Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1151 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | Fungi | 25 | Mar 4, 2026 | ||
| One-class Out-of-Distribution Detection | CIFAR-10 (test) | 25 | Feb 26, 2026 | ||
| Survival Analysis | METABRIC (5-fold cross-validation) | 25 | Jun 11, 2026 | ||
| Survival Analysis | FLCHAIN (5-fold cross-validation) | 25 | Jun 11, 2026 | ||
| Mirror Segmentation | MSD (test) | 25 | Feb 26, 2026 | ||
| Document-level Event Extraction | ChFinAnn (test) | 25 | Feb 26, 2026 | ||
| Relation Extraction | ChemProt (test) | 25 | Feb 26, 2026 | ||
| Speech Recognition | Hub5'00 | 25 | Feb 26, 2026 | ||
| Node Clustering | PubMed (test) | 25 | May 19, 2026 | ||
| Layout-to-Image Synthesis | COCO-Stuff (test) | 25 | Feb 26, 2026 | ||
| Near-duplicate video retrieval | CC_WEB_VIDEO | 25 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 (test) | 25 | Feb 26, 2026 | ||
| Speaker Verification | LibriSpeech (test) | 25 | Jun 9, 2026 | ||
| Zero-Shot Recognition | AWA1 (test) | 25 | Feb 27, 2026 | ||
| Partial Domain Adaptation | VisDA Synthetic-12 -> Real-6 2017 | 25 | Feb 26, 2026 | ||
| Action Classification | HMDB (test) | 25 | Feb 26, 2026 | ||
| Natural Language Inference | WNLI (test) | 25 | Feb 26, 2026 | ||
| Hand Pose Estimation | NYU (test) | 25 | Feb 26, 2026 | ||
| Multi-person Pose Tracking | PoseTrack 2018 (val) | 25 | Feb 26, 2026 | ||
| Speaker Verification | VoxCeleb1 hard (test) | 25 | Feb 26, 2026 | ||
| Speaker Verification | VoxCeleb1 extended (test) | 25 | Feb 26, 2026 | ||
| Unlabeled Parsing | Penn Treebank WSJ (test) | 25 | Feb 26, 2026 | ||
| Scene Classification | Places365 (val) | 25 | Feb 26, 2026 | ||
| Semantic Segmentation | Foggy Driving-dense (FDD) (test) | 25 | Feb 26, 2026 | ||
| Zero-shot Learning | AWA1 | 25 | Feb 27, 2026 |