Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 918 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Named Entity Recognition | NCBI | 29 | Apr 8, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP N=50 10,000 instances (test) | 29 | May 21, 2026 | ||
| Temporal Knowledge Graph Completion | ICEWS14 v1 (test) | 29 | Feb 26, 2026 | ||
| Layer Segmentation | Retinal OCT (test) | 29 | Mar 26, 2026 | ||
| Cell classification | Cell classification dataset (test) | 29 | Feb 26, 2026 | ||
| State change classification | Ego4D v1 (test) | 29 | Feb 26, 2026 | ||
| Next-Item Recommendation | Fashion Amazon (test) | 29 | Feb 26, 2026 | ||
| Next-Item Recommendation | Men Amazon (test) | 29 | Feb 26, 2026 | ||
| Predicate Classification | VG 50 (test) | 29 | Feb 26, 2026 | ||
| Semantic Correspondence | SPair-71k | 29 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 (test) | 29 | Mar 24, 2026 | ||
| Object Detection | FSCD-147 (test) | 29 | Feb 27, 2026 | ||
| Semantic Segmentation | FSS-1000 5-shot | 29 | May 20, 2026 | ||
| Bird's Eye View Object Detection | KITTI official leaderboard (test) | 29 | Feb 26, 2026 | ||
| Image Captioning | MSCOCO (test) | 29 | Feb 26, 2026 | ||
| Language modeling | PG-19 (val) | 29 | Jun 11, 2026 | ||
| Image Retrieval | Revisited Paris (RPar) Hard v1 | 29 | Feb 26, 2026 | ||
| Image Retrieval | Revisited Oxford (ROxf) v1 (Hard) | 29 | Feb 26, 2026 | ||
| Image Retrieval | Revisited Paris (RPar) Medium v1 | 29 | Feb 26, 2026 | ||
| Image Retrieval | Revisited Oxford (ROxf) v1 (Medium) | 29 | Feb 26, 2026 | ||
| Tabular Data Classification | UCI machine learning repository 21 datasets (test) | 29 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100-LT gamma=50 (test) | 29 | May 29, 2026 | ||
| Time-series Generation | Stocks | 29 | Mar 17, 2026 | ||
| Out-of-distribution (OOD) detection | CIFAR100 In-Distribution Place365 Out-of-Distribution (test) | 29 | May 21, 2026 | ||
| Time Series Forecasting | VISUELLE (test) | 29 | Feb 26, 2026 |