Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1776 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Named Entity Recognition | ADE (test) | 19 | Feb 26, 2026 | ||
| Constituency Parsing | CTB 5.0 (test) | 19 | Feb 26, 2026 | ||
| Text Classification | HyperPartisan | 19 | Feb 26, 2026 | ||
| Mortality Prediction | P-Mortality P12 (test) | 19 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 Long Tailed Imbalance Ratio 100 (test) | 19 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 Long Tailed Imbalance Ratio 100 (test) | 19 | Feb 26, 2026 | ||
| Named Entity Recognition | Chinese OntoNotes 4.0 (test) | 19 | Feb 26, 2026 | ||
| Multimodal Machine Translation | MSCOCO EN-FR (test) | 19 | Feb 26, 2026 | ||
| Map Segmentation | nuScenes | 19 | Jul 8, 2026 | ||
| Emotion Recognition | CMU-MOSEI (test) | 19 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO | 19 | Feb 26, 2026 | ||
| Instance-level search | ROxford + R1M (test) | 19 | Feb 26, 2026 | ||
| Unsupervised image segmentation | COCO-Stuff 3-class (test) | 19 | Feb 26, 2026 | ||
| Out-of-distribution detection | CIFAR-10 (Din) / SVHN (Dout) Far OOD (test) | 19 | Feb 26, 2026 | ||
| KG-to-text generation | AGENDA (test) | 19 | Feb 26, 2026 | ||
| Named Entity Recognition | CoNLL English 2003 | 19 | Mar 27, 2026 | ||
| Emotion Recognition in Conversation | IEMOCAP | 19 | Feb 26, 2026 | ||
| Aspect-Level Sentiment Analysis | SemEval Task 4 Laptop 2014 (test) | 19 | Feb 26, 2026 | ||
| Named Entity Recognition | SciTech News Target Domain | 19 | Feb 26, 2026 | ||
| Semi-supervised Video Object Segmentation | DAVIS 2016 (val) | 19 | Feb 26, 2026 | ||
| Cell Segmentation | PhC-C2DL-PSC (test) | 19 | Feb 26, 2026 | ||
| Short-Term Tracking | VOT 2017 2018 | 19 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | H36M | 19 | May 5, 2026 | ||
| Scene Graph Detection | Visual Genome (VG) Zero-Shot | 19 | Feb 26, 2026 | ||
| Scene Graph Classification | Visual Genome (VG) Zero-Shot | 19 | Feb 26, 2026 |