{% extends "base.html" %} {% block title %}Eval Runs — AI Reliability Platform{% endblock %} {% block content %} {% if runs %} {% for r in runs %} {% endfor %}
RunProviderModelStatusPass RateAvg LatencyCostCreated
#{{ r.id }} {{ r.provider }} {{ r.model }} {{ r.status }} {{ "%.1f"|format(r.passed_cases / r.total_cases * 100) if r.total_cases > 0 else "N/A" }}% {{ "%.0f"|format(r.avg_latency_ms) }}ms ${{ "%.4f"|format(r.estimated_cost) }} {{ r.created_at.strftime("%Y-%m-%d %H:%M") }}
{% else %}
No eval runs yet. Start one via the API:
curl -X POST http://localhost:8000/api/v1/eval/runs \
  -H "Content-Type: application/json" \
  -d '{"dataset_id": 1, "provider": "groq", "model": "llama-3.3-70b-versatile"}'
{% endif %} {% endblock %}