Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 3 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | GSM8K (test) | 954 | May 28, 2026 | ||
| Node classification | Cora (test) | 951 | May 19, 2026 | ||
| Image Classification | ImageNet 1k (test) | 939 | Jul 2, 2026 | ||
| Node Classification | Chameleon | 936 | Jun 25, 2026 | ||
| 3D Object Detection | nuScenes (test) | 924 | Jun 16, 2026 | ||
| Mathematical Reasoning | MATH500 (test) | 922 | Jul 8, 2026 | ||
| Science Question Answering | ScienceQA | 916 | Jun 26, 2026 | ||
| Text-to-Image Generation | GenEval | 914 | Jul 9, 2026 | ||
| Multivariate Forecasting | ETTh1 | 909 | Jun 11, 2026 | ||
| Language Modeling | C4 (val) | 908 | Jul 3, 2026 | ||
| Image Classification | CIFAR-10 (test) | 906 | Feb 26, 2026 | ||
| Question Answering | ARC Challenge | 906 | Apr 2, 2026 | ||
| Node Classification | Pubmed | 902 | Jun 23, 2026 | ||
| Multimodal Evaluation | MME | 902 | Jul 3, 2026 | ||
| Node Classification | Cornell | 900 | Jun 19, 2026 | ||
| Node Classification | Wisconsin | 898 | Jun 11, 2026 | ||
| Commonsense Reasoning | HellaSwag | 897 | Jun 29, 2026 | ||
| Image Classification | MNIST (test) | 894 | Mar 12, 2026 | ||
| Multimodal Understanding | MMBench | 887 | Jun 30, 2026 | ||
| Composed Image Retrieval | CIRR (test) | 887 | Jul 7, 2026 | ||
| Mathematical Reasoning | MATH | 882 | Apr 14, 2026 | ||
| Multi-task Language Understanding | MMLU | 881 | Apr 21, 2026 | ||
| Image Super-Resolution | Manga109 | 875 | May 26, 2026 | ||
| Image Classification | ImageNet-1K (val) | 871 | Jun 11, 2026 | ||
| Time Series Forecasting | ETTh1 | 869 | Jun 24, 2026 |