Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 863 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Visual Question Answering | GQA | 30 | Mar 4, 2026 | ||
| Continual Learning | Stanford Cars | 30 | May 12, 2026 | ||
| Causal Structure Learning | Gumbel synthetic dataset | 30 | Feb 27, 2026 | ||
| Model Inversion Attack | CelebA (test) | 30 | Jun 23, 2026 | ||
| Neural Network Verification | MNIST 1000 images | 30 | Feb 27, 2026 | ||
| Semantic Segmentation | NYU v2 | 30 | Jun 2, 2026 | ||
| Automatic Speech Recognition | Voicebank+Demand | 30 | Feb 26, 2026 | ||
| Visual Question Answering | TextVQA (test val) | 30 | Apr 14, 2026 | ||
| Traffic Forecasting | PEMS-03 Long-term (24 -> 24avg) | 30 | Feb 27, 2026 | ||
| Traffic Forecasting | PEMS-03 Short-term (12 -> 12avg) | 30 | Feb 27, 2026 | ||
| Code Safety Evaluation | APPS 1.0 (test) | 30 | Feb 26, 2026 | ||
| Multi-task Image Classification | 20-task Model Merging Benchmark (14-task + EMNIST, CIFAR10, Food101, FashionMNIST, RenderedSST2, KMNIST) | 30 | Feb 26, 2026 | ||
| Multiple Instance Learning | TCGA-ESCA | 30 | Feb 26, 2026 | ||
| Multiple Instance Learning | TCGA-BRCA | 30 | Feb 26, 2026 | ||
| Multi-class Classification | BRACS | 30 | Feb 26, 2026 | ||
| Evaluation | Overall Performance | 30 | Mar 4, 2026 | ||
| 3D scene reconstruction | DeepBlending | 30 | Feb 26, 2026 | ||
| OOD detection | MVTec Metal Nut - Similar artifacts (test) | 30 | Feb 27, 2026 | ||
| OOD Detection | ISIC Colour Chart Artefacts (Similar) (test) | 30 | Feb 27, 2026 | ||
| OOD detection | ISIC Colour Chart Artefacts Similar | 30 | Feb 27, 2026 | ||
| OOD Detection | ISIC Ink Artefacts Similar (test) | 30 | Feb 27, 2026 | ||
| Multi-Hop Question Answering | HotpotQA | 30 | Mar 11, 2026 | ||
| Image Classification | Tiny-ImageNet Dir-0.1 | 30 | Mar 13, 2026 | ||
| Image Classification | Tiny-ImageNet Dir-0.5 | 30 | Mar 13, 2026 | ||
| Automatic Speech Recognition | CHiME3 Mixed | 30 | Feb 26, 2026 |