Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1129 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video-to-Audio | VGGSound (test) | 25 | Jul 1, 2026 | ||
| Denoising | SSID (test) | 25 | Jun 17, 2026 | ||
| 3D Object Classification | ScanObjectNN PB_T50_RS (FULL Protocol) | 25 | Feb 26, 2026 | ||
| Object Detection | CS-positive | 25 | Feb 26, 2026 | ||
| Semantic Segmentation | Chest X-ray | 25 | Mar 31, 2026 | ||
| Mathematical Reasoning | DynaMath | 25 | May 28, 2026 | ||
| Hallucination Evaluation | HalBench | 25 | Jun 30, 2026 | ||
| Semantic Segmentation | HLS Burn Scars | 25 | Mar 10, 2026 | ||
| Novel-view synthesis | RE10K Large | 25 | Mar 27, 2026 | ||
| Place Recognition | nuScenes (BS) | 25 | Apr 7, 2026 | ||
| Image Denoising | CC15 | 25 | Feb 26, 2026 | ||
| Remote Sensing Image Dehazing | SateHaze1k Moderate | 25 | Apr 28, 2026 | ||
| Medical Visual Question Answering | MMMU H&M | 25 | Feb 26, 2026 | ||
| Forgery Classification | Average across 7 Sets (CASIA2, NIST16, DEFACTO, ForenSynths, DiffusionDB, Midjourney, RAISE) (test) | 25 | Feb 26, 2026 | ||
| Foreground Segmentation | Pascal-5i Fold-1 (test) | 25 | Apr 7, 2026 | ||
| Foreground Segmentation | Pascal-5i Fold-0 (test) | 25 | Apr 7, 2026 | ||
| Medical Image Segmentation | Lung Cancer (LC) (test) | 25 | Feb 26, 2026 | ||
| Robot Manipulation | MetaWorld, Adroit, and Dexart Combined | 25 | Jun 2, 2026 | ||
| Novel-view reconstruction | RE10K | 25 | Jun 2, 2026 | ||
| Image Classification | ImageNet-A OfficeHome source (test) | 25 | Feb 26, 2026 | ||
| Image Classification | ImageNet-R OfficeHome source (test) | 25 | Feb 26, 2026 | ||
| Image Classification | ImageNet-A MiniDomainnet source (test) | 25 | Feb 26, 2026 | ||
| Image Classification | ImageNet-R MiniDomainnet source (test) | 25 | Feb 26, 2026 | ||
| Infrared Small Target Detection | IRSatVideo-LEO (test) | 25 | Feb 26, 2026 | ||
| Infrared Small Target Detection | NUDT-MIRSDT (test) | 25 | Feb 26, 2026 |