Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 178 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Video Question Answering | Video-MME without subtitles | 81 | Jun 12, 2026 | ||
| Generative Hallucination | AMBER Generative | 81 | Jun 26, 2026 | ||
| Sequential model editing | Counterfact | 81 | May 27, 2026 | ||
| Multimodal Understanding | MMBench English | 81 | Jun 16, 2026 | ||
| Anomaly Localization | MPDD (test) | 81 | May 18, 2026 | ||
| Reasoning | ARC Challenge | 81 | May 18, 2026 | ||
| Image Generation | CIFAR10 50k samples (test) | 81 | Feb 26, 2026 | ||
| Multivariate Time Series Forecasting | ECL (test) | 81 | May 26, 2026 | ||
| 3D Object Detection | View-of-Delft (VoD) In Driving Corridor (val) | 81 | Apr 7, 2026 | ||
| Visual Question Answering | InfoSeek (test) | 81 | Apr 8, 2026 | ||
| Image Classification | 11 datasets base-to-new average | 81 | Feb 26, 2026 | ||
| Generalized Category Discovery | CUB-200 (test) | 81 | May 12, 2026 | ||
| Homography Estimation | HPatches | 81 | Apr 13, 2026 | ||
| Video Polyp Segmentation | SUN-SEG Hard (Unseen) | 81 | Jul 1, 2026 | ||
| Semantic Segmentation | nuScenes (test) | 81 | Apr 23, 2026 | ||
| Instance Segmentation | LVIS | 81 | Jun 4, 2026 | ||
| Molecular property prediction | Tox21 | 81 | Jul 7, 2026 | ||
| Image Retrieval | Revisited Oxford (ROxf) (Hard) | 81 | Feb 26, 2026 | ||
| Graph Regression | OGB-LSC PCQM4M v2 (val) | 81 | Feb 26, 2026 | ||
| Image Classification | MHIST (test) | 81 | May 12, 2026 | ||
| Node Classification | Pubmed transductive (test) | 81 | Mar 16, 2026 | ||
| Out-of-Distribution Detection | CIFAR10 (ID) vs SVHN (OOD) | 81 | May 22, 2026 | ||
| OOD Detection | CIFAR-100 IND SVHN OOD | 81 | May 26, 2026 | ||
| Text-to-image Person Re-identification | ICFG-PEDES (test) | 81 | Feb 27, 2026 | ||
| OOD detection | SUN (OOD) | 81 | Mar 4, 2026 |