RAG Eval — {{ report.suite }} {% if report.gate.passed %}PASSED{% else %}FAILED{% endif %}

{{ report.provider }}:{{ report.model }} · {{ report.created_at }}
Questions
{{ report.summary.n_questions }}
{% for m in quality_metrics %}{% if m in report.summary.quality %}
{{ m }}
{{ '%.2f'|format(report.summary.quality[m]) }}
{% endif %}{% endfor %}
p95 latency
{{ '%.0f'|format(report.summary.latency_p95_ms) }} ms
total cost
${{ '%.4f'|format(report.summary.total_cost_usd) }}

Gate checks

{% for c in report.gate.checks %} {% endfor %}
CheckValueThresholdResult
{{ c.name }} {{ c.value }} {{ c.threshold if c.threshold is not none else '' }} {% if c.passed %}PASS{% else %}FAIL{% endif %}

Per-question

{% for m in quality_metrics %}{% endfor %} {% for q in report.questions %} {% for m in quality_metrics %} {% if m in q.metrics %} {% set v = q.metrics[m].value %} {% else %}{% endif %} {% endfor %} {% endfor %}
IDQuestion{{ m[:4] }}ms$
{{ q.id }} {{ q.question }}{{ '%.2f'|format(v) }}—{{ '%.0f'|format(q.latency_ms) }} {{ '%.4f'|format(q.cost_usd) }}