{% load json_filters %}
{{ scenario_description }}
{% endif %} {% if expected_behavior %}Expected behaviour
Test prompt
{{ test_prompt }}
Verdict = most common severity
{{ agreement_rate|floatformat:0 }}%
Agreement
{{ severity }}
Verdict
{{ n_reps }}×
Repetitions
{% include "partials/icon.html" with name="triangle-alert" cls="w-3.5 h-3.5 -mt-0.5 mr-1" %}Low judge agreement. This verdict may be unstable; compare the repetitions below or increase repetitions.
{% endif %}{{ raw_json }}
No result data available for this scenario.