Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1451 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Zero-shot Language Reasoning | BoolQ, PIQA, HellaSwag, WinoGrande, ARC-e, ARC-c, OBQA, MTQA zero-shot | 21 | Apr 23, 2026 | ||
| Commonsense Question Answering | ARC Challenge | 21 | May 14, 2026 | ||
| Incorrectness detection | NQ-Open | 21 | Apr 23, 2026 | ||
| Incorrectness detection | SQuAD | 21 | Apr 23, 2026 | ||
| English-to-Chinese translation | FLORES-200 | 21 | Apr 23, 2026 | ||
| English-to-Chinese translation | WMT24 | 21 | Apr 23, 2026 | ||
| English-to-Chinese translation | WMT 23 | 21 | Apr 23, 2026 | ||
| English-to-Chinese translation | Our dataset | 21 | Apr 23, 2026 | ||
| Tabular Data Generation | Default | 21 | Apr 23, 2026 | ||
| Safety Evaluation | StrongReject | 21 | May 21, 2026 | ||
| Question Answering | ARC-e | 21 | May 13, 2026 | ||
| Anomaly Detection | MPDD | 21 | Jul 2, 2026 | ||
| DropRegion | DropRegion 100 random (test) | 21 | Apr 21, 2026 | ||
| Multi-robot navigation | Task Empty 100 random 4 robots (test) | 21 | Apr 21, 2026 | ||
| Conveyor Multi-Robot Navigation | Conveyor 100 random 4 robots (test) | 21 | Apr 21, 2026 | ||
| Robot Navigation | Highways 2 robots | 21 | Apr 21, 2026 | ||
| Skeleton-based Action Recognition | PKU-MMD Part II | 21 | Apr 21, 2026 | ||
| Mathematical Reasoning | Average Reasoning Benchmarks | 21 | Apr 21, 2026 | ||
| Mathematical Reasoning | AMC23 | 21 | Apr 21, 2026 | ||
| Mathematical Reasoning | Minvervamath | 21 | Apr 21, 2026 | ||
| Mathematical Reasoning | GSM8K | 21 | Apr 21, 2026 | ||
| Predicate Grounding | ProDG Cooking | 21 | Apr 21, 2026 | ||
| Medical Image Classification | OrganAMNIST | 21 | Jun 2, 2026 | ||
| Information Following | InfoBench | 21 | Apr 21, 2026 | ||
| Aggregated Multimodal Evaluation | Multimodal Evaluation Suite Average | 21 | Apr 21, 2026 |