PII Arena
GLINER detector

gliner-urchade+cpu-int8 PII detection benchmark

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

0.00%fully hidden annotations
0.00%detected / overlapped
0.00%extra masking
CPU characters / second

Strengths

Highest complete-masking rates by normalized data type.

Passwords, keys & tokens0.00%0 / 1,684
Logins & usernames0.00%0 / 8,791
Bank accounts & cards0.00%0 / 1,880

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 ↓
English40.00%0.00%0.00%
Russian40.00%0.00%0.00%
Multilingual10.00%0.00%

Configuration, source and version

Family
GLINER
Revision
1fcf13e85f4eef5394e1fcd406cf2ca9ea82351d
Eligible datasets
9 / 41
Character F1
0.000
Untouched diagnostic
100.00% · 72,095 / 72,095
Benchmark version
1.0.3 · 2026-09-09
CPU seconds / 10k chars
Not measured
GPU seconds / 10k chars
Not measured

Results by dataset

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

DatasetGold annotationsFully hidden ↑Detected ↑Extra masking ↓
ameau012,2420.00%0.00%0.00%
hivetrace1,6670.00%0.00%0.00%
kiji-multi7,5650.00%0.00%
nemotron-pii9,3910.00%0.00%0.00%
nym-ru9,4970.00%0.00%
redmadrobot5,5160.00%0.00%0.00%
secrets-issues2880.00%0.00%0.00%
synth-ru-tickets32,0990.00%0.00%
tab-echr3,8300.00%0.00%