Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1700 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Entity Regression (post-votes) | rel-stack | 19 | May 25, 2026 | ||
| Subgroup Discovery | MNIST Digit 7 (test) | 19 | May 21, 2026 | ||
| Video Generation | VBench extended prompts | 19 | May 21, 2026 | ||
| Video Generation | VBench | 19 | May 21, 2026 | ||
| Image Classification | m-bigearthnet (test) | 19 | May 21, 2026 | ||
| Industrial Anomaly Detection | MVTec, MPDD, VisA, DTD, and SDD Aggregate | 19 | May 21, 2026 | ||
| Industrial Anomaly Detection | SDD | 19 | May 21, 2026 | ||
| Industrial Anomaly Detection | DTD | 19 | May 21, 2026 | ||
| Industrial Anomaly Detection | VisA | 19 | May 21, 2026 | ||
| Industrial Anomaly Detection | MPDD | 19 | May 21, 2026 | ||
| Industrial Anomaly Detection | MVTec AD | 19 | May 21, 2026 | ||
| Action Recognition | FogAct 1.0 (test) | 19 | May 21, 2026 | ||
| Object Tracking | HOTC2020 (test) | 19 | May 21, 2026 | ||
| Referring Video Object Segmentation | MeViS v1 | 19 | May 20, 2026 | ||
| Open-vocabulary 3D segmentation | LERF-Mask (test) | 19 | May 29, 2026 | ||
| Graph Anomaly Detection | DBLP | 19 | May 27, 2026 | ||
| Mathematical Reasoning | MATH 500 | 19 | Jun 30, 2026 | ||
| Visual Question Answering | OK-VQA standard (test) | 19 | May 20, 2026 | ||
| Action recognition | NTU120 (5-fold) | 19 | May 20, 2026 | ||
| Action recognition | FPHA (5-fold) | 19 | May 20, 2026 | ||
| Action recognition | HDM05 (5-fold) | 19 | May 20, 2026 | ||
| Real-world visual perception | MME-RealWorld CN | 19 | May 19, 2026 | ||
| Real-world visual perception | MME-RealWorld Lite | 19 | May 19, 2026 | ||
| Zoom-dependent visual question answering | ZoomBench | 19 | May 19, 2026 | ||
| Visual perception of small objects | V* Bench | 19 | May 19, 2026 |