Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 322 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Open-Vocabulary Semantic Segmentation | Cityscapes (val) | 56 | Jul 7, 2026 | ||
| Image Classification | SAT | 56 | May 7, 2026 | ||
| LiDAR Semantic Segmentation | Place3D (Clean) | 56 | Feb 26, 2026 | ||
| Image Classification | 11 image datasets CoOp protocol (test) | 56 | Feb 26, 2026 | ||
| Automatic Speech Recognition | Fleurs | 56 | Mar 6, 2026 | ||
| Relative Pose Estimation | ScanNet 1500 pairs (test) | 56 | Mar 10, 2026 | ||
| Text-to-Image Retrieval | Urban-1K | 56 | Jul 2, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP procedurally transformed instances Mu-transformed (test) | 56 | Feb 26, 2026 | ||
| Image Super-Resolution | Set5 x3 scale (test) | 56 | May 26, 2026 | ||
| Science Reasoning | GPQA (test) | 56 | May 14, 2026 | ||
| Pansharpening | QuickBird full-resolution | 56 | Feb 26, 2026 | ||
| Model Calibration | ImageNet 1k (val) | 56 | Feb 26, 2026 | ||
| Survival Prediction | TCGA-KIRC (5-fold CV) | 56 | Mar 18, 2026 | ||
| Refusal Rate Evaluation | XSTest Safe (test) | 56 | Feb 26, 2026 | ||
| Text-to-Image Retrieval | MS-COCO 1K | 56 | Jul 3, 2026 | ||
| Video Action Recognition | HMDB51 (avg over all splits) | 56 | Feb 26, 2026 | ||
| Continual Learning | CIFAR-100 | 56 | Mar 12, 2026 | ||
| Image Classification | TinyImageNet (test) | 56 | Feb 26, 2026 | ||
| Compositional Zero-Shot Learning | C-GQA Closed World | 56 | Mar 18, 2026 | ||
| Audio Classification | US8K (test) | 56 | Jun 16, 2026 | ||
| Interpretation Error | IMDb (test) | 56 | Feb 26, 2026 | ||
| Interpretation | SST-2 | 56 | Feb 26, 2026 | ||
| Low-Light Image Enhancement | LIME | 56 | Mar 10, 2026 | ||
| Image Denoising | CBSD68 synthetic Gaussian (test) | 56 | Feb 26, 2026 | ||
| Medical Image Segmentation | GlaS (test) | 56 | May 15, 2026 |