Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 799 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Facial Landmark Localization | 300-W (Challenging set) | 32 | Feb 26, 2026 | ||
| Question Answering | WikiHop (test) | 32 | Feb 26, 2026 | ||
| Facial landmark detection | 300W official (test) | 32 | Feb 26, 2026 | ||
| Action Recognition | EPIC-Kitchens v1 (test s2 (unseen)) | 32 | Feb 26, 2026 | ||
| Partial Domain Adaptation | ImageNet-Caltech | 32 | Feb 26, 2026 | ||
| Vision-and-Language Navigation | Room-to-Room (R2R) Seen (val) | 32 | Feb 26, 2026 | ||
| Dependency Semantic Role Labeling | CoNLL 2009 (test) | 32 | Feb 26, 2026 | ||
| Fine-grained Video Categorization | ActivityNet v1.3 (val) | 32 | Feb 26, 2026 | ||
| 3D hand pose estimation | MSRA | 32 | Feb 26, 2026 | ||
| Image-to-Image Translation | edges -> handbags (test) | 32 | Jun 4, 2026 | ||
| Scene Completion | NYUCAD | 32 | Feb 26, 2026 | ||
| Salient Object Detection | HKU-IS 18 (test) | 32 | Feb 26, 2026 | ||
| 3D Semantic Segmentation | Matterport3D (test) | 32 | Mar 30, 2026 | ||
| Node Classification | CiteSeer 3% label rate | 32 | Mar 4, 2026 | ||
| Node Classification | CiteSeer 2% label rate | 32 | Mar 4, 2026 | ||
| Super-resolution | Set14 34 (test) | 32 | Feb 26, 2026 | ||
| Person Re-identification | SYSU | 32 | Mar 23, 2026 | ||
| AMR parsing | LDC2014T12 (Full) | 32 | Feb 26, 2026 | ||
| Vehicle Retrieval | VehicleID (Small) | 32 | Feb 26, 2026 | ||
| Human Pose Estimation | MPII | 32 | Feb 26, 2026 | ||
| Individual Treatment Effect Estimation | Jobs (out-of-sample) | 32 | Feb 26, 2026 | ||
| Open-ended Visual Question Answering | VQA (test-standard) | 32 | Feb 26, 2026 | ||
| Intent Detection | ATIS | 32 | Apr 14, 2026 | ||
| Subspace Clustering | MNIST | 32 | Feb 26, 2026 | ||
| Sentence Retrieval | Flickr30K | 32 | Feb 26, 2026 |