Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1971 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Portrait Matting | P3M-500-P 1.0 (test) | 18 | Feb 26, 2026 | ||
| Medical Image Segmentation | Prostate Task-3 | 18 | Feb 26, 2026 | ||
| Predicate Classification | VG150 (test) | 18 | Feb 26, 2026 | ||
| Data-to-Text Generation | ToTTo | 18 | Feb 26, 2026 | ||
| Abstractive Question Summarization | MATINF English translated subset (test) | 18 | Feb 26, 2026 | ||
| Relative Density-Ratio Estimation | Isolet | 18 | Feb 26, 2026 | ||
| Relative Density-Ratio Estimation | Mnist-r | 18 | Feb 26, 2026 | ||
| Neural Architecture Search | NAS-Bench-101 CIFAR-10 (test) | 18 | Feb 26, 2026 | ||
| Word Similarity | WS-353 (test) | 18 | Feb 26, 2026 | ||
| Dependency Parsing | CTB | 18 | Mar 19, 2026 | ||
| Coreference Resolution | English OntoNotes 5.0 (test) | 18 | Feb 26, 2026 | ||
| Online Task-incremental Learning | Split CIFAR100 | 18 | Feb 26, 2026 | ||
| Multi-label Classification | MS COCO 48 seen / 17 unseen classes v1 | 18 | Feb 27, 2026 | ||
| Crowd Tracking | DroneCrowd 1.0 (test) | 18 | Feb 26, 2026 | ||
| Video Classification | Kinetics-100 (test) | 18 | Feb 26, 2026 | ||
| Visual Machine Reading Comprehension | VisualMRC (test) | 18 | Feb 26, 2026 | ||
| Knowledge Graph Completion | DBP5L Greek (test) | 18 | Feb 26, 2026 | ||
| Point Cloud Registration | KITTI LiDAR sequences (00-07) | 18 | Feb 26, 2026 | ||
| Object Detection | COCO+ (val) | 18 | Feb 26, 2026 | ||
| Video Salient Object Detection | DAVIS (test) | 18 | Feb 26, 2026 | ||
| Video Salient Object Detection | VOS (test) | 18 | Feb 26, 2026 | ||
| Handwritten Text Recognition | RIMES 3 (test) | 18 | Feb 26, 2026 | ||
| Handwritten Text Recognition | IAM 30 (test) | 18 | Feb 26, 2026 | ||
| Video Action Recognition | Breakfast | 18 | May 13, 2026 | ||
| 3D Reconstruction | Ellis Island | 18 | Jun 5, 2026 |