Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 974 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Anomaly Localization | BUSI (test) | 28 | Feb 26, 2026 | ||
| Depth Estimation | SCARED (test) | 28 | Jun 26, 2026 | ||
| Novel-view synthesis | Shiny | 28 | Feb 26, 2026 | ||
| Instance Segmentation | COCO | 28 | Feb 27, 2026 | ||
| Membership Inference Attack | WikiMIA length 128 | 28 | Feb 26, 2026 | ||
| Action Segmentation | YouTube Instructions | 28 | Jul 7, 2026 | ||
| Referring Remote Sensing Image Segmentation | RRSIS-D (val) | 28 | May 26, 2026 | ||
| Cross-modal Retrieval | RSITMD (test) | 28 | Feb 26, 2026 | ||
| Adversarial Attack | SAM-1B subset 1.0 (test) | 28 | Feb 26, 2026 | ||
| Video Question Answering | NExT-QA zero-shot | 28 | Jun 16, 2026 | ||
| Image Retrieval | COCO (val) | 28 | Feb 26, 2026 | ||
| Attention Heatmap Prediction | TCGA-PRAD (Prostate Cancer) H&E WSIs (test) | 28 | Feb 26, 2026 | ||
| Few-shot Image Classification | Aircraft (test) | 28 | Feb 26, 2026 | ||
| Sentiment Classification | Laptop14 | 28 | Feb 26, 2026 | ||
| Indiscriminate Attack | CIFAR10-C (test) | 28 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K 1.0 (val) | 28 | Feb 26, 2026 | ||
| Failure Prediction | CIFAR100-LT IF=10 (test) | 28 | Feb 26, 2026 | ||
| Failure Prediction | CIFAR10-LT IF=10 (test) | 28 | Feb 26, 2026 | ||
| Image Captioning Hallucination Detection | FOIL (test) | 28 | Feb 26, 2026 | ||
| Open-vocabulary semantic segmentation | PAS-20 Pascal VOC (test) | 28 | Mar 24, 2026 | ||
| Time Series Forecasting | Weather | 28 | Feb 26, 2026 | ||
| Question Answering | NarrativeQA | 28 | May 12, 2026 | ||
| Visual Perception | MME | 28 | Mar 4, 2026 | ||
| Visual Localization | Aachen Day-Night 1.1 (Day) | 28 | Feb 26, 2026 | ||
| Text-to-image generation | TIFA | 28 | Feb 26, 2026 |