Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1912 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Deep Face Attribution | OW-DFA (Novel) | 18 | Feb 26, 2026 | ||
| Deep Face Attribution | OW-DFA (All) | 18 | Feb 26, 2026 | ||
| Image Reconstruction | FFHQ Glasses | 18 | Feb 26, 2026 | ||
| Image Reconstruction | FFHQ No glasses | 18 | Feb 26, 2026 | ||
| Zero-shot Image Classification | 16-dataset Zero-Shot Adversarial Robustness (ZSAR) Evaluation Suite | 18 | Feb 27, 2026 | ||
| Change Detection | SkyCap SAR Capella X-band 1.0 (test) | 18 | Feb 26, 2026 | ||
| Camera Pose Estimation | KITTI | 18 | Mar 10, 2026 | ||
| 3D Object Detection | V2X-Real (test) | 18 | Feb 26, 2026 | ||
| Chart Question Answering | ChartQA Human-authored | 18 | Apr 24, 2026 | ||
| Spatial Reasoning | SURDS (test) | 18 | Mar 4, 2026 | ||
| Image Classification | StanfordDogs (test) | 18 | Feb 27, 2026 | ||
| Re-identification | Macro Average (Across Datasets) | 18 | Feb 26, 2026 | ||
| Re-identification | CT-RATE | 18 | Feb 26, 2026 | ||
| Re-identification | ISIC 2020 | 18 | Feb 26, 2026 | ||
| Re-identification | NIH-CXR-LT | 18 | Feb 26, 2026 | ||
| Re-identification | CelebA | 18 | May 15, 2026 | ||
| Quantized Compressive Image Recovery | FFHQ (val) | 18 | Feb 26, 2026 | ||
| Monocular Depth Estimation | RobotCar Night (test) | 18 | Feb 26, 2026 | ||
| Video Classification | UCF Mini | 18 | Mar 25, 2026 | ||
| Visual Grounding | Lisa Grounding | 18 | Feb 26, 2026 | ||
| Color Understanding | ColorBench | 18 | Feb 26, 2026 | ||
| Anomaly Detection | MVTec (test) | 18 | Feb 26, 2026 | ||
| Monocular Depth Estimation | 3D-Mirage | 18 | Feb 26, 2026 | ||
| 6DoF hand trajectory prediction | HOT3D OOD (test) | 18 | Feb 26, 2026 | ||
| 6DoF hand trajectory prediction | EgoMAN Unseen (test) | 18 | Feb 26, 2026 |