Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 346 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | Places-365 (val) | 54 | Jun 26, 2026 | ||
| Out-of-Distribution Detection | Average OpenImage-O, Texture, iNaturalist, ImageNet-O | 54 | Feb 26, 2026 | ||
| Traffic Forecasting | NAVER-Seoul (test) | 54 | Feb 26, 2026 | ||
| Natural Language Inference | HANS (test) | 54 | Feb 26, 2026 | ||
| Two-sample testing | CIFAR-10 vs CIFAR-10.1 1.0 (test) | 54 | Feb 26, 2026 | ||
| Video Recognition | Kinetics-400 (test) | 54 | Jun 11, 2026 | ||
| Multi-Object Tracking and Segmentation | BDD100K segmentation tracking (val) | 54 | Feb 26, 2026 | ||
| Image Classification | ImageNet V2 1.0 (test) | 54 | Feb 26, 2026 | ||
| Clustering | DBLP | 54 | Jun 23, 2026 | ||
| Offline Reinforcement Learning | D4RL Gym hopper-medium | 54 | Jun 15, 2026 | ||
| Scene Text Recognition | SVTP 645 (test) | 54 | Feb 26, 2026 | ||
| Video Quality Assessment | LIVE-VQC (test) | 54 | Feb 26, 2026 | ||
| Image Classification | CIFAR-LT-100 Imbalance Factor 50 (test) | 54 | May 12, 2026 | ||
| 3D Human Shape Estimation | SSP-3D (test) | 54 | Feb 26, 2026 | ||
| Continual Learning | CIFAR-100 (10-split) | 54 | May 13, 2026 | ||
| Semantic Segmentation | ADE20k (100-5) | 54 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 1.0 (test) | 54 | Feb 26, 2026 | ||
| Polyp Segmentation | Kvasir-SEG | 54 | Jul 7, 2026 | ||
| 3D Geometry Reconstruction | ScanNet | 54 | Feb 26, 2026 | ||
| Defocus Deblurring | DP Dataset Indoor 1.0 (test) | 54 | Feb 26, 2026 | ||
| Visual Object Tracking | NFS (Need for Speed) 30 FPS (test) | 54 | Feb 26, 2026 | ||
| Visual Object Tracking | VOT 2018 (test) | 54 | Feb 26, 2026 | ||
| Image Deraining | 1200 (test) | 54 | Jun 23, 2026 | ||
| Graph Classification | RDT-M5K | 54 | Mar 19, 2026 | ||
| Semantic Image Synthesis | Cityscapes | 54 | May 18, 2026 |