Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 597 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Zero-shot Evaluation | Various Tasks Average (test) | 38 | Feb 26, 2026 | ||
| Jailbreak Attack Evaluation | TRIDENT CORE | 38 | Feb 26, 2026 | ||
| GUI Navigation | AITW | 38 | Jun 30, 2026 | ||
| Low-Light Image Enhancement | MIT-Adobe FiveK | 38 | Jul 7, 2026 | ||
| Natural Language Processing | 7 NLP Tasks (test) | 38 | Apr 3, 2026 | ||
| Multi-modal Vision-Language Understanding | MMVet | 38 | Feb 26, 2026 | ||
| Object Detection | MS-COCO | 38 | Feb 27, 2026 | ||
| Geometry problem solving | MathVista GPS | 38 | Feb 26, 2026 | ||
| Video Question Answering | LVBench | 38 | May 26, 2026 | ||
| Science Question Answering | SQA-I | 38 | Jun 1, 2026 | ||
| Infrared-visible Image Fusion | MSRS | 38 | May 14, 2026 | ||
| Classification | CIFAR10 | 38 | Feb 26, 2026 | ||
| Composed Image Retrieval | GeneCIS (test) | 38 | Feb 26, 2026 | ||
| Image Quality Assessment | CVIU | 38 | Feb 26, 2026 | ||
| Continual Visual Question Answering | VQA v2 (test) | 38 | Jul 3, 2026 | ||
| Image Super-Resolution | Manga109 x4 scale (test) | 38 | May 26, 2026 | ||
| Adversarial Attack | CIFAR100 | 38 | May 21, 2026 | ||
| Classification | FGVCAircraft | 38 | Apr 7, 2026 | ||
| Defect Detection | MVTec-AD | 38 | Apr 23, 2026 | ||
| Scene Classification | NWPU | 38 | Feb 27, 2026 | ||
| Maximum Independent Set | RB [200-300] | 38 | Jun 1, 2026 | ||
| Dialogue Reasoning | MUTUAL | 38 | May 15, 2026 | ||
| Object Detection | OV-LVIS | 38 | Jul 3, 2026 | ||
| Fraud Detection | Amazon (test) | 38 | Mar 11, 2026 | ||
| Community Detection | ogb-arxiv | 38 | Feb 26, 2026 |