Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 980 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Gaze Estimation | MPIIFaceGaze (leave-one-subject-out) | 28 | Mar 16, 2026 | ||
| Speech Command Recognition | GSC-MUSAN (test) | 28 | Feb 26, 2026 | ||
| Speech Command Recognition | GSC-QUT (test) | 28 | Feb 26, 2026 | ||
| Machine Translation | WMT14 DE-EN (test) | 28 | Feb 27, 2026 | ||
| Multivariate Time Series Forecasting | Electricity full (test) | 28 | Feb 26, 2026 | ||
| Multivariate Time Series Forecasting | ETTm2 full (test) | 28 | Feb 26, 2026 | ||
| Matting | AIM-500 (test) | 28 | Feb 26, 2026 | ||
| Link Prediction | ogbl-citation2 (val) | 28 | Feb 26, 2026 | ||
| Link Prediction | ogbl-ddi (val) | 28 | Feb 26, 2026 | ||
| Confidence Calibration | CoraFull | 28 | Feb 26, 2026 | ||
| Accident anticipation | DAD | 28 | Jun 15, 2026 | ||
| Vehicle Detection | Waymo Open Dataset LEVEL_1 v1.2 (val) | 28 | Feb 26, 2026 | ||
| HalfCheetah | D4RL Medium-Replay v0 | 28 | Feb 26, 2026 | ||
| Text Retrieval | COCO Caption | 28 | Feb 26, 2026 | ||
| Scene Completion | SUNCG (test) | 28 | Feb 26, 2026 | ||
| Anomaly Segmentation | Fishyscapes Static (test) | 28 | Feb 26, 2026 | ||
| CT Reconstruction | COVID (test) | 28 | Feb 26, 2026 | ||
| CT Reconstruction | AAPM (test) | 28 | Feb 26, 2026 | ||
| Alzheimer's disease classification | TADPOLE | 28 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 | 28 | Feb 26, 2026 | ||
| Few-shot Classification | CUB200 5-way 5-shot | 28 | Feb 26, 2026 | ||
| Image classification | Colored MNIST unbiased (test) | 28 | Feb 26, 2026 | ||
| Fair Classification | COMPAS (test) | 28 | Feb 26, 2026 | ||
| Classification | AdultCensus (test) | 28 | Feb 26, 2026 | ||
| Fair Classification | Synthetic 1.0 (test) | 28 | Feb 26, 2026 |