PIIMB PII Masking - Avg F2: leaderboard
PIIMB evaluates zero-shot PII masking over OpenPII, Gretel, Nemotron-PII, and Privy datasets, with F2, F1, precision, recall, and NER metrics.
Metric: Average F2 (%). Source: huggingface.co. 36 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | OpenMed privacy-filter-multilingual-v2 | 91.68 | |
| 2 | knowledgator gliner-stream-pii-v1.0 | 89.93 | |
| 3 | OpenMed OpenMed-PII-SuperClinical-Large-434M-v1 | 88.52 | |
| 4 | OpenMed privacy-filter-nemotron-v2 | 87.34 | |
| 5 | VidaiUK stirling-minimo-pii-10m | 86.91 | |
| 6 | OpenMed OpenMed-PII-SuperClinical-Small-44M-v1 | 86.79 | |
| 7 | antoniogr7 pii-identifier-v0.1 | 86.23 | |
| 8 | kalyan-ks ettin-68m-nemotron-pii | 84.11 | |
| 9 | fastino gliner2-privacy-filter-PII-multi | 83.48 | |
| 10 | kalyan-ks ettin-32m-nemotron-pii | 83.08 |
Interactive version: theaggregate.ai/benchmark?slug=piimb-pii-masking-avg-f2 · How It Works · Data refreshed daily, snapshot 2026-10-20.