Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1743 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Anomaly Localization | TN3K | 19 | Mar 23, 2026 | ||
| Anomaly Localization | KSDD | 19 | Feb 27, 2026 | ||
| Semantic Segmentation | UltrasoundNerveMSBench | 19 | Feb 26, 2026 | ||
| Semantic Segmentation | USforKidneyMSBench | 19 | Feb 26, 2026 | ||
| Semantic Segmentation | Promise12 MSBench | 19 | Feb 26, 2026 | ||
| Semantic Segmentation | PandentalMSBench | 19 | Feb 26, 2026 | ||
| Medical Image Segmentation | MosMedPlus MSBench | 19 | Feb 26, 2026 | ||
| Medical Image Segmentation | FHPsAOPMSBench | 19 | Feb 26, 2026 | ||
| Medical Image Segmentation | CovidQUExMSBench | 19 | Feb 26, 2026 | ||
| Medical Image Segmentation | BusiMSBench | 19 | Feb 26, 2026 | ||
| Visual Reasoning | GQA (test-dev) | 19 | Feb 26, 2026 | ||
| Class-incremental learning | DomainNet 10-split | 19 | Feb 26, 2026 | ||
| Aggregate Model Performance | LLaVA Benchmarks Aggregate | 19 | Feb 27, 2026 | ||
| Mobile GUI Agent Task | AndroidLab | 19 | Feb 26, 2026 | ||
| Spatial Reasoning | VSI-Bench Vanilla regime | 19 | Feb 26, 2026 | ||
| Open-Vocabulary Segmentation | Vaihingen (test) | 19 | May 6, 2026 | ||
| Open-Vocabulary Segmentation | Potsdam (test) | 19 | May 6, 2026 | ||
| Open-Vocabulary Segmentation | LoveDA (test) | 19 | May 6, 2026 | ||
| Video Knowledge Acquisition | Video-MMLU | 19 | Feb 26, 2026 | ||
| Long-context Question Answering | MuSiQue | 19 | Apr 10, 2026 | ||
| Robotic Manipulation | RoboTwin | 19 | Jul 9, 2026 | ||
| Remote Sensing Visual Question Answering | RSVQA low-resolution | 19 | Feb 26, 2026 | ||
| Super-Resolution | Urban100 | 19 | Feb 26, 2026 | ||
| Super-Resolution | BSD100 | 19 | Feb 26, 2026 | ||
| Super-Resolution | StreamSR | 19 | Feb 26, 2026 |