AlignEval Evaluation Report

Generated: {{ timestamp }}

Summary

Total Cases
{{ summary.total_cases }}
Passed
{{ summary.passed_cases }} ({{ (summary.passed_cases / summary.total_cases * 100)|round(1) }}%)
Average Score
{{ summary.average_score|round(3) }}

Metric Averages

{% for metric, score in summary.metric_averages.items() %}
{{ metric }} {{ score|round(3) }}
{% endfor %}

Detailed Results

{% for result in results %} {% endfor %}
Input Output Overall Score Status Metrics
{{ result.test_case.input[:100] }}{% if result.test_case.input|length > 100 %}...{% endif %}
{{ result.test_case.actual_output[:100] }}{% if result.test_case.actual_output|length > 100 %}...{% endif %}
{{ result.overall_score|round(3) }} {{ 'PASSED' if result.passed else 'FAILED' }} {% for mr in result.metric_results %}
{{ mr.metric_name }}: {{ mr.normalized_score|round(3) }} {% if mr.error %} (Error: {{ mr.error }}) {% endif %}
{% endfor %}