Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1660 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Colorization | Multi-instance (test) | 20 | Feb 26, 2026 | ||
| Image Colorization | Extended COCO-Stuff (test) | 20 | Feb 26, 2026 | ||
| Left Atrium Segmentation | LASeg 5% labeled data 4:76 ratio (test) | 20 | Feb 26, 2026 | ||
| Instance Segmentation | COCO 49 (val) | 20 | Feb 26, 2026 | ||
| Natural Language Inference | GLUE | 20 | May 14, 2026 | ||
| Age Regression | HCP | 20 | Apr 16, 2026 | ||
| Sequential Recommendation | Zhihu | 20 | Feb 26, 2026 | ||
| Sequential Recommendation | KuaiRec | 20 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 40 labeled samples | 20 | Feb 26, 2026 | ||
| Conformal Prediction | iNaturalist | 20 | Feb 26, 2026 | ||
| Knowledge Assessment | LAMA-based Knowledge Assessment (test) | 20 | Feb 26, 2026 | ||
| Anomaly Detection | MSL (test) | 20 | Mar 11, 2026 | ||
| 3D Object Detection | IRV2V | 20 | Feb 26, 2026 | ||
| Text-to-image generation | LAION-Aesthetic 6.5+ (test) | 20 | Feb 26, 2026 | ||
| Backdoor Defense | TREC | 20 | Feb 26, 2026 | ||
| Backdoor Defense | SUBJ | 20 | Feb 26, 2026 | ||
| Backdoor Defense | CR | 20 | Feb 26, 2026 | ||
| Backdoor Defense | MR | 20 | Feb 26, 2026 | ||
| Text Classification | MR | 20 | Feb 26, 2026 | ||
| Text Classification | SST-2 | 20 | Feb 26, 2026 | ||
| Canonical Correlation Analysis | Synthetic Data | 20 | Feb 26, 2026 | ||
| Anomaly Detection | 34 benchmark datasets aggregate (test) | 20 | Feb 26, 2026 | ||
| Few-shot Semantic Segmentation | COCO 20 i (cross-val) | 20 | Feb 26, 2026 | ||
| Object Classification | ScanObjectNN Overall | 20 | Feb 26, 2026 | ||
| Image Generation | CIFAR-10 32x32 (train) | 20 | Feb 26, 2026 |