{% extends "base.html" %} {% block title %}Classify · {{ profile.name }}{% endblock %} {% block content %}

Classification benchmark · {{ profile.name }}

Benchmarks an ONNX text-classifier's latency and throughput (Lemonade's onnxruntime recipe, /v1/classify). Deliberately separate from the model/router leaderboard -- classification latency isn't comparable to LLM token throughput. This runs synchronously.

{% if capabilities.error %}

Couldn't reach this instance ({{ capabilities.error }}) -- engine and backend fall back to free text.

{% endif %}
{% if classify_models %} {% else %}
No onnxruntime classifier models pulled yet on this profile -- pull one via lemonmatrix profile pull-model (recipe onnxruntime), then reload this page.
{% endif %}
{% if classify_backends %} {% else %}
No onnxruntime backend detected -- install it on the profile page first, or enter it manually.
{% endif %}
{% if default_os %}
{{ default_os }} (fixed by this profile)
{% else %}
Couldn't detect -- see profile page to fix discovery.
{% endif %}

Classify results for {{ profile.name }}

{% if not results %}

No classify results yet.

{% else %}
{% for r in results %} {% endfor %}
TimestampModelLatency (ms)Throughput (/sec)Top KValidNotes
{{ r.timestamp }} {{ r.model.name }} {{ "%.1f"|format(r.metrics.latency_ms) }} {{ "%.2f"|format(r.metrics.classifications_per_sec) }} {{ r.metrics.top_k or "–" }} {{ "valid" if r.validity.valid else "invalid" }} {{ r.validity.notes or "" }}
{% endif %}
{% endblock %}