Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 246 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Relation Extraction | DocRED v1 (test) | 66 | Feb 26, 2026 | ||
| 3D Pose Estimation | Human3.6M | 66 | Feb 26, 2026 | ||
| Multi-Object Tracking | KITTI (test) | 66 | Jun 23, 2026 | ||
| Text-to-Video Retrieval | YouCook2 (val) | 66 | Feb 27, 2026 | ||
| Optical Flow | KITTI 2012 (test) | 66 | Apr 14, 2026 | ||
| Scene Text Recognition | IC13 | 66 | Feb 27, 2026 | ||
| Face Alignment | 300-W (Full) | 66 | Feb 26, 2026 | ||
| Semantic Image Synthesis | ADE20K | 66 | Feb 27, 2026 | ||
| Crowd Counting | UCF_CC_50 (test) | 66 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO 2017 (val) | 66 | Apr 1, 2026 | ||
| Deepfake Detection | FakeAVCeleb (test) | 66 | May 1, 2026 | ||
| Node Classification | Cora 3% label rate | 66 | Mar 4, 2026 | ||
| Visual Question Answering (Multiple-choice) | VQA 1.0 (test-dev) | 66 | Feb 26, 2026 | ||
| Person Re-identification | PRID2011 | 66 | Feb 26, 2026 | ||
| Image Classification | SVHN to MNIST (test) | 66 | Feb 26, 2026 | ||
| Point Cloud Registration | 3DLoMatch Indoor (test) | 66 | Feb 26, 2026 | ||
| Image Captioning Evaluation | Pascal-50S (test) | 66 | Feb 26, 2026 | ||
| Few-shot classification | Omniglot | 66 | May 26, 2026 | ||
| Molecular Property Prediction | MoleculeNet HIV (scaffold) | 66 | Feb 26, 2026 | ||
| Retrosynthesis prediction | USPTO-FULL (test) | 66 | Jun 16, 2026 | ||
| Audio Captioning | AudioCaps | 66 | May 26, 2026 | ||
| Automatic Speech Recognition | AISHELL-1 (dev) | 66 | Jun 18, 2026 | ||
| 3D Anomaly Detection | Real3D-AD | 66 | May 8, 2026 | ||
| Mathematical Reasoning | MathVista (test) | 66 | Jun 1, 2026 | ||
| 3D Human Pose Estimation | Campus (test) | 66 | Feb 26, 2026 |