Trained for $5.5M, proved frontier performance was possible at low cost
| Benchmark | Score | Rank |
|---|---|---|
ARC-C Grade-school science questions requiring reasoning | 96.8% | #21 / 40 |
MATH Competition-level mathematics problems | 90.2% | #24 / 50 |
HumanEval Coding ability - generating correct Python functions | 92.1% | #28 / 50 |
HellaSwag Common sense reasoning about everyday situations | 88.9% | #29 / 36 |
MMLU Tests knowledge across 57 subjects from STEM to humanities | 88.5% | #30 / 54 |
SWE-bench Real-world GitHub issue resolution | 42% | #39 / 40 |
Arena Elo Human preference ranking via blind comparisons | 1318 | #40 / 52 |
TerminalArtificial Analysis Agentic terminal coding tasks requiring multi-step execution | 6.8% | #45 / 48 |
GPQA PhD-level science questions even experts struggle with | 59.1% | #53 / 64 |