Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1281 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Depth estimation | DIODE Indoor | 24 | May 29, 2026 | ||
| Person Re-Identification | GRID (test) | 24 | Feb 26, 2026 | ||
| Video Prediction | KTH (test) | 24 | Feb 26, 2026 | ||
| Video Paragraph Captioning | ActivityNet Captions ae (test) | 24 | Feb 26, 2026 | ||
| Retinal Disease Classification | OCT 2017 (test) | 24 | Feb 26, 2026 | ||
| Image Classification | MNIST Permutation-invariant (DW) | 24 | Feb 26, 2026 | ||
| Image Classification | Permutation-invariant MNIST (SW) | 24 | Feb 26, 2026 | ||
| Panoptic Segmentation | MS-COCO (val) | 24 | Feb 26, 2026 | ||
| Semantic Video Segmentation | Cityscapes (test) | 24 | Feb 26, 2026 | ||
| Image Captioning | COCO c5 references online (test) | 24 | Feb 26, 2026 | ||
| Multi-label Image Classification | MS-COCO 2014 (test) | 24 | Feb 26, 2026 | ||
| Semantic Correspondence | SPair-71k | 24 | Feb 26, 2026 | ||
| Image Classification | iNaturalist 2017 (test) | 24 | Mar 10, 2026 | ||
| Face Anti-Spoofing | OULU-NPU (Protocol 1) | 24 | Feb 26, 2026 | ||
| Image Classification | Colored MNIST (test) | 24 | Feb 26, 2026 | ||
| Link Prediction | WN18RR v1 (test) | 24 | Feb 26, 2026 | ||
| Video-grounded Dialogue | DSTC7 (test) | 24 | Feb 26, 2026 | ||
| Matrix Completion | MovieLens-100K (test) | 24 | Jun 4, 2026 | ||
| Super-resolution | DIV2KRK 100 images (test) | 24 | Feb 26, 2026 | ||
| Nuclear Instance Segmentation | Kumar | 24 | Mar 10, 2026 | ||
| Multi-class Classification | 20NewsGroup | 24 | Feb 26, 2026 | ||
| Relationship Extraction | SemEval Task 8 2010 (test) | 24 | Feb 26, 2026 | ||
| Intent Classification | ODIC (test) | 24 | Feb 26, 2026 | ||
| Single-view depth estimation | KITTI raw (test) | 24 | Feb 26, 2026 | ||
| Human Pose Prediction | Human 3.6M Subject 5 (test) | 24 | Feb 27, 2026 |