{% extends "layout.html" %} {% macro cost_content(result) %} {% if result.cost_usd is not none %} ${{ "%.4f" | format(result.cost_usd) }} {% else %}—{% endif %} {% endmacro %} {% block title %}Results · cua-speedrun{% endblock %} {% block content %}
Published evaluations

Results explorer

Compare model performance, time, and cost within one exact evaluation contract.

Methodology New evaluation
{% if tracks %} {% endif %} {% if track %}
Track {{ track.label }} {{ track.name }}{% if track.gpu %} · {{ track.gpu }}{% endif %}
{% if seasons %}
{% else %}No published contract{% endif %}
{% if season %}
{% if season.benchmark %}Benchmark{{ season.benchmark }}{% endif %} {% if season.hardware %}Hardware{{ season.hardware }}{% endif %} {% if season.algorithm %}Algorithm{{ season.algorithm }}{% endif %} Status{{ season.status }}
{% endif %}
{% endif %} {% if current %}
{{ entry_count }}of {{ entry_count }} results
Rankings

Leaderboard

All included results, ordered by average performance.

{% for result in dashboard_entries %} {% endfor %}
CompareRankModelEffortPerformanceTime / taskCost / taskStatus
{{ loop.index }} {{ result.model }} {% if result.entry_name != result.model %}{{ result.entry_name }}{% endif %} {{ result.effort }} {{ "%.2f" | format(result.performance * 100) }}% {{ "%.1f" | format(result.time_per_task_sec) }}s {{ cost_content(result) }} {% if not result.qualification_known %}Score only{% elif result.reference %}Reference{% elif result.qualifying %}Qualifies{% else %}Below bar{% endif %}{% if result.qualification_known and result.frontier %}Frontier{% endif %}{% if result.provisional %}Provisional{% endif %}
0 selected Select two results
{% else %}

No published results

Run and publish an evaluation to create this track’s first result.

New evaluation
{% endif %} {% endblock %}