{% extends "base.html" %} {% block title %}Raw Results{% endblock %} {% block content %}

Raw Results

Run:
Model:
Scenario:
Dataset:
Task:
{% for result in filtered_data %} {% endfor %}

{% for result in filtered_data %}
{% if result['model'].get('prompt') %}

{{result['model']['prompt']}}
{% endif %}

Response: {{result['model']['response']}} {% if result['model'].get('answer') %}
Ground Truth: {{result['model']['answer']}} {% endif %}

    {% for metric_score in result['evaluator']['scores'] %}
  • {{metric_score['name']}}: {{metric_score['score']}}
  • {% endfor %}

{{result['evaluator']['prompt']}}
{% endfor %}
{% endblock %}