Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1282 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Age Estimation | FG-NET (test) | 24 | Feb 26, 2026 | ||
| Near-duplicate video retrieval | CC_WEB_VIDEO Cleaned | 24 | Feb 26, 2026 | ||
| Egocentric Action Anticipation | EPIC-Kitchens-55 S1 - Seen (test) | 24 | Feb 26, 2026 | ||
| Scene Recognition | MIT indoor 67 (val) | 24 | Mar 25, 2026 | ||
| Lung Segmentation | Montgomery County (MC) (test) | 24 | Feb 26, 2026 | ||
| Depth Estimation | KITTI 50m cap (test) | 24 | Feb 26, 2026 | ||
| Top-K Recommendation | Last.FM (test) | 24 | Mar 18, 2026 | ||
| Node-level classification | Europe | 24 | Feb 26, 2026 | ||
| Point Cloud Registration | ModelNet40 (test) | 24 | Feb 26, 2026 | ||
| Question Matching | LCQMC (test) | 24 | Feb 26, 2026 | ||
| Question Matching | LCQMC (dev) | 24 | Feb 26, 2026 | ||
| Natural Language Inference | XNLI (dev) | 24 | Feb 26, 2026 | ||
| Semantic Segmentation | LIP (val) | 24 | Feb 26, 2026 | ||
| Video Frame Interpolation | Middlebury (other) | 24 | Feb 26, 2026 | ||
| Temporal Action Segmentation | 50 Salads granularity (Eval) | 24 | Feb 26, 2026 | ||
| Object Classification | miniImageNet (test) | 24 | Feb 26, 2026 | ||
| Vision-and-Language Navigation | Room-to-Room (R2R) (test unseen) | 24 | Feb 26, 2026 | ||
| Multi-label Image Classification | MS-COCO (test) | 24 | Feb 26, 2026 | ||
| Relation Extraction | BioNLP ST 2011 (test) | 24 | Feb 26, 2026 | ||
| Relation Extraction | BioNLP ST 2013 (test) | 24 | Feb 26, 2026 | ||
| Clustering | Fashion (full) | 24 | Feb 26, 2026 | ||
| Clustering | USPS (full) | 24 | Feb 26, 2026 | ||
| Aspect-level Sentiment Analysis | Laptop L (test) | 24 | Feb 26, 2026 | ||
| Visual Question Answering | VQA 2.0 (test) | 24 | Feb 26, 2026 | ||
| Generative Modeling | ImageNet 32x32 downsampled | 24 | Feb 26, 2026 |