Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1035 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Object Detection | MS-COCO 2017 (val) | 27 | Feb 27, 2026 | ||
| Natural Language Inference | SNLI hard 1.0 (test) | 27 | Feb 26, 2026 | ||
| Machine Translation | WMT16 Ro-En (test) | 27 | Feb 27, 2026 | ||
| Multi-document summarization | WCEP (test) | 27 | Feb 26, 2026 | ||
| Image Classification | S-CIFAR-10 | 27 | Feb 26, 2026 | ||
| Graph Regression | ZINC 12k graphs v1 (test) | 27 | Feb 26, 2026 | ||
| Image Classification | ImageNet-100 1.0 (val) | 27 | Feb 26, 2026 | ||
| No-Reference Image Quality Assessment | TID2013 (80/20 split) | 27 | Feb 26, 2026 | ||
| Weakly-supervised semantic segmentation | MS COCO 2014 (val) | 27 | Feb 26, 2026 | ||
| Video Prediction | BAIR 64x64 (test) | 27 | Mar 6, 2026 | ||
| Dialogue Generation | PersonaChat (test) | 27 | Jun 12, 2026 | ||
| Facial Expression Recognition | ExpW | 27 | Feb 26, 2026 | ||
| Certified Image Classification | MNIST (test) | 27 | Feb 27, 2026 | ||
| Image Classification Certified Robustness | MNIST (test) | 27 | Feb 27, 2026 | ||
| Image Classification | ColoredMNIST (test) | 27 | Jul 2, 2026 | ||
| Incremental Semantic Segmentation | Pascal VOC disjoint setup 2012 (VOC 15-5) | 27 | Jun 4, 2026 | ||
| Lossless Compression | ImageNet64 (test) | 27 | Feb 26, 2026 | ||
| Incremental Learning | CIFAR-100 (test) | 27 | May 13, 2026 | ||
| Single-object discovery | COCO 20k | 27 | May 13, 2026 | ||
| Co-saliency Object Detection | CoSal 2015 | 27 | Feb 26, 2026 | ||
| Image Classification | Flowers | 27 | Feb 26, 2026 | ||
| Segmentation | Hippocampus (test) | 27 | Feb 26, 2026 | ||
| Salient Object Detection | DUT | 27 | Feb 26, 2026 | ||
| Medical Image Segmentation | Spleen Task-5 | 27 | Feb 26, 2026 | ||
| Medical Image Segmentation | Medical Segmentation Decathlon (MSD) (test) | 27 | Feb 26, 2026 |