{% extends 'base.html' %} {% block title %}Benchmark Tasks ยท yawn.memory{% endblock %} {% block body_class %}bench-runs-page{% endblock %} {% block app_main %}
BENCHMARK TASKS

LongMemEval Run Browser

Browse LME benchmark runs, inspect per-task scores, and (for the active run) view live graph projections.

bench-inspection/v1 Read-only artifact explorer
{% if runs %}
{% for run in runs %}

{{ run.label }}

{% if run.is_active %} ACTIVE {% elif run.live_graph_source_run_id %} LIVE SOURCE {% else %} ARTIFACT {% endif %}
variant: {{ run.variant }} {{ run.completed_items }}/{{ run.total_items }} items {% if run.started_at %} {{ run.started_at[:10] }} {% endif %}
{% if run.source_warning %}
{{ run.source_warning }}
{% endif %}
{% endfor %}
{% elif configured is false %}

Benchmark catalog is not configured.

Set MENHIR_BENCH_RESULTS_ROOT to point at the archolith-bench results directory.

{% else %}

No benchmark runs found.

The results directory does not contain any run data.

{% endif %}
{% endblock %} {% block extra_head %} {% endblock %}