Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 363 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Speech Recognition | VoxPopuli (test) | 52 | Apr 21, 2026 | ||
| Link Prediction | Photo | 52 | Jun 11, 2026 | ||
| Deepfake Detection | FaceForensics++ c23 (test) | 52 | May 12, 2026 | ||
| Node classification | ogbn-arxiv v1 (test) | 52 | Feb 26, 2026 | ||
| Regression | California Housing (CH) (test) | 52 | Feb 26, 2026 | ||
| Question Answering | Natural Questions | 52 | Feb 27, 2026 | ||
| Time Series Classification | SpokenArabicDigits | 52 | Mar 13, 2026 | ||
| Time Series Classification | JapaneseVowels | 52 | Mar 13, 2026 | ||
| Classification | pima | 52 | Apr 10, 2026 | ||
| Natural Language Inference | MNLI (test) | 52 | Apr 21, 2026 | ||
| Generic Event Boundary Detection | Kinetics-GEBD (val) | 52 | Jun 4, 2026 | ||
| Word-in-Context Classification | WiC | 52 | Apr 14, 2026 | ||
| Entity Typing | FewNERD (test) | 52 | Feb 26, 2026 | ||
| Multimodal Machine Translation (English-German) | Multi30K 2016 (test) | 52 | Feb 26, 2026 | ||
| Relation Extraction | CONLL04 | 52 | Apr 3, 2026 | ||
| Image Deraining | Rain100H | 52 | Feb 26, 2026 | ||
| Natural language inference | RTE (test) | 52 | Feb 26, 2026 | ||
| Emotion Recognition | ER | 52 | Jun 19, 2026 | ||
| Image Classification | ImageNet-Sketch (val) | 52 | Feb 27, 2026 | ||
| Facial Expression Recognition | SFEW 2.0 | 52 | May 7, 2026 | ||
| Calibration | CIFAR-10H | 52 | Feb 26, 2026 | ||
| Trajectory Prediction | ETH-UCY Average (test) | 52 | Feb 26, 2026 | ||
| Bird's Eye View (BEV) Detection | KITTI Cars (IoU3D ≥ 0.7) (test) | 52 | Feb 26, 2026 | ||
| Object Detection | CrowdHuman (val) | 52 | Feb 26, 2026 | ||
| Facial Landmark Detection | 300W | 52 | Feb 26, 2026 |