Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1648 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Segmentation | Cityscapes 1/2 (1488 labels) | 20 | Feb 26, 2026 | ||
| Change Detection | SECOND (test) | 20 | Feb 26, 2026 | ||
| Node Classification | Arxiv Covariate shift time split | 20 | Feb 26, 2026 | ||
| Machine Translation | WMT En-De 14 (val) | 20 | Feb 26, 2026 | ||
| Retrieval Following | Natural Questions (test) | 20 | Feb 26, 2026 | ||
| Retrieval Following | ConFiQA MC 1.0 (test) | 20 | Feb 26, 2026 | ||
| Retrieval Following | ConFiQA MR 1.0 (test) | 20 | Feb 26, 2026 | ||
| Retrieval Following | ConFiQA QA 1.0 (test) | 20 | Feb 26, 2026 | ||
| Document-level Relation Extraction | Re-DocRED 1.0 (test) | 20 | Feb 26, 2026 | ||
| Image Classification | ImageNet (test) | 20 | Feb 26, 2026 | ||
| Free-format Multimodal Hallucination Assessment | RefoMB (dev) | 20 | Feb 26, 2026 | ||
| Hallucination Assessment | MHumanEval | 20 | Feb 26, 2026 | ||
| Instance Segmentation | COCO | 20 | Feb 26, 2026 | ||
| Pancreas Segmentation | Pancreas-CT (20% labeled, 80% unlabeled) | 20 | Feb 26, 2026 | ||
| Medical Image Segmentation | Abdominal MRI-CT | 20 | Feb 26, 2026 | ||
| Medical Image Segmentation | Abdominal CT-MRI | 20 | Feb 26, 2026 | ||
| Composed Image Retrieval | FashionIQ 1.0 (test) | 20 | Feb 26, 2026 | ||
| Aspect-Based Sentiment Analysis | Laptop14 original (test) | 20 | Feb 26, 2026 | ||
| Aspect-Based Sentiment Analysis | Restaurant14 original (test) | 20 | Feb 26, 2026 | ||
| Novel View Synthesis | RealEstate10K Hard | 20 | Feb 26, 2026 | ||
| Image Classification | ImageNet | 20 | Feb 26, 2026 | ||
| Event-level Financial Sentiment Analysis | EFSA | 20 | Feb 26, 2026 | ||
| Fine-grained Event-level Financial Sentiment Analysis | EFSA | 20 | Feb 26, 2026 | ||
| Coarse-grained Event-level Financial Sentiment Analysis | EFSA | 20 | Feb 26, 2026 | ||
| Online Continual Learning | CIFAR-10 10/1 (test) | 20 | Feb 27, 2026 |