{% extends "ui/base_ui.html" %} {% block title %}Eval Leaderboard - ATP Platform{% endblock %} {% block content %}
| # | Agent | critical_pass_rate | malformed_rate | mean_rubric | breakpoint | task_type |
|---|---|---|---|---|---|---|
| {{ loop.index }} | {{ e.agent_name }} | {{ "%.3f"|format(e.critical_pass_rate) if e.critical_pass_rate is not none else "—" }} | {{ "%.3f"|format(e.malformed_rate) if e.malformed_rate is not none else "—" }} | {{ "%.3f"|format(e.mean_rubric) if e.mean_rubric is not none else "—" }} | {{ e.breakpoint_axis_level or "—" }} | {{ e.task_type or "—" }} |
No scored eval runs yet. Run atp test method/cases/<suite> to populate the store.