Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1753 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Human Mesh Recovery | EMDB (test) | 19 | Feb 26, 2026 | ||
| Medical Image Segmentation | breast ultrasound (test) | 19 | Feb 26, 2026 | ||
| Cardiac Segmentation | ACDC 10% labeled scans | 19 | Feb 26, 2026 | ||
| Virtual Try-on | VITON paired HD (test) | 19 | Feb 26, 2026 | ||
| Person Search | PRW v1 (test) | 19 | Feb 26, 2026 | ||
| Scene Text Recognition | ArT (test) | 19 | Feb 26, 2026 | ||
| wet-AMD conversion prediction | HARBOR 12-month window (test) | 19 | Feb 26, 2026 | ||
| wet-AMD conversion prediction | HARBOR 6-month window (test) | 19 | Feb 26, 2026 | ||
| Classification | SICAP v2 | 19 | Mar 23, 2026 | ||
| Classification | BACH | 19 | Feb 26, 2026 | ||
| Semantic Segmentation | GTA5 to Cityscapes, BDD100K, Mapillary Vistas (val) | 19 | Feb 26, 2026 | ||
| Response Harmfulness Classification | Public Response Harmfulness Benchmarks (HarmBenchResponse, SafeRLHF, BeaverTails, XSTEST-RESP) | 19 | May 11, 2026 | ||
| Multimodal Understanding | SEED-I | 19 | Feb 26, 2026 | ||
| Geometric Matching | ETH3D Original Resolution | 19 | Feb 26, 2026 | ||
| Implicit Sentiment Analysis | Laptop14 ISA original (test) | 19 | Feb 26, 2026 | ||
| Implicit Sentiment Analysis | Restaurant14 ISA original (test) | 19 | Feb 26, 2026 | ||
| Object Detection | EvDET200K (test) | 19 | Feb 26, 2026 | ||
| Graph Generation | Ego-small (test) | 19 | May 18, 2026 | ||
| Image Classification | ImageNet-1k 1 (val) | 19 | Feb 26, 2026 | ||
| Online Continual Learning | miniImageNet 100/1 (test) | 19 | Feb 27, 2026 | ||
| Common Sense Reasoning | WorldSense | 19 | May 22, 2026 | ||
| Tool Use | API-Bank (test) | 19 | Jun 16, 2026 | ||
| Image Classification | CIFAR-100 10-shot (test) | 19 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 5-shot (test) | 19 | Feb 26, 2026 | ||
| Multimodal Dialogue Evaluation | LLaVA-Bench Wild (test) | 19 | Feb 26, 2026 |