Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 431 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Entity Alignment | DBP ZH-EN 15K | 47 | Feb 26, 2026 | ||
| Visual Object Tracking | OTB 2015 (test) | 47 | Feb 26, 2026 | ||
| Action Anticipation | EPIC-KITCHENS unseen S2 (test) | 47 | Feb 26, 2026 | ||
| Question Answering | MetaQA 3-hop | 47 | Mar 17, 2026 | ||
| 5-way Classification | miniImageNet 5-way (test) | 47 | Feb 26, 2026 | ||
| BEV Object Detection | KITTI (test) | 47 | Feb 27, 2026 | ||
| Node Classification | Cora (Fixed) | 47 | Mar 31, 2026 | ||
| Grammatical Error Correction | JFLEG | 47 | Feb 26, 2026 | ||
| Semantic Segmentation | S3DIS (test) | 47 | Feb 26, 2026 | ||
| Molecular Property Classification | MoleculeNet BACE | 47 | May 14, 2026 | ||
| Node Classification | CiteSeer (random) | 47 | Feb 26, 2026 | ||
| Gaussian Denoising | Set12 | 47 | Feb 26, 2026 | ||
| Image Quality Assessment | TID 2013 (full) | 47 | Feb 26, 2026 | ||
| Clustering | COIL-20 | 47 | Feb 26, 2026 | ||
| Face Verification | LFW (Labeled Faces in the Wild) unrestricted-labeled-outside-data protocol 14 | 47 | Feb 26, 2026 | ||
| Multi-Person Pose Estimation | MPII Multi-Person full (test) | 47 | Feb 26, 2026 | ||
| Image Retrieval | Oxford 105k | 47 | Feb 26, 2026 | ||
| Person Re-identification | i-LIDS (test) | 47 | Feb 26, 2026 | ||
| Hyperspectral Tensor Reconstruction | Hyperspectral radiance image tensor (full) | 47 | Feb 26, 2026 | ||
| Domain Adaptation | MNIST to MNIST-M (test) | 47 | Jun 4, 2026 | ||
| Classification | AIRPLANE | 47 | Feb 26, 2026 | ||
| Molecule Generation | MOSES (test) | 47 | Jun 23, 2026 | ||
| Molecular Property Prediction | MoleculeNet ClinTox (scaffold) | 47 | May 14, 2026 | ||
| Speech Classification | VF | 47 | Feb 26, 2026 | ||
| Semantic Segmentation | COCOStuff 164k (val) | 47 | Apr 8, 2026 |