Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1658 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Feature Matching | MegaDepth extreme-scale (test) | 20 | Feb 26, 2026 | ||
| Relative Pose Estimation | MegaDepth extreme-scale (test) | 20 | Feb 26, 2026 | ||
| Infrared Image Classification | LLVIP | 20 | May 19, 2026 | ||
| Cross-file code completion | CrossCodeEval (test) | 20 | Mar 18, 2026 | ||
| Detection | KUMC | 20 | Feb 26, 2026 | ||
| Open-domain Question Answering | TriviaQA | 20 | Jun 11, 2026 | ||
| Coreference Resolution | CLUEWSC | 20 | Apr 30, 2026 | ||
| Referring Expression Grounding | RefCOCO+ | 20 | Jun 8, 2026 | ||
| Referring Expression Grounding | RefCOCO | 20 | Jun 8, 2026 | ||
| Instrument Classification | Beijing Opera | 20 | Jun 18, 2026 | ||
| Segmentation | OASIS3 (test) | 20 | Apr 23, 2026 | ||
| Segmentation | IBIS-subcort (test) | 20 | Feb 26, 2026 | ||
| Math Word Problem solving | SVAMP English (test) | 20 | Feb 26, 2026 | ||
| Semantic Segmentation | PascalVOC | 20 | Apr 21, 2026 | ||
| Face Verification | AgeDB-30 | 20 | Feb 26, 2026 | ||
| Long-term forecasting | Electricity | 20 | Feb 26, 2026 | ||
| Unsupervised video summarization | TVSum (unsupervised) | 20 | Feb 26, 2026 | ||
| Unsupervised video summarization | SumMe unsupervised | 20 | Feb 26, 2026 | ||
| Audio Question and Answering | ClothoAQA | 20 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 standard (test) | 20 | Feb 26, 2026 | ||
| Common-sense QA | PIQA | 20 | Jun 5, 2026 | ||
| Multimodal Understanding | SEED-Bench Image (test) | 20 | Feb 26, 2026 | ||
| Image Classification | StanfordCars (test) | 20 | Mar 30, 2026 | ||
| Image Classification | CIFAR-100 | 20 | Feb 26, 2026 | ||
| Semantic Segmentation | COCO 3697 labels (1/32) | 20 | Feb 26, 2026 |