Powered Bard and Google Workspace AI, strong multilingual performance
| Benchmark | Score | Rank |
|---|---|---|
HellaSwag Common sense reasoning about everyday situations | 93.4% | #17 / 36 |
ARC-C Grade-school science questions requiring reasoning | 95.1% | #29 / 40 |
MMLU Tests knowledge across 57 subjects from STEM to humanities | 86.1% | #39 / 53 |
HumanEval Coding ability - generating correct Python functions | 64.5% | #44 / 49 |
MATH Competition-level mathematics problems | 48.8% | #45 / 49 |