Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1398 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Object Classification | ModelNet-C | 22 | Mar 24, 2026 | ||
| Summarization | MeetingBank | 22 | Feb 26, 2026 | ||
| Pedestrian Detection | KAIST (test) | 22 | Feb 26, 2026 | ||
| Image Difference Captioning | Spot-the-Diff (test) | 22 | Mar 9, 2026 | ||
| Image Difference Captioning | Image-Edit-Request (test) | 22 | Mar 9, 2026 | ||
| Referring Object Classification | LVIS (test) | 22 | Feb 26, 2026 | ||
| Histopathology image classification | NSCLC (test) | 22 | Feb 26, 2026 | ||
| PAN-sharpening | QB Reduced-Resolution | 22 | Feb 26, 2026 | ||
| Automatic Speech Recognition | TED-LIUM | 22 | Jun 9, 2026 | ||
| Visual Question Answering | PathMMU 1.0 (ALL test) | 22 | Feb 26, 2026 | ||
| Fine-grained Video Understanding | MVBench | 22 | Feb 26, 2026 | ||
| Monocular Depth Estimation | NuScenes | 22 | Apr 23, 2026 | ||
| Class-wise Forgetting | Imagenette Stable Diffusion v1.4 (val) | 22 | Feb 26, 2026 | ||
| Polling-based Object Probing Evaluation (POPE) | MSCOCO POPE (Popular) | 22 | Feb 26, 2026 | ||
| Long-context generation | LongBench | 22 | Mar 10, 2026 | ||
| Image Classification | ImageNet-1k 1.0 (val) | 22 | Feb 26, 2026 | ||
| Detailed Captioning | ShapeNeRF-Text 1.0 (test) | 22 | Feb 26, 2026 | ||
| Word-level sign language recognition | MS-ASL 200 | 22 | Feb 26, 2026 | ||
| Word-level sign language recognition | MS-ASL 100 | 22 | Feb 26, 2026 | ||
| Language Modeling | Arxiv zero-shot | 22 | Jun 9, 2026 | ||
| Language Modeling | AG News zero-shot | 22 | Jun 9, 2026 | ||
| Language Modeling | Wikitext zero-shot | 22 | Jun 9, 2026 | ||
| Document Information Extraction | DeepForm (test) | 22 | May 27, 2026 | ||
| Object Discovery | MOVI-C | 22 | Apr 20, 2026 | ||
| Long-tailed Image Classification | CIFAR100-LT Imbalance Factor 10 | 22 | Feb 26, 2026 |