Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 571 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Winograd Schema Challenge | WinoGrande | 39 | May 8, 2026 | ||
| Federated Backdoor Defense | CIFAR-10 | 39 | May 7, 2026 | ||
| Membership Inference Attack | newsQA | 39 | May 7, 2026 | ||
| Membership Inference Attack | SQuAD | 39 | May 7, 2026 | ||
| Object Manipulation | OGBench cube play (Double) | 39 | Jun 9, 2026 | ||
| Hallucination Detection | CoQA | 39 | May 27, 2026 | ||
| Code Generation | LiveCodeBench v5 | 39 | Jun 9, 2026 | ||
| Math Reasoning | MATH 500 | 39 | Apr 29, 2026 | ||
| Anomaly Localization | Eyecandies | 39 | Jul 8, 2026 | ||
| Imaging Platform Classification | Street View Imagery | 39 | Apr 23, 2026 | ||
| View Direction Classification | Street View Imagery | 39 | Apr 23, 2026 | ||
| Human Perception Regression | Street View Imagery | 39 | Apr 23, 2026 | ||
| Socio-economic Indicator Regression | Street View Imagery | 39 | Apr 23, 2026 | ||
| Cultural Visual Question Answering | CVQA (eval) | 39 | Apr 21, 2026 | ||
| Task Addition | 8 classification datasets (Cars, DTD, EuroSAT, GTSRB, MNIST, RESISC45, SUN397, SVHN) (test) | 39 | Jun 24, 2026 | ||
| Tool Selection | MetaTool | 39 | May 26, 2026 | ||
| Math | MATH500 | 39 | May 19, 2026 | ||
| Multiple-choice audio understanding | MMAU mini (test) | 39 | Jun 8, 2026 | ||
| Genomic sequence modeling | Nucleotide Transformer (NT) 2.5B multi-species | 39 | Apr 16, 2026 | ||
| Open-ended Evaluation | BQD | 39 | Apr 15, 2026 | ||
| Multi-choice Evaluation | BQD | 39 | Apr 15, 2026 | ||
| Preference Evaluation | VCD | 39 | Apr 15, 2026 | ||
| Node classification | Instagram (test) | 39 | May 12, 2026 | ||
| Question Answering | MetaQA 3-hop | 39 | Apr 24, 2026 | ||
| Question Answering | MetaQA 2-hop | 39 | Apr 24, 2026 |