Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1334 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Classification | TREC | 23 | Feb 26, 2026 | ||
| Sentiment Analysis | SST5 | 23 | Feb 26, 2026 | ||
| Sentiment Analysis | SST2 | 23 | Feb 26, 2026 | ||
| Sentiment Analysis | MR | 23 | Feb 26, 2026 | ||
| Citation Intent Classification | SCICITE | 23 | Feb 26, 2026 | ||
| Image Denoising | SIDD 1 (val) | 23 | Feb 26, 2026 | ||
| Machine Translation | De-En (test) | 23 | Feb 26, 2026 | ||
| Image Classification | Sketches | 23 | Feb 26, 2026 | ||
| Information Retrieval | NaturalQuestions (NQ) (test) | 23 | Feb 26, 2026 | ||
| Dialog State Tracking | SGD 15 tasks CL | 23 | Feb 26, 2026 | ||
| Image-to-image translation | Horse -> Zebra | 23 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | Human3.6M (S5, S6, S7, S8) | 23 | Feb 26, 2026 | ||
| Relation Extraction | TACRED Original (test) | 23 | Feb 26, 2026 | ||
| Object Detection | PASCAL VOC + COCO-20 2007 (test) | 23 | Feb 26, 2026 | ||
| Audio Classification | AudioSet Full (test) | 23 | Feb 26, 2026 | ||
| Face Recognition | MegaFace | 23 | Feb 26, 2026 | ||
| Multi-view Depth Estimation | ScanNet (test) | 23 | Feb 26, 2026 | ||
| Node Classification | Wisconsin standard (test) | 23 | Feb 26, 2026 | ||
| Node Classification | Texas standard (test) | 23 | Feb 26, 2026 | ||
| Image Generation | LSUN Churches 256x256 | 23 | Mar 4, 2026 | ||
| Image Classification | CIFAR10 Clean | 23 | Jun 23, 2026 | ||
| Offline Reinforcement Learning | D4RL mujoco-hopper (med-replay) | 23 | Feb 26, 2026 | ||
| Panoptic Segmentation | COCO (test) | 23 | Feb 26, 2026 | ||
| Question Answering | HybridQA (test) | 23 | Feb 26, 2026 | ||
| Isolated Sign Language Recognition | MSASL200 | 23 | Feb 26, 2026 |