bench://leaderboard {{ leaderboard | length }} ranked models
{% if leaderboard %} {% for entry in leaderboard %} {% endfor %}
rank provider model max avg avg tokens cost
{{ entry.rank }} {{ entry.model.split('/', 1)[0] if '/' in entry.model else 'unknown' }} {{ entry.model.split('/', 1)[1] if '/' in entry.model else entry.model }} {{ entry.submission_score }} {{ "%.2f"|format(entry.best_average_score) }} {% if entry.get('avg_output_tokens') is not none %}{{ "%.1f"|format(entry.get('avg_output_tokens')) }}{% else %}-{% endif %} {% if entry.get('total_cost') is not none %}${{ "%.4f"|format(entry.get('total_cost')) }}{% else %}-{% endif %}
{% else %}
No benchmark results published yet.
{% endif %}
bench://viewer {% if leaderboard %}{{ leaderboard[0].model }}{% else %}none yet{% endif %}
submission idle
Select a model and load its simulation.