{% extends "layout.html" %} {% block title %}Tracks · cua-speedrun{% endblock %} {% block content %} {% if track %}
Track contract

{{ track.name }}

{{ track.algorithm.summary }}

{{ track.gpu or "CPU" }} {{ track.algorithm.label }}
Fixed by maintainers

Agents per evaluation, scoring, seed policy, and execution defaults.

Chosen for each evaluation

Benchmark, agent, GPU type, algorithm, parallel evaluations, and execution placement.

Default evaluation algorithm

{{ track.algorithm.label }}

{{ track.algorithm.key }}
Evaluation replica 1 User-scaled independently
{% if track.algorithm.shared_compute %}
Reusable compute 1 Shared across task batches
Active agents{{ track.agents_per_evaluation }}Per evaluation
Prepared env pool{{ track.environment_pool_size }}{{ track.algorithm.environment_pool_factor }}× agent slots
{% else %}
Isolated task slots {{ track.agents_per_evaluation }} Fresh compute + VM per task
{% endif %}
Agent mode{{ track.algorithm.agent_mode }} Parallel evaluations{{ "Supported" if track.algorithm.supports_parallel_evaluations else "Fixed at one" }} Runtime capabilities{{ track.algorithm.required_capabilities | join(", ") or "None" }}
01

Resources

Default GPU
{{ track.gpu or "None" }}
Agents / evaluation
{{ track.agents_per_evaluation }}
Prepared env pool
{{ track.environment_pool_size }}
02

Scoring

Success bar
{{ "%.0f" | format(track.success_percent) }}%
Ranking
{{ track.ranking_rule }}
Failed task charge
{{ track.failure_charge }}
03

Sampling

Runs / task
{{ track.runs_per_task }}
Seed policy
{{ track.seed_policy }}
Leaderboard role
{{ "Reference only" if track.reference_only else "Competitive" }}
Current installation

Compatible execution

{% if track.supported_topologies %}
{% for topology in track.supported_topologies %}
{{ topology.label }}{{ topology.key }}
{% endfor %}
{% else %}

No registered execution topology provides this algorithm's required capabilities.

{% endif %}
Implementation

Versioned Python module

{{ track.algorithm.source_file }} {% if track.algorithm.aliases %}

Aliases: {{ track.algorithm.aliases | join(", ") }}

{% endif %}

The algorithm code is included in the run's measurement hash.

{% if track.server_config %}
Track server configurationJSON
{{ track.server_config | tojson(indent=2) }}
{% endif %} {% if track.algorithm.source %}
Algorithm source{{ track.algorithm.source_file }}
{{ track.algorithm.source }}
{% endif %}
{% else %}

No tracks registered

Add a track to catalog/tracks.yaml and restart the dashboard.

{% endif %} {% endblock %}