Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1767 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Point Cloud Completion | ShapeNet-ViPC Novel categories | 19 | Jul 7, 2026 | ||
| Binary Classification | Epsilon (test) | 19 | Feb 26, 2026 | ||
| Few-shot segmentation | COCO-20ⁱ (S0, S1, S2, S3, Mean) | 19 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 (test) | 19 | Mar 6, 2026 | ||
| Text-to-Music Generation | MusicCaps | 19 | Jun 12, 2026 | ||
| Out-of-Distribution Detection | CIFAR-10 | 19 | Feb 26, 2026 | ||
| Long-form Transcription | Rev 16 | 19 | Feb 26, 2026 | ||
| Long-form Transcription | Kincaid46 | 19 | Feb 26, 2026 | ||
| Long-form Transcription | Meanwhile | 19 | Feb 26, 2026 | ||
| Long-form Transcription | TED-LIUM3 | 19 | Feb 26, 2026 | ||
| Metal Artifact Reduction | DeepLesion synthesized (Medium Metal) | 19 | Feb 26, 2026 | ||
| Text-to-Video Retrieval | Something-to-Something Template v2 | 19 | Feb 26, 2026 | ||
| Sleep Stage Classification | Sleep-EDF SC 20 | 19 | Feb 26, 2026 | ||
| 3D Object Detection | KITTI Pedestrian official (test) | 19 | Feb 26, 2026 | ||
| Speech Emotion Recognition | IEMOCAP Speaker-independent 5-fold cross-validation | 19 | Feb 26, 2026 | ||
| Hammer | Adroit Hammer Cloned v0 | 19 | Feb 26, 2026 | ||
| Pen | Adroit Pen v0 (Cloned) | 19 | Feb 26, 2026 | ||
| Hammer | Adroit Hammer Human v0 | 19 | Feb 26, 2026 | ||
| Pen | Adroit Pen Human v0 | 19 | Feb 26, 2026 | ||
| Question Answering | AdversarialQA (val) | 19 | Feb 26, 2026 | ||
| Relation Extraction | TACRED v1.0 (5% train) | 19 | Feb 26, 2026 | ||
| Object Detection | N-Caltech101 | 19 | Jun 19, 2026 | ||
| Person Re-identification | Celeb-reID light | 19 | Jun 11, 2026 | ||
| Answer Sentence Selection | WQA (test) | 19 | Feb 27, 2026 | ||
| Positive-Unlabeled Classification | CIFAR-10 (test) | 19 | Feb 26, 2026 |