{% extends "base.html" %} {% block title %}{{ id }} — bench dashboard{% endblock %} {% block content %}

← runs

{{ id }} {{ rubric_badge.label }}

{{ date }}

{% for w in warnings %}

⚠ {{ w }}

{% endfor %}
{% for row in summary %}
{{ row.label }}{{ row.value }}
{% endfor %}
{% if !outcome_pills.is_empty() %}
{% for o in outcome_pills %} {{ o.label }} {{ o.count }} {% endfor %}
{% endif %}
{% if !hacking.is_empty() %}

⚠ Reward hacking suspected

{% endif %} {% if has_rubrics %}

Rubric averages by lane

{% for lane in lanes %}{% endfor %} {% for row in rubric_rows %} {% for v in row.values %}{% endfor %} {% endfor %}
rubric{{ lane }}avg
{{ row.label }}{{ v }}{{ row.avg }}
{% endif %} {% if !reports.is_empty() %}

Analysis reports

{% for report in reports %}
{{ report.label }} {{ report.filename }}
{{ report.html|safe }}
{% endfor %}
{% endif %}

Rollouts

{{ grid_html|safe }}
{% endblock %}