Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1773 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| AUC Maximization | german | 19 | Feb 26, 2026 | ||
| Event-based Semantic Segmentation | DDD17 (test) | 19 | Feb 26, 2026 | ||
| Audio Tagging | FSD50K (eval) | 19 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal VOC 2012 | 19 | Feb 26, 2026 | ||
| Image Classification | ImageNet natural distribution shift v2 (test) | 19 | Feb 26, 2026 | ||
| Defocus Deblurring | DPD (test) | 19 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 (test) | 19 | Feb 26, 2026 | ||
| Multimodal AutoML | Multimodal Benchmark | 19 | Feb 26, 2026 | ||
| Human Pose Estimation | CrowdPose (val) | 19 | Feb 26, 2026 | ||
| Word Sense Disambiguation | FEWS (test) | 19 | Mar 6, 2026 | ||
| Factuality Evaluation | QAGS XSUM | 19 | Feb 26, 2026 | ||
| Time series forecasting | wiki (test) | 19 | Feb 26, 2026 | ||
| Time series forecasting | solar (test) | 19 | Feb 26, 2026 | ||
| Time series forecasting | exchange (test) | 19 | Feb 26, 2026 | ||
| Machine Translation Evaluation | WMT segment-level 2019 (test) | 19 | Feb 26, 2026 | ||
| Machine Translation Evaluation | TAC summary-level 2008-2011 (test) | 19 | Feb 26, 2026 | ||
| Single Image Reflection Removal | Nature (test) | 19 | Feb 26, 2026 | ||
| Sign Language Recognition | SLR500 | 19 | Mar 9, 2026 | ||
| Grammatical Error Correction | BEA 2019 (dev) | 19 | Feb 26, 2026 | ||
| Action Recognition | UTD-MHAD (val) | 19 | Feb 26, 2026 | ||
| Video Quality Assessment | CSIQ-VQA (80/20 train-test) | 19 | Feb 26, 2026 | ||
| Math Word Problem Solving | Math23K | 19 | Feb 26, 2026 | ||
| Video Recognition | HMDB51 (test) | 19 | Feb 26, 2026 | ||
| Dialogue Evaluation | EmpatheticDialogues | 19 | Feb 26, 2026 | ||
| Machine Translation | OPUS-100 (test) | 19 | Feb 27, 2026 |