Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1086 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Gland Segmentation | CRAG (test) | 26 | Apr 13, 2026 | ||
| Multi-organ segmentation | Synapse multi-organ CT v1 (fixed (18 train, 12 test)) | 26 | Apr 29, 2026 | ||
| Music Auto-tagging | MagnaTagATune (test) | 26 | Feb 26, 2026 | ||
| Visual Question Answering | VSR | 26 | May 21, 2026 | ||
| Action Recognition | THU-READ | 26 | Feb 26, 2026 | ||
| Language Modeling | XSum | 26 | Feb 26, 2026 | ||
| Title Classification | e-commerce title classification (test) | 26 | Feb 26, 2026 | ||
| Machine Translation | WMT Original 2014-2018 (test) | 26 | Feb 26, 2026 | ||
| Embodied Task Completion | ALFRED unseen (test) | 26 | May 26, 2026 | ||
| Embodied Task Completion | ALFRED seen (test) | 26 | May 26, 2026 | ||
| Intent Classification | Clinc150 (test) | 26 | Feb 26, 2026 | ||
| Machine Translation | Multi30K En → De (test) | 26 | Feb 26, 2026 | ||
| Object Detection | 1 Mpx (test) | 26 | Feb 26, 2026 | ||
| Relation Extraction | ADE | 26 | Jun 30, 2026 | ||
| Long-tailed Image Classification | CIFAR-100 long-tailed (IF=100) (test) | 26 | Jun 2, 2026 | ||
| Sentence Retrieval | Flickr30K 1K (test) | 26 | Feb 26, 2026 | ||
| Few-Shot Object Detection | MS-COCO | 26 | Feb 26, 2026 | ||
| Aspect Sentiment Triplet Extraction | Rest 15 (test) | 26 | Feb 26, 2026 | ||
| 3D Scene Reconstruction | ScanNet V2 (test) | 26 | Feb 26, 2026 | ||
| Grounded Text-to-Image Generation | COCO 2014 (val) | 26 | Feb 27, 2026 | ||
| Misinformation Detection | SLN (test) | 26 | Feb 26, 2026 | ||
| Roll call vote prediction | Roll call vote prediction (Time-Based) | 26 | Feb 26, 2026 | ||
| Video Grounding | MAD 1.0 (test) | 26 | Apr 1, 2026 | ||
| Video Compression | MCL-JCV (test) | 26 | Feb 26, 2026 | ||
| Action Recognition | Something-Something V2 | 26 | Apr 20, 2026 |