Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 953 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Prompt Classification | EXPGUARD (test) | 28 | Mar 4, 2026 | ||
| 3D tracking | ADT 61 (test) | 28 | Mar 4, 2026 | ||
| 3D tracking | PointOdyssey 102 (test) | 28 | Mar 4, 2026 | ||
| Semantic Segmentation | P-R Potsdam and Vaihingen | 28 | Mar 4, 2026 | ||
| Semantic Segmentation | Cityscapes Adverse Conditions ACDC | 28 | Mar 4, 2026 | ||
| Semantic Segmentation | GTAV Generalization to Cityscapes, BDD100K, Mapillary | 28 | Mar 4, 2026 | ||
| Disclosure | BOLT SMS single-turn | 28 | Mar 4, 2026 | ||
| Emotional Support | BOLT SMS single-turn | 28 | Mar 4, 2026 | ||
| Disclosure | BOLT SMS multi-turn | 28 | Mar 4, 2026 | ||
| Emotional Support | BOLT SMS multi-turn | 28 | Mar 4, 2026 | ||
| Mathematical Reasoning | Gaokao | 28 | May 7, 2026 | ||
| Medical Reasoning | MedDDx (test) | 28 | Mar 4, 2026 | ||
| Multi-choice medical QA | Multi-choice medical QA benchmarks (test) | 28 | Mar 4, 2026 | ||
| Record Linkage | Process Industry Shift Logs | 28 | Mar 4, 2026 | ||
| Adversarial Attack | ImageNet (val) | 28 | Mar 4, 2026 | ||
| Grounding | RefCOCO | 28 | Mar 4, 2026 | ||
| Binary manipulation detection | MMFakeBench 10000 samples (test) | 28 | Mar 4, 2026 | ||
| Binary manipulation detection | MMFakeBench 1000 samples (val) | 28 | Mar 4, 2026 | ||
| Image Completion | Sentinel-2 T33TUL (test) | 28 | Mar 4, 2026 | ||
| Image Completion | Sentinel-2 T32TQR (test) | 28 | Mar 4, 2026 | ||
| Image Completion | Sentinel-2 T30UYV (test) | 28 | Mar 4, 2026 | ||
| MSI Completion | Toy MSI database | 28 | Mar 4, 2026 | ||
| MSI Completion | Painting MSI | 28 | Mar 4, 2026 | ||
| MSI Completion | Flowers MSI database | 28 | Mar 4, 2026 | ||
| MSI Completion | Cloth MSI database | 28 | Mar 4, 2026 |