Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 49 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Segmentation | NYUD v2 (test) | 187 | Feb 26, 2026 | ||
| Domain Generalization | Office-Home (test) | 187 | Jul 3, 2026 | ||
| Domain Adaptation | Office-31 | 187 | May 8, 2026 | ||
| Panoptic Segmentation | COCO 2017 (val) | 187 | Jun 15, 2026 | ||
| Traffic speed forecasting | PEMS-BAY (test) | 187 | May 19, 2026 | ||
| Jailbreak Attack | STRONGREJECT (held-out behaviors) | 186 | Jun 4, 2026 | ||
| Text-to-Speech | X-Voice (test) | 186 | May 8, 2026 | ||
| Image Reconstruction | Peppers | 186 | Jun 5, 2026 | ||
| Untargeted Adversarial Attack | ImageNet | 186 | Mar 31, 2026 | ||
| Grade School Math Reasoning | GSM8K | 186 | Jun 23, 2026 | ||
| Generalized Category Discovery | CUB | 186 | May 22, 2026 | ||
| Node Classification | Computer | 186 | Jun 11, 2026 | ||
| Science Question Answering | ScienceQA SQA-IMG | 186 | Apr 24, 2026 | ||
| Out-of-Distribution Detection | Textures | 186 | Apr 28, 2026 | ||
| Object Detection | COCO | 186 | May 12, 2026 | ||
| Moment Retrieval | Charades-STA (test) | 186 | Apr 3, 2026 | ||
| Question Answering | PopQA | 186 | Mar 12, 2026 | ||
| Image Generation | CIFAR10 32x32 (test) | 186 | May 6, 2026 | ||
| Object Classification | ScanObjectNN OBJ_ONLY | 186 | May 19, 2026 | ||
| Long Context Understanding | LongBench V2 | 185 | Jul 8, 2026 | ||
| Reasoning | GPQA Diamond | 185 | May 18, 2026 | ||
| Image Classification | CIFAR-10 IID | 185 | May 25, 2026 | ||
| Video Understanding | EgoSchema | 185 | Jun 12, 2026 | ||
| Text-to-Image Generation | T2I-CompBench | 185 | Apr 16, 2026 | ||
| Object Detection | OV-COCO | 185 | Jul 3, 2026 |