Back to Pulse

ThreatPrint benchmark

April 13, 2026 benchmark claim: 96% detection / 0% false positives. This page summarizes what is published and labels unpublished fields honestly.

Methodology

The published run used the Pulse-Proxy extended benchmark script against the production proxy with attack and clean prompt corpora. Attack prompts count as detected when blocked or warned. Clean prompts count as false positives when blocked or warned.

Corpus size

Published summary: 100 attack prompts and 100 clean prompts. If this changes, update the benchmark artifact and this page together.

Confusion matrix

True positives96published April 13 run
False negatives4published April 13 run
False positives0published April 13 run
True negatives100published April 13 run

Latency table

p50pending publication
p95pending publication
p99pending publication

Reproducibility instructions

  1. Clone Pulse-Proxy.
  2. Set PULSE_KEY for a valid test key.
  3. Run scripts/extended-benchmark.ps1.
  4. Publish results/benchmark-summary.md and the commit/version used.

Failure cases

The April 13 run included missed attack prompts in encoded/obfuscated categories. Do not claim 100% detection.

Commit/version

Package version and rule bundle are published in the benchmark artifact; exact release commit for this public page is pending publication.