PII Arena
ONNX detector

ner-ru-gherman-onnx PII detection benchmark

Measured on 9 of 41 retained datasets under the same frozen scoring and masking protocol.

19.10%fully hidden annotations
36.49%detected / overlapped
0.12%extra masking
CPU characters / second

Strengths

Highest complete-masking rates by normalized data type.

People's names63.95%7,059 / 11,039
Addresses & locations54.89%4,889 / 8,907
Logins & usernames19.21%1,689 / 8,791

Watch list

Lowest observed complete-masking rates; inspect before deployment.

Other sensitive attributes0.00%0 / 224
Customer & employee IDs0.00%0 / 1,819
Network identifiers0.00%0 / 18,902

Language coverage

The overall leader can differ from the best choice for one language slice.

LanguageDatasetsFully hidden ↑Detected ↑Extra masking ↓
English423.92%41.31%0.10%
Russian411.98%31.21%0.17%
Multilingual154.95%60.49%

Configuration, source and version

Family
ONNX
Revision
2bd219a78a06657c59fa8c2540ccbad703972e7c
Eligible datasets
9 / 41
Character F1
0.355
Untouched diagnostic
63.51% · 45,789 / 72,095
Benchmark version
1.0.3 · 2026-09-09
CPU seconds / 10k chars
Not measured
GPU seconds / 10k chars
Not measured

mirror of ner-ru-gherman

Results by dataset

Complete masking is primary; detection shows whether any character overlapped.

DatasetGold annotationsFully hidden ↑Detected ↑Extra masking ↓
secrets-issues2880.00%0.00%0.11%
hivetrace1,6670.84%30.17%0.09%
synth-ru-tickets32,0994.70%27.12%
ameau012,24210.26%29.30%0.06%
tab-echr3,83014.39%55.95%
nym-ru9,49725.25%37.61%
nemotron-pii9,39131.80%39.46%0.00%
redmadrobot5,51634.86%44.29%0.19%
kiji-multi7,56554.95%60.49%