Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1907 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| OOD Detection | ndt2015 OOD WMT15 En-Fr ID (test) | 18 | Feb 26, 2026 | ||
| OOD Detection | ndd2015 (OOD) WMT15 En-Fr (ID) (test) | 18 | Feb 26, 2026 | ||
| OOD Detection | WMT15 Subtitles OOD En-Fr ID (test) | 18 | Feb 26, 2026 | ||
| OOD Detection | Medical (OOD) WMT15 En-Fr (ID) (test) | 18 | Feb 26, 2026 | ||
| OOD Detection | Koran OOD WMT15 En-Fr ID (test) | 18 | Feb 26, 2026 | ||
| OOD Detection | WMT15 En-Fr (ID) IT (OOD) (test) | 18 | Feb 26, 2026 | ||
| Visual World Modelling | AURORA-BENCH Average | 18 | Feb 26, 2026 | ||
| Visual World Modelling | Kubric | 18 | Feb 26, 2026 | ||
| Visual World Modelling | WhatsUp | 18 | Feb 26, 2026 | ||
| Visual World Modelling | Something-Something | 18 | Feb 26, 2026 | ||
| Visual World Modelling | Action Genome | 18 | Feb 26, 2026 | ||
| Visual World Modelling | MagicBrush | 18 | Feb 26, 2026 | ||
| Scientific Question Answering | GPQA | 18 | Feb 26, 2026 | ||
| Logical Reasoning | SynLogic | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | Olympiad | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | AMC | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 25 | 18 | Feb 26, 2026 | ||
| Text Classification | MultiNLI (test) | 18 | Feb 26, 2026 | ||
| Recommendation | Gowalla IID | 18 | Feb 26, 2026 | ||
| Recommendation | Amazon Electronic (IID) | 18 | Feb 26, 2026 | ||
| Recommendation | Amazon Health (IID) | 18 | Feb 26, 2026 | ||
| Safety Alignment | HarmBench | 18 | Feb 26, 2026 | ||
| Safety Alignment | Average (Do-Not-Answer, HarmBench, HH-RLHF, Salad Bench) | 18 | Feb 26, 2026 | ||
| Image Classification | Fashion-MNIST standard (test) | 18 | Feb 26, 2026 | ||
| Multi-modal Representation Learning | MMEB OOD 1.0 | 18 | Feb 26, 2026 |