Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1272 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Reading Comprehension | Lambada | 24 | Mar 6, 2026 | ||
| Long-document summarization | ArXiv (test) | 24 | Feb 26, 2026 | ||
| Mathematical Reasoning | MMLU Mathematics (test) | 24 | Mar 6, 2026 | ||
| Question Answering | FriendsQA (test) | 24 | Feb 26, 2026 | ||
| Deepfake Detection | FaceForensics++ c40 (test) | 24 | May 15, 2026 | ||
| Image Classification | ImageNet-C | 24 | Mar 4, 2026 | ||
| Sentence-level Relation Extraction | SemEval (test) | 24 | Feb 26, 2026 | ||
| Text reconstruction from gradients | SST-2 | 24 | Mar 18, 2026 | ||
| Text reconstruction from gradients | CoLA | 24 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 (test) | 24 | Feb 26, 2026 | ||
| Pan-sharpening | GaoFen2 real-world full-resolution | 24 | Feb 26, 2026 | ||
| Pan-sharpening | WorldView III (test) | 24 | Feb 26, 2026 | ||
| Multi-Label Classification | MS-COCO (test) | 24 | Feb 26, 2026 | ||
| Few-shot Segmentation | BCV Liver (in-domain) | 24 | Feb 26, 2026 | ||
| Classification | Adult Income 1996 (train and test) | 24 | Feb 26, 2026 | ||
| Node Classification | Cora | 24 | Feb 26, 2026 | ||
| Shape Matching | DT4D-H inter-class (test) | 24 | Mar 20, 2026 | ||
| Regression | RCF-MNIST | 24 | Feb 26, 2026 | ||
| Causal discovery | Synthetic Gaussian IL2H | 24 | Feb 26, 2026 | ||
| Latent Hierarchical Causal Structure Discovery | Synthetic Gaussian IL2H Structure | 24 | Feb 26, 2026 | ||
| Estimating data collection requirements | BDD100K Semi-supervised | 24 | Feb 26, 2026 | ||
| Estimating data collection requirements | CIFAR-100 2 Types | 24 | Feb 26, 2026 | ||
| Control | Beta Tracking | 24 | Feb 26, 2026 | ||
| Named Entity Recognition | I2B2 2010 (test) | 24 | Feb 26, 2026 | ||
| 4x Video Super-Resolution | REDS4 (test) | 24 | Feb 26, 2026 |