{% extends "base.html" %} {% block title %}Rerank · {{ profile.name }}{% endblock %} {% block content %}
Benchmarks a reranking request's latency and throughput (Lemonade's llamacpp GGUF recipe only --
FastFlowLM doesn't support reranking -- /v1/rerank). Deliberately separate from the
model/router leaderboard -- reranking throughput isn't comparable to LLM token throughput. This runs
synchronously.
Couldn't reach this instance ({{ capabilities.error }}) -- engine and backend fall back to free text.
{% endif %}No rerank results yet.
{% else %}| Timestamp | Model | Latency (ms) | Throughput (/sec) | Documents | Top N | Valid | Notes |
|---|---|---|---|---|---|---|---|
| {{ r.timestamp }} | {{ r.model.name }} | {{ "%.1f"|format(r.metrics.latency_ms) }} | {{ "%.2f"|format(r.metrics.documents_per_sec) }} | {{ r.metrics.document_count }} | {{ r.metrics.top_n or "–" }} | {{ "valid" if r.validity.valid else "invalid" }} | {{ r.validity.notes or "" }} |