Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 353 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| hopper locomotion | D4RL hopper medium-expert | 53 | May 7, 2026 | ||
| Language Modeling | The Pile (test) | 53 | Jun 2, 2026 | ||
| Video Segmentation | DAVIS | 53 | Jun 23, 2026 | ||
| Traffic Forecasting | PeMSD8 (test) | 53 | Feb 26, 2026 | ||
| Traffic Forecasting | PeMSD4 (test) | 53 | Feb 26, 2026 | ||
| Traffic Forecasting | PeMSD3 (test) | 53 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL HalfCheetah Medium v2 | 53 | Jun 2, 2026 | ||
| Knowledge Base Question Answering | WebQSP | 53 | Jun 2, 2026 | ||
| Classification | credit-g | 53 | Jul 7, 2026 | ||
| Bird's Eye View Object Detection | KITTI (test) | 53 | Feb 26, 2026 | ||
| Medical Image Segmentation | MMWHS | 53 | Jul 7, 2026 | ||
| Clustering | Wine | 53 | Jun 25, 2026 | ||
| Depth Completion | KITTI | 53 | May 29, 2026 | ||
| RGBT Tracking | RGBT 234 | 53 | Feb 26, 2026 | ||
| Link Prediction | ogbl-collab | 53 | May 25, 2026 | ||
| Text-to-image | MS-COCO 1k (test) | 53 | Feb 26, 2026 | ||
| Hand Pose Estimation | HO-3D (test) | 53 | Feb 26, 2026 | ||
| Image Generation | ImageNet 256x256 (test val) | 53 | Jun 5, 2026 | ||
| Chinese Spelling Check | SIGHAN15 (test) | 53 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | Textures (test) | 53 | Apr 13, 2026 | ||
| Image Harmonization | iHarmony4 (all) | 53 | Feb 26, 2026 | ||
| Confidence calibration | CIFAR-100-LT (test) | 53 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 (test) | 53 | Feb 26, 2026 | ||
| Open Information Extraction | CaRB (test) | 53 | Feb 26, 2026 | ||
| Open Set Domain Adaptation | Office-Home | 53 | May 8, 2026 |