Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 818 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Monocular Depth Estimation | SUN-RGBD (test) | 31 | Apr 30, 2026 | ||
| Sentiment Analysis | SST-2 | 31 | Feb 26, 2026 | ||
| 3D Human Pose and Shape Estimation | EMDB Protocol 1 24 joints | 31 | Feb 27, 2026 | ||
| Pansharpening | GF2 reduced-resolution | 31 | Feb 26, 2026 | ||
| Temporal Action Localization | ActivityNet 1.3 (50%-50%) | 31 | Jun 1, 2026 | ||
| Visual Grounding | Who's Waldo (test) | 31 | Feb 26, 2026 | ||
| Image Retrieval | RPar+R1M Hard | 31 | Feb 26, 2026 | ||
| Image Retrieval | RPar+R1M Medium | 31 | Feb 26, 2026 | ||
| Crowd Counting | UCF-QNRF (Q) (test) | 31 | Feb 26, 2026 | ||
| Object Recognition | COCO (val) | 31 | Feb 26, 2026 | ||
| Class-Incremental Learning | ImageNet-R 10 tasks | 31 | May 12, 2026 | ||
| Anomaly Detection | BrainMRI | 31 | Feb 26, 2026 | ||
| Visual Object Tracking | LaSOT 2019 (test) | 31 | Feb 26, 2026 | ||
| Instruction following | ALFRED (test-unseen) | 31 | May 26, 2026 | ||
| Entity Recognition | BioNLP | 31 | Apr 23, 2026 | ||
| Mathematical Reasoning | GSM8K @MetaMath (test) | 31 | Feb 26, 2026 | ||
| Referring Expression Generation | RefCOCOg (val) | 31 | Feb 26, 2026 | ||
| Compositional Image Retrieval | GeneCIS (test) | 31 | Feb 27, 2026 | ||
| Image Classification | UC Merced | 31 | Apr 14, 2026 | ||
| Text Classification | FPB | 31 | Mar 5, 2026 | ||
| Image Classification | CIFAR-100 non-IID alpha=0.1 | 31 | Mar 4, 2026 | ||
| Text Classification | Tweet Sentiment | 31 | Feb 26, 2026 | ||
| Multi-task Language Understanding | CEval | 31 | Jun 19, 2026 | ||
| Heart Rate Prediction | IEEE SPC12 | 31 | Feb 26, 2026 | ||
| Information Retrieval | HotpotQA | 31 | Jun 1, 2026 |