Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1513 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semi-supervised graph classification | RDT-M5K (10-fold cross-validation) | 21 | Feb 26, 2026 | ||
| Semi-supervised graph classification | RDT-B (10-fold cross-validation) | 21 | Feb 26, 2026 | ||
| Semi-supervised graph classification | COLLAB (10-fold cross-validation) | 21 | Feb 26, 2026 | ||
| Semi-supervised graph classification | NCI1 (10-fold cross-validation) | 21 | Feb 26, 2026 | ||
| Semi-supervised graph classification | DD (10-fold cross-validation) | 21 | Feb 26, 2026 | ||
| Semi-supervised graph classification | PROTEINS (10-fold cross-validation) | 21 | Feb 26, 2026 | ||
| Time-series Generation | Sines | 21 | Feb 26, 2026 | ||
| Visual Question Answering | VQA Karpathy (test) | 21 | Feb 26, 2026 | ||
| Referring Expression Comprehension | RefGTA (test) | 21 | Feb 26, 2026 | ||
| Referring Expression Comprehension | RefGTA (val) | 21 | Feb 26, 2026 | ||
| Multiple Choice Question Answering | QASC (test) | 21 | Apr 2, 2026 | ||
| SMS Spam Classification | SMS Spam | 21 | Jun 26, 2026 | ||
| Image Classification | CIFAR-10-LT Imbalance Ratio 10 (test) | 21 | Feb 26, 2026 | ||
| Natural Language Inference | RTE | 21 | Feb 26, 2026 | ||
| Few-shot Action Recognition | HMDB51 meta (test) | 21 | Feb 26, 2026 | ||
| Point Cloud Classification | ScanObjectNN Object & Background 1.0 | 21 | Feb 26, 2026 | ||
| Online Continual Learning | TinyImageNet Sequential (test) | 21 | Feb 26, 2026 | ||
| Online Continual Learning | CIFAR-100 Sequential (test) | 21 | Feb 26, 2026 | ||
| Online Continual Learning | CIFAR-10 Sequential (test) | 21 | Feb 26, 2026 | ||
| Reconstruction | Replica average over 8 scenes | 21 | Feb 26, 2026 | ||
| Graph Explanation | Mutag | 21 | May 15, 2026 | ||
| Image Classification | fMoW | 21 | Mar 25, 2026 | ||
| Text-to-Image Generation | MS-COCO Captions 30,000 (val) | 21 | Feb 26, 2026 | ||
| Text-based position localization | KITTI360 Pose (test) | 21 | Apr 3, 2026 | ||
| Overall Audio-Visual Question Answering | MUSIC-AVQA (test) | 21 | Feb 26, 2026 |