Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1459 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Membership Inference Attack | VL-MIA Text LLaMA Adapter TEXTLEN=32 | 21 | Apr 2, 2026 | ||
| Membership Inference Attack | VL-MIA Text MiniGPT-4 TEXTLEN=64 | 21 | Apr 2, 2026 | ||
| Membership Inference Attack | VL-MIA Text MiniGPT-4 TEXTLEN=32 | 21 | Apr 2, 2026 | ||
| Membership Inference Attack | VL-MIA Text LLaVA TEXTLEN=64 | 21 | Apr 2, 2026 | ||
| Membership Inference Attack | VL-MIA Text LLaVA TEXTLEN=32 | 21 | Apr 2, 2026 | ||
| Medical Lesion Segmentation | Breast Lesion | 21 | Apr 14, 2026 | ||
| Medical Lesion Segmentation | Lung Infection | 21 | Apr 14, 2026 | ||
| Object Detection | COCO | 21 | May 6, 2026 | ||
| Membership Inference | Real Authors (test) | 21 | Apr 2, 2026 | ||
| Membership Inference | World Facts (test) | 21 | Apr 2, 2026 | ||
| Membership Inference | WikiMIA (test) | 21 | Apr 2, 2026 | ||
| Image Generation | sDCI Densely Captioned Images (test) | 21 | Apr 2, 2026 | ||
| Image Generation | MJHQ 30K (test) | 21 | Apr 2, 2026 | ||
| Image Classification | CIFAR-10 (test) | 21 | Apr 2, 2026 | ||
| Graduate-level Science Reasoning | GPQA | 21 | Jul 3, 2026 | ||
| Encrypted Traffic Classification | CIC-IoT 2022 | 21 | Apr 1, 2026 | ||
| Summarization | CNN/DailyMail | 21 | Apr 1, 2026 | ||
| Graph Coarsening | Cora | 21 | Jun 16, 2026 | ||
| Speech Separation | LibriCSS Utterance-wise v1 (test) | 21 | Apr 1, 2026 | ||
| Search-grounded Image Generation | KnowGen | 21 | Mar 31, 2026 | ||
| Chart Question Answering | ChartQA | 21 | Apr 10, 2026 | ||
| Image Retrieval | Overall Average | 21 | Mar 31, 2026 | ||
| Molecule generation | QM9H | 21 | Apr 2, 2026 | ||
| Classification | leukemia | 21 | Mar 31, 2026 | ||
| Video Understanding | PerceptionTest (test) | 21 | Mar 31, 2026 |