Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 575 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Time Series Classification | HAR | 39 | Feb 26, 2026 | ||
| Text Rendering | LongText-Bench English | 39 | Jun 17, 2026 | ||
| Class-Incremental Learning | CUB (B0 Inc10) | 39 | Apr 14, 2026 | ||
| 60 min. forecasting | Rotterdam (test) | 39 | Feb 26, 2026 | ||
| Time Series Classification | 128 UCR datasets | 39 | May 22, 2026 | ||
| Classification | BreastMNIST | 39 | Apr 3, 2026 | ||
| Code Generation | HumanEval | 39 | Mar 16, 2026 | ||
| Image Classification | PACS (leave-one-domain-out) | 39 | Jun 19, 2026 | ||
| Surgical phase recognition | MultiBypass140 | 39 | Mar 16, 2026 | ||
| GUI Grounding | Screenspot v1 | 39 | Mar 30, 2026 | ||
| Jailbreak Mitigation and Utility Evaluation | LLM Safety and Utility Evaluation Suite (StrongReject, AdvBench, IFeval, MMLU) (test) | 39 | Feb 26, 2026 | ||
| Point Cloud Lossless Attribute Compression | MPEG CAT1 Scant | 39 | Feb 26, 2026 | ||
| Point Cloud Lossless Attribute Compression | MPEG CAT1 Dense | 39 | Feb 26, 2026 | ||
| Multi-Agent Rearrangement | Multi-agent Non-monotone Rearrangement Environment (test) | 39 | Feb 26, 2026 | ||
| Class-Incremental Learning | CIFAR-10 Sequential | 39 | Feb 26, 2026 | ||
| Task-Incremental Learning | CIFAR10 Sequential | 39 | Feb 26, 2026 | ||
| Multivariate Time Series Classification | UEA 30% missing rate (test) | 39 | Apr 3, 2026 | ||
| Question Answering | HotpotQA (test) | 39 | Feb 26, 2026 | ||
| Cross-domain image retrieval | Office-Home R→A (test) | 39 | Feb 26, 2026 | ||
| Cross-domain image retrieval | Office-Home C→R (test) | 39 | Feb 26, 2026 | ||
| Cross-domain image retrieval | Office-Home P→R (test) | 39 | Feb 26, 2026 | ||
| Single-class unlearning | MNIST | 39 | Jun 24, 2026 | ||
| Planning | PushT | 39 | Jun 9, 2026 | ||
| Multi-view Clustering | ProteinFold | 39 | Feb 26, 2026 | ||
| Multi-view Clustering | DHA | 39 | Feb 26, 2026 |