Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 616 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| OOD Detection | OpenImage-O OOD on ImageNet-1K | 37 | May 15, 2026 | ||
| Video Temporal Grounding | QVHighlights (val) | 37 | May 6, 2026 | ||
| Survival Prediction | TCGA-KIRP (5-fold CV) | 37 | Mar 18, 2026 | ||
| Visual Question Answering | VQAT | 37 | Jul 1, 2026 | ||
| 3D Point Cloud Classification | ModelNet40-C (test) | 37 | Jun 12, 2026 | ||
| Interactive Motion Synthesis | InterHuman (test) | 37 | Mar 31, 2026 | ||
| Synthetic image detection | Glide 50-27 | 37 | May 1, 2026 | ||
| Semantic Segmentation | ADE-20k A-847 (test) | 37 | Feb 26, 2026 | ||
| Text-to-Speech | LibriTTS clean (test) | 37 | Jun 23, 2026 | ||
| Clustering | Yale | 37 | Mar 17, 2026 | ||
| Shape Matching | SHREC19 remeshed (test) | 37 | Feb 26, 2026 | ||
| Anomaly Detection | SMAP (test) | 37 | Jul 1, 2026 | ||
| Clustering | MNIST | 37 | Feb 26, 2026 | ||
| Long-form Question Answering with Citations | ASQA | 37 | Feb 26, 2026 | ||
| 3D Classification | ScanObjectNN OBJ-BG official | 37 | Apr 20, 2026 | ||
| Dynamic link prediction | Contact | 37 | Apr 14, 2026 | ||
| Dynamic link prediction | UN Vote | 37 | Apr 14, 2026 | ||
| Dynamic link prediction | UN Trade | 37 | Apr 14, 2026 | ||
| Dynamic link prediction | US Legislature | 37 | Apr 14, 2026 | ||
| Sentiment Analysis | Financial Phrasebank | 37 | Feb 26, 2026 | ||
| Temporal Sentence Grounding | TACoS (test) | 37 | Jun 2, 2026 | ||
| Object Detection | PASCAL VOC 2007 (test) | 37 | Apr 21, 2026 | ||
| Metric Depth Estimation | iBIMS-1 | 37 | Jun 1, 2026 | ||
| Text Recognition | IIIT, SVT, IC13, IC15, SVTP, CT | 37 | Feb 26, 2026 | ||
| Shape Classification | ScanObjectNN | 37 | Jun 2, 2026 |