Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 857 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image-to-image retrieval | Flowers | 30 | Mar 23, 2026 | ||
| Image-to-image retrieval | Pets | 30 | Mar 23, 2026 | ||
| Image-to-image retrieval | Cars | 30 | Mar 23, 2026 | ||
| Out-of-Distribution Detection | OpenOOD ImageNet-1k ID Far-OOD | 30 | May 27, 2026 | ||
| Node Classification | Twitch | 30 | Apr 14, 2026 | ||
| OCR Verification | Curated dataset of 1,000 PDF pages 1.0 (test) | 30 | Mar 18, 2026 | ||
| In-context retrieval | Real-world data | 30 | May 8, 2026 | ||
| Sensitive-escalation deferral-advice | IEEE-CIS (val) | 30 | Mar 17, 2026 | ||
| Image-Text Retrieval | General Domain | 30 | Mar 17, 2026 | ||
| Image Classification | General Domain 31 tasks | 30 | Mar 17, 2026 | ||
| Medical Image-Text Classification | Medical Specialties | 30 | Mar 17, 2026 | ||
| Natural Language Understanding | GLUE | 30 | May 26, 2026 | ||
| Localization | ImageNet (val) | 30 | Mar 17, 2026 | ||
| Attribution Faithfulness | ImageNet | 30 | Apr 27, 2026 | ||
| Attribution Faithfulness Evaluation | ImageNet (test) | 30 | Mar 17, 2026 | ||
| Faithfulness Evaluation | ImageNet | 30 | Mar 17, 2026 | ||
| Edge Classification | WN18RR 10 way Lexical KG (test) | 30 | Mar 17, 2026 | ||
| Edge Classification | WN18RR 5 way Lexical KG (test) | 30 | Mar 17, 2026 | ||
| Traffic Data Completion | Seattle | 30 | Mar 17, 2026 | ||
| Traffic Data Completion | PEMS07 | 30 | Mar 17, 2026 | ||
| Traffic Data Completion | Guangzhou | 30 | Mar 17, 2026 | ||
| Novel View Synthesis | NeRF-LLFF | 30 | Mar 17, 2026 | ||
| Memory Control Flow Attack (Override) | MEMFLOW Override | 30 | Mar 17, 2026 | ||
| Visual Question Answering | VQA 10,000 samples v2 (val) | 30 | Jun 4, 2026 | ||
| 3D pointcloud manipulation | MetaWorld | 30 | Jun 2, 2026 |