Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1325 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Weakly Supervised Video Anomaly Detection | UCFCrime 1.0 (test) | 23 | Feb 26, 2026 | ||
| Open-ended Visual Question Answering | PMC-VQA (test) | 23 | Feb 26, 2026 | ||
| Coding | MBPP | 23 | May 22, 2026 | ||
| Code Generation | LiveCodeBench v1 (test) | 23 | May 28, 2026 | ||
| Multi-page Document Question Answering | DUDE | 23 | Apr 28, 2026 | ||
| Time Series Anomaly Detection | UCR-AD archive | 23 | Feb 26, 2026 | ||
| Summarization | Summarization | 23 | Jun 23, 2026 | ||
| Time Series Forecasting | Traffic Standard (test) | 23 | Jun 1, 2026 | ||
| Human Pose Estimation | ExLPose-OCN (test) | 23 | Feb 27, 2026 | ||
| Novel View Synthesis | HyperNeRF (vrig) | 23 | Feb 26, 2026 | ||
| Person Re-identification | P-DukeMTMC | 23 | May 20, 2026 | ||
| Medical Image Segmentation | PH2 | 23 | Mar 19, 2026 | ||
| Monocular Depth Estimation | KITTI Raw (Eigen) | 23 | Feb 26, 2026 | ||
| Visual Place Recognition | SF-XL v2 (test) | 23 | Jul 2, 2026 | ||
| Anomaly Localization | VisA | 23 | Apr 8, 2026 | ||
| Oriented Object Detection | DOTA 1.0 (train test) | 23 | Feb 26, 2026 | ||
| Medical Image Segmentation | Synapse multi-organ CT MICCAI 2015 (test) | 23 | Jul 9, 2026 | ||
| Text-based Visual Question Answering | TextVQA 52 | 23 | Feb 26, 2026 | ||
| Composed Image Retrieval | CIRR Index Set v1.0 | 23 | Feb 26, 2026 | ||
| Diagram Understanding | AI2D F | 23 | Feb 26, 2026 | ||
| Mathematical Reasoning | MathVista F | 23 | Feb 26, 2026 | ||
| Multi-discipline Multimodal Understanding | MMMU F | 23 | Feb 26, 2026 | ||
| Machine Translation (Zh ⇒ En) | WMT 22 (test) | 23 | Feb 26, 2026 | ||
| Question Answering | Natural Questions (NQ) | 23 | Mar 27, 2026 | ||
| Video Instance Segmentation | OVIS | 23 | Jul 2, 2026 |