Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2214 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Affine-invariant depth estimation | KITTI, NYUv2, ETH3D, ScanNet, DIODE, DA-2K Aggregated | 16 | Mar 18, 2026 | ||
| Affine-invariant depth estimation | DA-2K | 16 | Mar 18, 2026 | ||
| Machine Translation | BOUQuET Overall | 16 | Mar 18, 2026 | ||
| Machine Translation | BOUQuET En-YY | 16 | Mar 18, 2026 | ||
| Machine Translation | BOUQuET XX-En | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ All total | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ En-YY (total) | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ En-YY, v. low resource level | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ En-YY, low resource level | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ En-YY mid resource level | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ En-YY, high resource level | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ XX-En total | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ XX-En v. low resource level | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ XX-En, low resource level | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ XX-En mid resource level | 16 | Mar 18, 2026 | ||
| Translation | FLoRes+ XX-En, high resource level | 16 | Mar 18, 2026 | ||
| Personalized Writing | LongLaMP Wri | 16 | Mar 18, 2026 | ||
| Review Generation | LongLaMP Rev | 16 | Mar 18, 2026 | ||
| Abstractive Summarization | LongLaMP Abs | 16 | Mar 18, 2026 | ||
| Jailbreak Attack | JBB-Behaviors | 16 | Mar 18, 2026 | ||
| Image-to-SVG | SArena-Icon | 16 | Mar 18, 2026 | ||
| General Language Modeling Performance | Aggregate AlpacaEval, TruthfulQA, GSM8K, DROP, AGI Eval, BBH, MMLU | 16 | Mar 18, 2026 | ||
| Mathematical Reasoning | Omni-MATH | 16 | Mar 18, 2026 | ||
| Federated Out-of-Distribution Detection | Cifar-10 | 16 | Mar 18, 2026 | ||
| Out-of-distribution classification | Camelyon17 WILDS OOD (test) | 16 | Apr 21, 2026 |