Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1145 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Instance Segmentation | OCHuman (val) | 25 | Feb 26, 2026 | ||
| Reinforcement Learning | CartPole v1 (test) | 25 | Feb 26, 2026 | ||
| Action Localization | AVA 2.2 | 25 | Feb 26, 2026 | ||
| Single Object Video Segmentation | FBMS-59 | 25 | Feb 26, 2026 | ||
| Untargeted Point Cloud Attack | Bosphorus, Eurecom, and SIAT-3DFE (test) | 25 | Feb 26, 2026 | ||
| Targeted Attack | 3D Face Dataset | 25 | Feb 26, 2026 | ||
| Object Detection | COCO | 25 | Mar 10, 2026 | ||
| Hyper-relational extraction | HyperRED (dev) | 25 | Feb 26, 2026 | ||
| Video Deblurring | GoPro | 25 | Mar 17, 2026 | ||
| Visual Question Answering | VQA v1 | 25 | Mar 10, 2026 | ||
| Offline Reinforcement Learning | D4RL halfcheetah-full-replay v2 | 25 | Jun 2, 2026 | ||
| Regularized Linear Regression | YearPredictionMSD (train) | 25 | Feb 26, 2026 | ||
| Image Generation | CIFAR-10 | 25 | Feb 26, 2026 | ||
| Temporal relation classification | TB-DENSE | 25 | Feb 26, 2026 | ||
| Aspect-level sentiment analysis | Rest 14 | 25 | Feb 26, 2026 | ||
| Information Retrieval | TREC DL | 25 | May 29, 2026 | ||
| Action Classification | Kinetics-400 v1 (val) | 25 | Feb 26, 2026 | ||
| Text-to-Image Retrieval | MSCOCO (test) | 25 | Feb 26, 2026 | ||
| Regression | Year | 25 | Feb 26, 2026 | ||
| Binary Classification | MIMIC 2 | 25 | Feb 26, 2026 | ||
| Multi-label Classification | sub-MNIST (test) | 25 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Walker-medium-replay v2 | 25 | Feb 26, 2026 | ||
| Reading Comprehension | ReCoRD | 25 | Jun 29, 2026 | ||
| Verified Robustness | MNIST (test) | 25 | Feb 26, 2026 | ||
| RGB-D Saliency Detection | DUTLF-Depth | 25 | Feb 26, 2026 |