Classification | STL-10 | 33 | Feb 26, 2026 | ||
| Fake News Video Detection | FakeSV (Source: FakeTT) (test) | 33 | Feb 26, 2026 | ||
| Multi-Label Class-Incremental Learning | PASCAL VOC B0-C4 | 33 | Mar 9, 2026 | ||
| Human Pose Estimation | WiPose | 33 | Jul 7, 2026 | ||
| Region Captioning | DLC-Bench | 33 | Jun 19, 2026 | ||
| 3D Scene Generation | WorldScore | 33 | Mar 4, 2026 | ||
| Semantic Segmentation | Embryo image dataset (test) | 33 | May 13, 2026 | ||
| Image Classification | Caltech 256 | 33 | Apr 23, 2026 | ||
| Image Classification | Food101 | 33 | Mar 31, 2026 | ||
| Desnowing | WeatherBench | 33 | Mar 17, 2026 | ||
| Semantic Segmentation | GID | 33 | May 26, 2026 | ||
| Visual Question Answering | MM-Vet | 33 | Mar 9, 2026 | ||
| 200-way retrieval | THINGS-MEG Intra-subject | 33 | May 19, 2026 | ||
| Driver and Traffic Scene Recognition | AIDE | 33 | Feb 26, 2026 | ||
| Abstract Visual Reasoning | ARC-AGI 2 | 33 | May 14, 2026 | ||
| Image Classification | OrganCMNIST MedMNIST (test) | 33 | Apr 3, 2026 | ||
| Video Understanding | WorldSense | 33 | Jun 24, 2026 | ||
| Open-Vocabulary Segmentation | iSAID | 33 | Jun 23, 2026 | ||
| Open-Vocabulary Segmentation | Vaihingen | 33 | Jun 23, 2026 | ||
| Open-Vocabulary Segmentation | Potsdam | 33 | Jun 23, 2026 | ||
| Open-Vocabulary Segmentation | LoveDA | 33 | Jun 23, 2026 | ||
| Text-to-image generation | OneIG-Bench | 33 | Jun 12, 2026 |