{% extends "base.html" %} {% block title %}Evaluation #{{ evaluation.id }} — evalkit{% endblock %} {% block content %}
Projects / Project #{{ evaluation.project_id }} / Evaluation #{{ evaluation.id }}
Suite
{{ evaluation.suite_name }}
Status
{{ evaluation.status.value }}Average Score
{% if evaluation.average_score is not none %} {% set pct = (evaluation.average_score * 100) | int %}{{ pct }}%
{% else %}—
{% endif %}Test Cases
{{ evaluation.results | length }}
No tags
{% endif %}{{ tc.question }}
Expected
{% for tool in (tc.expected_tool_calls or []) %}{{ tool.parameters | tojson(indent=2) }}
{% endif %}
Actual
{% for tool in (tc.actual_tool_calls or []) %} {% set idx = loop.index0 %} {% set expected_list = tc.expected_tool_calls or [] %} {% set name_match = idx < expected_list | length and expected_list[idx].name == tool.name %}{{ tool.parameters | tojson(indent=2) }}
{% endif %}
⏳
Evaluation in progress
Results will appear here once complete.
{% else %}📭
No results available
{% endif %}