Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 117 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Molecular property prediction | BACE | 107 | Jul 7, 2026 | ||
| 3D Object Detection | SUN RGB-D | 107 | Jun 2, 2026 | ||
| Adversarial Attack | ImageNet (test) | 107 | May 22, 2026 | ||
| Video Object Segmentation | DAVIS 2017 (test) | 107 | Feb 26, 2026 | ||
| Super-Resolution | RealSR (test) | 107 | Jun 30, 2026 | ||
| Semantic Segmentation | PASCAL-5^i (test) | 107 | Feb 26, 2026 | ||
| Out-of-distribution Detection | CIFAR-100 | 107 | Feb 26, 2026 | ||
| Single Image Reflection Removal | Real20 (test) | 107 | Jul 1, 2026 | ||
| Image Denoising | Set12 (test) | 107 | May 7, 2026 | ||
| JPEG image artifacts removal | LIVE1 | 107 | Jun 26, 2026 | ||
| Molecular Property Prediction | MoleculeNet MUV (scaffold) | 107 | Jun 25, 2026 | ||
| Handwritten Mathematical Expression Recognition | CROHME 2019 (test) | 107 | Feb 26, 2026 | ||
| Zero-shot Reasoning | WinoGrande | 107 | Jun 4, 2026 | ||
| Text-based Visual Question Answering | TextVQA | 106 | Jul 1, 2026 | ||
| Time Series Forecasting | ETTh2 | 106 | Jun 16, 2026 | ||
| Commonsense Reasoning | HellaSwag | 106 | Jul 8, 2026 | ||
| Manim Animation Generation | ManimBench | 106 | Apr 21, 2026 | ||
| Arithmetic Reasoning | Arithmetics | 106 | Apr 15, 2026 | ||
| Embodied Task Completion | ALFWorld | 106 | Jun 4, 2026 | ||
| Visual Question Answering | COCO | 106 | Apr 15, 2026 | ||
| Time Series Forecasting | Solar | 106 | May 21, 2026 | ||
| Emotional Intelligence | Polish EQ-Bench | 106 | Apr 14, 2026 | ||
| Logical Reasoning | LogiQA | 106 | Jun 17, 2026 | ||
| Image Generation | ImageNet 1K (val) | 106 | May 26, 2026 | ||
| Mathematical Reasoning | MATH 500 | 106 | Feb 26, 2026 |