Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2322 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| kNN | Random | 16 | Feb 26, 2026 | ||
| Medical Image Segmentation | ETIS (test) | 16 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL Gym | 16 | Mar 25, 2026 | ||
| 3D Human Pose Prediction | Human3.6M | 16 | Feb 26, 2026 | ||
| Graph Classification | MNIST-75SP (test) | 16 | Feb 26, 2026 | ||
| Binary Classification | UCI Waveform (test) | 16 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100N Fine | 16 | Feb 26, 2026 | ||
| Textual Style Transfer | English Detoxification Dataset | 16 | Feb 26, 2026 | ||
| Textual Style Transfer | Russian Detoxification Dataset | 16 | Feb 26, 2026 | ||
| Image Manipulation Detection | General Inference Speed Evaluation Images | 16 | Feb 27, 2026 | ||
| Image Classification | STL10 (Nl=150, M=100k, γl=10) long-tailed (test) | 16 | Feb 26, 2026 | ||
| Image Classification | CIFAR100 long-tailed (Nl=150, Ml=2000, γl=γu=10) (test) | 16 | Feb 26, 2026 | ||
| Image Classification | CIFAR100 (Nl=50, Ml=400, γl=γu=10) long-tailed (test) | 16 | Feb 26, 2026 | ||
| Image Classification | CIFAR10-LT (Nl=1500, Ml=3000, γl=γu=100) (test) | 16 | Feb 26, 2026 | ||
| Depth-aware Panoptic Segmentation | Cityscapes-DPS (val) | 16 | Feb 26, 2026 | ||
| Novel View Synthesis | Trevi Fountain Phototourism (test) | 16 | Feb 26, 2026 | ||
| Novel View Synthesis | Sacre Coeur Phototourism (test) | 16 | Feb 26, 2026 | ||
| Summarization | Vietnews (test) | 16 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100-LT gamma=20 (test) | 16 | Feb 26, 2026 | ||
| Instance Matting | HIM2K Natural | 16 | Feb 26, 2026 | ||
| Instance Matting | HIM2K Synthetic | 16 | Feb 26, 2026 | ||
| Spatial-Temporal Video Super-Resolution | Vimeo90K x4 | 16 | Feb 26, 2026 | ||
| Spatial-Temporal Video Super-Resolution | UCF101 x4 | 16 | Feb 26, 2026 | ||
| En-De Chat Translation | BConTrasT (test) | 16 | Feb 26, 2026 | ||
| Continual Model Refinement for Extractive Question Answering | MRQA streams (val) | 16 | Feb 26, 2026 |