Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1059 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Object Detection | nuScenes J | 26 | Apr 2, 2026 | ||
| Mathematics | Beyond | 26 | Apr 2, 2026 | ||
| Mathematics | AIME 26 | 26 | Apr 2, 2026 | ||
| Brief Hospital Course (BHC) Generation | MIMIC-IV (test) | 26 | Apr 2, 2026 | ||
| Diagnosis | MIMIC-IV (test) | 26 | Apr 2, 2026 | ||
| Survival Analysis | PBC | 26 | Jul 2, 2026 | ||
| Handwritten Text Recognition | RIMES | 26 | Apr 20, 2026 | ||
| Camera Understanding | LaMAR | 26 | May 15, 2026 | ||
| Camera Understanding | TartanAir | 26 | May 15, 2026 | ||
| Camera Understanding | Stanford2D3D | 26 | May 15, 2026 | ||
| Mathematical Reasoning | Geometry3k | 26 | Apr 14, 2026 | ||
| Semantic Segmentation | ADE20K | 26 | Jun 23, 2026 | ||
| Anomaly Detection | Real-IAD | 26 | Jul 2, 2026 | ||
| Text-to-Image Generation | DPG | 26 | Jun 30, 2026 | ||
| Math | AIME 2025 | 26 | Mar 31, 2026 | ||
| Lesion Segmentation | ISIC 2018 | 26 | May 19, 2026 | ||
| Object Hallucination Evaluation | POPE averaged across MS-COCO, A-OKVQA, and GQA (test) | 26 | May 25, 2026 | ||
| Semantic Segmentation | MaSTr1325 80-20 (test) | 26 | Mar 27, 2026 | ||
| Novel View Synthesis | ACID (Large) | 26 | Jul 1, 2026 | ||
| Mathematical Reasoning | Math500 | 26 | Jun 16, 2026 | ||
| Video Question Answering | NextQA | 26 | Apr 8, 2026 | ||
| Temporal Action Segmentation | LARa | 26 | Mar 26, 2026 | ||
| Jailbreak Attack | TrustLLM | 26 | Mar 26, 2026 | ||
| Deception Detection | MU3D | 26 | Jun 11, 2026 | ||
| Object Recognition | ModelNet40 fully-supervised (test) | 26 | Mar 26, 2026 |