harness-evaluator Dashboard
Runs
API: Runs
Runs
{% if runs %} {% for run in runs %}
{{ run.run_name }}
{{ run.total_cells }}
cells
{{ run.passed }}
passed
{{ run.failed }}
failed
${{ "%.4f"|format(run.total_cost) }}
cost
{{ "%.1f"|format(run.avg_success * 100) }}%
avg success
{% endfor %} {% else %}
No runs found. Execute an eval with
harness-evaluator run
first.
{% endif %}