Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1780 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Link Prediction | USAir 90/10 (train) | 19 | Feb 26, 2026 | ||
| Information Retrieval | TREC Title queries 1-3 | 19 | Feb 26, 2026 | ||
| Trajectory Prediction | Stanford Drone (test) | 19 | Feb 26, 2026 | ||
| Face Identification | IJB-A 1:N Identification | 19 | Feb 26, 2026 | ||
| Instance Segmentation | Mapillary Vistas Dataset (val) | 19 | Feb 26, 2026 | ||
| Fine-grained Entity Typing | FGN (test) | 19 | Feb 26, 2026 | ||
| Combinatory Categorial Grammar | CCG (test) | 19 | Feb 26, 2026 | ||
| Multivariate Time Series Classification | ArabicDigits | 19 | Feb 26, 2026 | ||
| Semantic Role Labeling | CoNLL WSJ 2005 (dev) | 19 | Feb 26, 2026 | ||
| Speech Command Recognition | Google Speech Command Dataset 20-cmd V2 (test) | 19 | Feb 26, 2026 | ||
| Natural Language Inference | SNLI 1.0 (test) | 19 | Feb 26, 2026 | ||
| Color Image Denoising | McMaster (test) | 19 | Feb 26, 2026 | ||
| Traffic Speed Forecasting | PeMSD7 Large (test) | 19 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | Human3.6M Protocol 2 (subjects 9 and 11) | 19 | Feb 26, 2026 | ||
| Sentiment Classification | MR (Movie Review) binary (test) | 19 | Feb 26, 2026 | ||
| Instance Segmentation | COCO (minival) | 19 | Feb 26, 2026 | ||
| Question Answering | TriviaQA Wikipedia (dev-full) | 19 | Feb 26, 2026 | ||
| Handwriting Recognition | LipiTk Handwriting Devanagari script (test) | 19 | Feb 26, 2026 | ||
| Semantic Segmentation | S3DIS (5th fold) | 19 | Feb 27, 2026 | ||
| Person Image Generation | DeepFashion (test) | 19 | Feb 26, 2026 | ||
| Image Classification | Imbalanced CIFAR-10 long-tailed ratio 100 ResNet32 (test) | 19 | Feb 26, 2026 | ||
| Human Parsing | Human3.6M | 19 | Feb 26, 2026 | ||
| Weakly supervised semantic segmentation | VOC 2012 (val) | 19 | Feb 26, 2026 | ||
| Pose Estimation | Penn Action Dataset (test) | 19 | Feb 26, 2026 | ||
| Inductive Node Classification | PPI (test) | 19 | Feb 26, 2026 |