Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2299 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Face Verification | AgeDB (val) | 16 | Feb 26, 2026 | ||
| Face Verification | LFW (val) | 16 | Feb 26, 2026 | ||
| Point Cloud Registration | 3DLoMatch indoor RGBD (test) | 16 | Feb 26, 2026 | ||
| Point Cloud Registration | 3DMatch indoor RGBD (test) | 16 | Feb 26, 2026 | ||
| Remote Sensing Image Classification | DOTA | 16 | Feb 26, 2026 | ||
| Table Fact Verification | TabFact full | 16 | Feb 26, 2026 | ||
| Table Fact Verification | TabFact full (test) | 16 | Feb 26, 2026 | ||
| Video Question Answering | VCGBench (test) | 16 | Feb 26, 2026 | ||
| Segmentation | Polyp | 16 | Mar 6, 2026 | ||
| Image-to-Web Conversion | IW-BENCH Average | 16 | Feb 26, 2026 | ||
| Image-to-Web Conversion | IW-BENCH (Complex) | 16 | Feb 26, 2026 | ||
| Image-to-Web Conversion | IW-BENCH Medium | 16 | Feb 26, 2026 | ||
| Image-to-Web Conversion | IW-BENCH (Simple split) | 16 | Feb 26, 2026 | ||
| Categorical classification | LaMP-2 (test) | 16 | May 20, 2026 | ||
| Dynamic Facial Expression Recognition | MAFW | 16 | Feb 26, 2026 | ||
| Scene Parsing | Cityscapes (val) | 16 | Feb 26, 2026 | ||
| Multilingual Machine Translation | OPUS-7 | 16 | Feb 26, 2026 | ||
| Multi-hop Question Answering | MuSiQue 2022 | 16 | Feb 26, 2026 | ||
| Human Mesh Recovery | SPEC-MTP (test) | 16 | Feb 26, 2026 | ||
| Language understanding and knowledge | MMLU-Pro | 16 | Mar 10, 2026 | ||
| Anomaly Localization | PCB-Bank (test) | 16 | Feb 26, 2026 | ||
| Performance Prediction | WMT Benchmarks Average WMT'14 & WMT'19 (aggregation) | 16 | Feb 26, 2026 | ||
| Performance Prediction | WMT En-De 2019 (val) | 16 | Feb 26, 2026 | ||
| Performance Prediction | WMT En-Fr 2014 (val) | 16 | Feb 26, 2026 | ||
| Performance Prediction | WMT En-De 2014 (val) | 16 | Feb 26, 2026 |