Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1147 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Monocular Depth Estimation | Diode Indoor (test) | 25 | Feb 26, 2026 | ||
| Lossless Image Compression | DIV2K | 25 | Mar 4, 2026 | ||
| Generalized Few-Shot Learning | ImageNet base and novel classes 1K | 25 | Feb 26, 2026 | ||
| Object affordance recognition | COCO 2017 (val) | 25 | Feb 26, 2026 | ||
| Constituency parsing | CTB 5.1 (test) | 25 | Feb 26, 2026 | ||
| Trajectory Prediction | PIE (test) | 25 | Jun 18, 2026 | ||
| Lane Detection | CULane | 25 | Feb 26, 2026 | ||
| Multi-view Clustering | Fashion | 25 | Feb 26, 2026 | ||
| Text-to-Video Retrieval | MSR-VTT 1K videos (test) | 25 | Feb 26, 2026 | ||
| Visual Question Answering | ChartQA (val) | 25 | Feb 26, 2026 | ||
| Classification | mini-ImageNet 5-shot (test) | 25 | Feb 26, 2026 | ||
| Image Classification | ImageNet-21K | 25 | May 26, 2026 | ||
| Video Salient Object Detection | Seg V2 | 25 | Jul 1, 2026 | ||
| Point cloud matching | 4DLoMatch (test) | 25 | Apr 10, 2026 | ||
| Image Classification | CIFAR-10 | 25 | Feb 26, 2026 | ||
| Open-world Semi-Supervised Learning | CIFAR-10 | 25 | Feb 26, 2026 | ||
| Scene Recognition | SUN RGB-D Scene (test) | 25 | Feb 26, 2026 | ||
| Video Super-resolution | REDS4 RGB (test) | 25 | Feb 27, 2026 | ||
| Open-Domain Question Answering | Natural Questions (NQ) (dev) | 25 | Feb 26, 2026 | ||
| Anomaly Detection | CIFAR-10 average of 10 tasks (test) | 25 | Feb 26, 2026 | ||
| Image Generation | CUB200 (train) | 25 | Feb 26, 2026 | ||
| Node classification | Pubmed standard (original) | 25 | Feb 26, 2026 | ||
| Classification | molbbbp OGB | 25 | Feb 26, 2026 | ||
| Action Recognition | Epic-Kitchens (test) | 25 | Feb 26, 2026 | ||
| Graph Classification | ogbg-molhiv (val) | 25 | Feb 26, 2026 |