Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2109 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Soil Surface Moisture Retrieval | PALSAR-2 Mine Environment L-band (evaluated observations) | 16 | Jul 2, 2026 | ||
| Long-caption Cross-modal Retrieval | DOCCI (test) | 16 | Jul 2, 2026 | ||
| Image-to-Text Retrieval | Urban-1k | 16 | Jul 2, 2026 | ||
| Question Answering | HotpotQA | 16 | Jul 2, 2026 | ||
| Question Answering | MS-MARCO | 16 | Jul 2, 2026 | ||
| Question Answering | NQ | 16 | Jul 2, 2026 | ||
| Membership Inference Attack | Llama-13B | 16 | Jul 1, 2026 | ||
| Membership Inference Attack | OPT-6.7B | 16 | Jul 1, 2026 | ||
| Membership Inference Attack | OLMo-7B | 16 | Jul 1, 2026 | ||
| Membership Inference Attack | Pythia 6.9B | 16 | Jul 1, 2026 | ||
| End-to-End Autonomous Driving | NAVSIM v2 (navhard-two-stage) | 16 | Jul 1, 2026 | ||
| Medical Visual Question Answering | MIMIC-Ext MIMIC-CXR VQA | 16 | Jul 1, 2026 | ||
| Medical Visual Question Answering | Quilt-VQA | 16 | Jul 1, 2026 | ||
| Medical Visual Question Answering | VQA-Med 2021 | 16 | Jul 1, 2026 | ||
| Medical Visual Question Answering | Medical VQA | 16 | Jul 1, 2026 | ||
| Navigation | RealMobile (test) | 16 | Jul 1, 2026 | ||
| Visual Question Answering | VQA v2 | 16 | Jul 7, 2026 | ||
| Image Classification | CIFAR-100 | 16 | Jul 1, 2026 | ||
| Object Detection | Cityscapes → BDD100K Diverse Context Adaptation (target) | 16 | Jul 1, 2026 | ||
| Video Prediction | Human3.6M 4 → 4 frames (test) | 16 | Jul 1, 2026 | ||
| Makeup Transfer | MT-Wild (test) | 16 | Jul 1, 2026 | ||
| Multi-Agent Systems Routing Defense | MMLU | 16 | Jun 30, 2026 | ||
| Text-to-image person retrieval | ICFG-PEDES | 16 | Jun 30, 2026 | ||
| Image Classification | CIFAR-10 | 16 | Jun 30, 2026 | ||
| Food Classification | Food-101 9 | 16 | Jun 30, 2026 |