Near-frontier performance at flash pricing, native tool use and code execution
| Benchmark | Score | Rank |
|---|---|---|
HellaSwag Common sense reasoning about everyday situations | 94.1% | #16 / 36 |
ARC-C Grade-school science questions requiring reasoning | 96.2% | #28 / 40 |
HumanEval Coding ability - generating correct Python functions | 89.5% | #32 / 50 |
MMLU Tests knowledge across 57 subjects from STEM to humanities | 88.1% | #34 / 54 |
MATH Competition-level mathematics problems | 77.2% | #34 / 50 |
Arena Elo Human preference ranking via blind comparisons | 1290 | #42 / 52 |
GPQA PhD-level science questions even experts struggle with | 62.1% | #51 / 64 |