INNER CODE UNIT · Python

mean

wgpsec/AboutSecurity · scripts/bench-skill.py:237

    mean = sum(values) / n
    stddev = math.sqrt(sum((x - mean) ** 2 for x in values) / (n - 1)) if n > 1 else 0.0
    return {
        "mean": round(mean, 4),
        "stddev": round(stddev, 4),
        "min": round(min(values), 4),
        "max": round(max(values), 4),
    }


def generate_benchmark_json(
    skill_name: str,
    skill_path: str,
    all_runs: list[dict],
    model: str,
) -> dict:
    """Generate benchmark.json from collected run data."""
    configs = {}

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…