88.3%

Of the text it masked needed masking

On the same 127 judgments: the characters the engine masked that fall inside spans the first annotator marked as direct or quasi-identifiers, out of all the characters it masked. Close to the benchmark's token-level weighted precision, not identical to it.

Updated 16 Oct 2026, from its newest record.

The record it is computed from

Records behind this figure
Record	As stated	Dated	Source
The engine is measured on a public benchmark	We measure the engine on two public benchmarks and publish the result for the…	15 Oct 2026	Pilán et al., TAB, Table 7 discussion; NIST SP…

The engine is measured on a public benchmark
As stated
We measure the engine on two public benchmarks and publish the result for the…
Dated
15 Oct 2026
Source
Pilán et al., TAB, Table 7 discussion; NIST SP…

Each record links to its own page, its source and its permanent copy.

The de-identification standard Every figure