Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 261 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Scene Text Recognition | SVTP | 64 | Mar 20, 2026 | ||
| Image Classification | Imbalanced CIFAR-10 (val) | 64 | Feb 26, 2026 | ||
| Multivariate Time Series Forecasting | Solar Energy | 64 | Feb 26, 2026 | ||
| Word-level language modeling | WikiText-103 (dev) | 64 | Feb 26, 2026 | ||
| Multi-hop Question Answering | HotpotQA fullwiki setting (test) | 64 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 Symmetric Noise (test) | 64 | Feb 26, 2026 | ||
| 3D Object Detection | SUN RGB-D (test) | 64 | Feb 26, 2026 | ||
| Gait Recognition | CASIA-B CL (Coat) #1-2 (probe) | 64 | Feb 27, 2026 | ||
| Action Recognition | Charades | 64 | Feb 26, 2026 | ||
| Whole-body Pose Estimation | COCO-Wholebody 1.0 (val) | 64 | Feb 26, 2026 | ||
| Multiple Choice Question Answering | RACE | 64 | Jun 1, 2026 | ||
| Semantic Segmentation | ScanNet (test) | 64 | Mar 10, 2026 | ||
| Image Retrieval | Stanford Online Products | 64 | May 12, 2026 | ||
| Topic Classification | DBPedia (test) | 64 | Feb 26, 2026 | ||
| Part-of-Speech Tagging | Penn TreeBank (test) | 64 | Feb 26, 2026 | ||
| 3D Molecule Generation | QM9 (test) | 64 | Mar 25, 2026 | ||
| Low-rank tensor decomposition | Cardiac MRI tensor | 64 | Feb 26, 2026 | ||
| Classification | HAR (test) | 64 | Jun 23, 2026 | ||
| Image Generation | CIFAR-10 32x32 (50K samples) | 64 | Feb 26, 2026 | ||
| 3D Shape recognition | ModelNet10 (test) | 64 | Feb 26, 2026 | ||
| Semantic Segmentation | Vaihingen (test) | 64 | May 12, 2026 | ||
| Polyp Segmentation | ClinicDB | 64 | Apr 7, 2026 | ||
| Commonsense reasoning | PIQA 1.0 (test) | 64 | Apr 21, 2026 | ||
| Class-incremental learning | ImageNet-R 5-task | 64 | May 28, 2026 | ||
| Video Action Classification | Diving-48 | 64 | Apr 23, 2026 |