Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 969 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text-to-image retrieval | MSCOCO 48 (test) | 28 | Feb 26, 2026 | ||
| Image-to-text retrieval | MSCOCO 48 (test) | 28 | Feb 26, 2026 | ||
| Text-to-image retrieval | Flickr30K 84 (test) | 28 | Feb 26, 2026 | ||
| Image-to-text retrieval | Flickr30K 84 (test) | 28 | Feb 26, 2026 | ||
| Video Depth Estimation | ScanNet 90 frames | 28 | Jul 3, 2026 | ||
| 3D Question Answering | ScanQA v1.0 (test) | 28 | May 29, 2026 | ||
| Depth Estimation | ETH3D (test) | 28 | Jul 7, 2026 | ||
| Text-to-Image Retrieval | COCO (test) | 28 | Jun 30, 2026 | ||
| Image Classification | CIFAR-10 Imbalance Factor 200 Long-Tailed (test) | 28 | Feb 26, 2026 | ||
| Vision-Language Modeling | LWilder | 28 | Feb 26, 2026 | ||
| Vision-Language Modeling | LiveB | 28 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K | 28 | Feb 26, 2026 | ||
| Referential Audio-Visual Segmentation | Ref-AVS (seen) | 28 | May 15, 2026 | ||
| Image Classification | FLW | 28 | Apr 24, 2026 | ||
| Adversarial Attack | CIFAR10 (test) | 28 | May 22, 2026 | ||
| Medical Question Answering | MedQA (test) | 28 | Jul 7, 2026 | ||
| Social Dialogue | SOTOPIA Interaction with GPT-4o | 28 | Feb 26, 2026 | ||
| Social Dialogue | SOTOPIA Self-Chat | 28 | Feb 26, 2026 | ||
| Audio Reconstruction | MusicDB (test) | 28 | Feb 26, 2026 | ||
| Multi-level multi-discipline evaluation | C-Eval | 28 | Feb 26, 2026 | ||
| Gradient Compression | CIFAR-10 ConvNet gradients | 28 | Feb 26, 2026 | ||
| Scene Classification | UCM | 28 | Feb 27, 2026 | ||
| Scene Classification | NWPU RESISC45 (test) | 28 | May 8, 2026 | ||
| Text classification | GLUE | 28 | Mar 24, 2026 | ||
| Tabular Classification | Travel (test) | 28 | Feb 26, 2026 |