Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
Distil-PIIgithub.com · Low evidenceDistil PII is a family of small language models (SLMs) specialized for policy-aware PII redaction, designed to run on-premises or on-device with low latency and cost. After fine-tuning, its 1B model achieves a 0.81 LLM-as-judge score, matching frontier 600B+ models while preserving privacy and operational signals.
Parse Score