Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 977 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Hand Reconstruction | DexYCB (test) | 28 | Feb 26, 2026 | ||
| Text-to-Image Retrieval | CC 152K (test) | 28 | Apr 9, 2026 | ||
| Image-to-Text Retrieval | CC 152K (test) | 28 | Apr 9, 2026 | ||
| Image Classification | ImageNet 1k (source) | 28 | Feb 26, 2026 | ||
| Robustness Verification | MNIST (test) | 28 | Jul 7, 2026 | ||
| Dense Video Captioning | ActivityNet (val) | 28 | Mar 6, 2026 | ||
| Room Layout Estimation | MatterportLayout (test) | 28 | Feb 26, 2026 | ||
| Multimodal Classification | UPMC Food-101 (test) | 28 | Feb 26, 2026 | ||
| Object Detection | Watercolor (test) | 28 | Mar 24, 2026 | ||
| Scene Graph Detection (SGDet) | Visual Genome (VG) | 28 | Apr 23, 2026 | ||
| Pose estimation | YFCC100M | 28 | Feb 26, 2026 | ||
| Glass Segmentation | RGB-T dataset All images 1.0 (test) | 28 | Feb 26, 2026 | ||
| Glass Segmentation | RGB-T dataset Images without glass 1.0 (test) | 28 | Feb 26, 2026 | ||
| Glass Segmentation | RGB-T dataset Images with glass 1.0 (test) | 28 | Feb 26, 2026 | ||
| 3D Human Pose and Mesh Reconstruction | 3DPW (test) | 28 | Mar 24, 2026 | ||
| 35-way Speech Classification | Speech Commands 8kHz 35-way (test) | 28 | Feb 27, 2026 | ||
| Few-shot classification | CropDiseases (test) | 28 | Feb 26, 2026 | ||
| Image Classification | PatchCamelyon (test) | 28 | Feb 27, 2026 | ||
| OOD detection | Retinal Glaucoma images REFUGE (test) | 28 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 (test) | 28 | Feb 26, 2026 | ||
| Long-form Transcription | Earnings-21 | 28 | Jun 9, 2026 | ||
| Scene Text Detection | MSRA-TD500 | 28 | Feb 26, 2026 | ||
| Text-to-Image Retrieval | FETA manually curated Car-Manuals 1.0 | 28 | Feb 26, 2026 | ||
| Image-to-Text Retrieval | FETA manually curated Car-Manuals 1.0 | 28 | Feb 26, 2026 | ||
| Speech Recognition | AISHELL-1 (dev) | 28 | Feb 26, 2026 |