Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1475 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Anomaly Detection | PSM | 21 | Feb 27, 2026 | ||
| Anomaly Detection | SMAP | 21 | Feb 27, 2026 | ||
| Anomaly Detection | MSL | 21 | Feb 27, 2026 | ||
| Multimodal Abstractive Summarization | How2 (test) | 21 | May 13, 2026 | ||
| Image Classification | MNIST (test) | 21 | Feb 27, 2026 | ||
| Depth Prediction | NYU v2 | 21 | Mar 10, 2026 | ||
| Federated Semi-supervised Learning | CIFAR100 alpha=1.0 (test) | 21 | Feb 27, 2026 | ||
| Time-series forecasting | SolarWind block-wise test-time missingness (test) | 21 | Feb 26, 2026 | ||
| Calibration for Unsupervised Domain Adaptation | Cityscapes to ACDC Normal weather to adverse weather (test) | 21 | Feb 26, 2026 | ||
| Calibration for Unsupervised Domain Adaptation | SYNTHIA to Cityscapes 16 classes (test) | 21 | Feb 26, 2026 | ||
| Calibration for Unsupervised Domain Adaptation | GTAv to Cityscapes Source: Synthetic, Target: Real (test) | 21 | Feb 26, 2026 | ||
| Visual Question Answering | nuScenes-QA | 21 | May 21, 2026 | ||
| Multi-modal Question Answering | MMStar | 21 | Jun 4, 2026 | ||
| Camouflaged Object Segmentation | COD10K 2016 (test) | 21 | Feb 26, 2026 | ||
| Camouflaged Object Segmentation | NC4K 4121 (test) | 21 | Feb 26, 2026 | ||
| Robotic Manipulation | RoboTwin Hard 2.0 | 21 | Jul 7, 2026 | ||
| Anomaly Detection | MVTec-AD | 21 | Feb 26, 2026 | ||
| Node Classification | Twitch ID | 21 | Feb 26, 2026 | ||
| Node Classification | Citeseer (OOD) | 21 | Feb 26, 2026 | ||
| Node Classification | Citeseer (ID) | 21 | Feb 26, 2026 | ||
| Node Classification | Cora (OOD) | 21 | Feb 26, 2026 | ||
| Machine Unlearning | WMDP | 21 | Apr 21, 2026 | ||
| Few-Shot Class-Incremental Learning | miniImageNet 5-way 5-shot (incremental) | 21 | Feb 26, 2026 | ||
| Few-Shot Class-Incremental Learning | CUB-200 | 21 | Feb 26, 2026 | ||
| Image Classification | SVIRO (test) | 21 | Feb 26, 2026 |