Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2169 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Graph Reasoning | G-Real | 16 | May 12, 2026 | ||
| Graph Reasoning | NLGraph | 16 | May 12, 2026 | ||
| Novel View Synthesis | D-NeRF Lego | 16 | May 12, 2026 | ||
| Mobile UI Task Automation | AndroidWorld (full) | 16 | May 12, 2026 | ||
| Time Series Forecasting | M4 Competition (test) | 16 | May 12, 2026 | ||
| Joint Demosaicking and Video Frame Interpolation | Proposed Polarization Video Benchmark 1.0 (test) | 16 | May 12, 2026 | ||
| Tabular Anomaly Detection | 15 datasets aggregate | 16 | May 12, 2026 | ||
| Tabular Anomaly Detection | thyroid | 16 | May 12, 2026 | ||
| Tabular Anomaly Detection | satimage 2 | 16 | May 12, 2026 | ||
| Tabular Anomaly Detection | satellite | 16 | May 12, 2026 | ||
| Tabular Anomaly Detection | mammography | 16 | May 12, 2026 | ||
| Tabular Anomaly Detection | ionosphere | 16 | May 12, 2026 | ||
| Tabular Anomaly Detection | cardiotocography | 16 | May 12, 2026 | ||
| Tabular Anomaly Detection | cardio | 16 | May 12, 2026 | ||
| Anomaly Detection | pima | 16 | May 12, 2026 | ||
| Forward PDE solving | Klein-Gordon 10K-epoch | 16 | May 12, 2026 | ||
| Forward PDE solving | Conv-Diff 10K-epoch | 16 | May 12, 2026 | ||
| Forward PDE Solving | Allen–Cahn 10K-epoch | 16 | May 12, 2026 | ||
| Forward PDE Solving | Helmholtz 10K-epoch | 16 | May 12, 2026 | ||
| Forward PDE Solving | Burgers 10K-epoch | 16 | May 12, 2026 | ||
| Video-based spatial intelligence | MMSI-Video-Bench | 16 | Jun 11, 2026 | ||
| Reasoning | STB26 | 16 | May 12, 2026 | ||
| Video Question Answering | VideoMME | 16 | May 26, 2026 | ||
| Visual Grounding | Visual Grounding Suite Average Performance | 16 | May 12, 2026 | ||
| Document Visual Question Answering | Doc VQA | 16 | May 12, 2026 |