Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2027 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Binary Classification | Pendigits UCI (test) | 17 | Mar 23, 2026 | ||
| Binary Classification | Optdigits UCI (test) | 17 | Mar 23, 2026 | ||
| Open-Vocabulary Semantic Segmentation | PASCAL Context 459 (val) | 17 | Mar 23, 2026 | ||
| Open-Vocabulary Semantic Segmentation | ADE20K 847 (val) | 17 | Mar 23, 2026 | ||
| Disorder Diagnosis (HC vs. MDD) | U center | 17 | Mar 23, 2026 | ||
| Disorder Diagnosis (HC vs. BD) | U center | 17 | Mar 23, 2026 | ||
| Disorder Diagnosis (HC vs. ASD) | ABIDE (NYU site) | 17 | Mar 23, 2026 | ||
| Classification | Single-site clinical dataset HC vs. MDD | 17 | Mar 23, 2026 | ||
| Classification | Single-site clinical dataset HC vs. BD | 17 | Mar 23, 2026 | ||
| Identity-Preserving Video Generation | OpenS2V (test) | 17 | Mar 23, 2026 | ||
| E-voting system evaluation | Analyzed E-Voting Systems | 17 | Mar 23, 2026 | ||
| Maturity Evaluation | Internet Voting Systems Protocols | 17 | Mar 23, 2026 | ||
| Information Retrieval | Natural Questions BEIR | 17 | Mar 20, 2026 | ||
| Information Retrieval | MS MARCO BEIR | 17 | Mar 20, 2026 | ||
| Information Retrieval | ClimateFEVER BEIR | 17 | Mar 20, 2026 | ||
| Information Retrieval | Touche BEIR 2020 | 17 | Mar 20, 2026 | ||
| Visual Counting | CountBenchQA | 17 | Apr 7, 2026 | ||
| Utility Evaluation | NQ-Open | 17 | Mar 20, 2026 | ||
| Utility Evaluation | MMLU | 17 | Mar 20, 2026 | ||
| Scientific Chart Interpretation | CharXiv Reasoning | 17 | Jun 23, 2026 | ||
| Multi-Hop QA | 2Wiki | 17 | Mar 20, 2026 | ||
| Single-Hop QA | NQ | 17 | Mar 20, 2026 | ||
| Layout-to-image generation | LayoutSAM Eval | 17 | Jul 1, 2026 | ||
| Gradient Inversion Attack | ImageNet | 17 | Mar 19, 2026 | ||
| Direct Recommendation | Amazon Sports 5-core filtering (leave-one-out) | 17 | Mar 19, 2026 |