Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 406 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Classification | PAMAP2 | 48 | Apr 3, 2026 | ||
| Classification | PAMAP2 original and sensor dropout | 48 | Apr 3, 2026 | ||
| Susceptibility to adversarial fine-tuning | ImageNet | 48 | Apr 3, 2026 | ||
| Mean function estimation | DTI | 48 | Apr 2, 2026 | ||
| Mean function estimation | Electricity Demand | 48 | Apr 2, 2026 | ||
| Failure Detection | WORM-Nem | 48 | Apr 1, 2026 | ||
| Out-of-Distribution Detection | LIDC-Tex | 48 | Apr 1, 2026 | ||
| Out-of-Distribution Detection | LIDC-Mal | 48 | Apr 1, 2026 | ||
| Out-of-Distribution Detection | ARC-Nuc | 48 | Apr 1, 2026 | ||
| Out-of-Distribution Detection | ARC-BC | 48 | Apr 1, 2026 | ||
| Failure Detection | LIDC-Tex | 48 | Apr 1, 2026 | ||
| Failure Detection | LIDC-Mal | 48 | Apr 1, 2026 | ||
| Failure Detection | CAR-CS | 48 | Apr 1, 2026 | ||
| Failure Detection | ARC-Nuc | 48 | Apr 1, 2026 | ||
| Failure Detection | ARC BC | 48 | Apr 1, 2026 | ||
| Cross-modal Retrieval | AEA 553 events (test) | 48 | Apr 1, 2026 | ||
| Predicting answer correctness | TruthfulQA | 48 | May 7, 2026 | ||
| Medical Reasoning | PubMedQA | 48 | Jul 7, 2026 | ||
| Anomaly Detection | ESA-ADB | 48 | May 11, 2026 | ||
| Roadmap Update | Environment Size 20x20x20 | 48 | Mar 31, 2026 | ||
| Active Learning | Ilpd | 48 | Jun 9, 2026 | ||
| Weather Forecasting | ISD 10% few-shot (test) | 48 | Mar 31, 2026 | ||
| Machine Translation | English-to-German (En-De) | 48 | Mar 27, 2026 | ||
| Code Generation | MBPP | 48 | Jun 12, 2026 | ||
| Image Classification | ImageNet-LT | 48 | Mar 26, 2026 |