Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2097 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Node Clustering | Citeseer (test) | 17 | Feb 26, 2026 | ||
| Image Clustering | MNIST (labelled) | 17 | Feb 26, 2026 | ||
| Image Clustering | CIFAR100-20 (labelled) | 17 | Feb 26, 2026 | ||
| Image Clustering | CIFAR10 (labelled) | 17 | Feb 26, 2026 | ||
| Image Clustering | STL10 (labelled) | 17 | Feb 26, 2026 | ||
| Action Recognition | Kinetics-400 Nov. 2018 (val) | 17 | Feb 26, 2026 | ||
| Visual Localization | Extended CMU Seasons (Park) | 17 | Feb 26, 2026 | ||
| Pedestrian Trajectory Prediction | Stanford Drone Dataset | 17 | Feb 26, 2026 | ||
| Egocentric Action Anticipation | EPIC-KITCHENS (val) | 17 | Feb 26, 2026 | ||
| Part-of-Speech Tagging | UD (Universal Dependencies) Indonesian (test) | 17 | Feb 26, 2026 | ||
| Visual Object Tracking | OTB 2013 | 17 | Feb 26, 2026 | ||
| Top-K Recommendation | MovieLens 20M (test) | 17 | Feb 26, 2026 | ||
| Emotion Cause Extraction | Emotion Cause Corpus | 17 | Feb 26, 2026 | ||
| Unconditional image modeling | ImageNet 64x64 | 17 | Feb 26, 2026 | ||
| CTR Prediction | MovieLens 20M (test) | 17 | Feb 26, 2026 | ||
| Action Recognition | EPIC-KITCHENS 1 (S1 Seen kitchens) | 17 | Feb 26, 2026 | ||
| Dependency-based Semantic Role Labeling | CoNLL 2009 (Out-of-domain (Brown)) | 17 | Feb 26, 2026 | ||
| Face Identification | FG-NET (leave-one-out) | 17 | Feb 26, 2026 | ||
| Image Classification | FLO | 17 | Feb 26, 2026 | ||
| Commonsense Reasoning | Winograd Schema Challenge (WSC) (test) | 17 | Feb 26, 2026 | ||
| Regression | News (test) | 17 | Feb 26, 2026 | ||
| Visual Object Tracking | OTB 2013 | 17 | Feb 26, 2026 | ||
| CTR prediction | Last.FM (test) | 17 | Feb 26, 2026 | ||
| Heterogeneous Face Recognition | Oulu-CASIA NIR-VIS | 17 | Feb 26, 2026 | ||
| Clustering | Fashion-MNIST standard (test) | 17 | Feb 26, 2026 |