Accuracy Benchmarks

Transparent, independently verifiable detection rates. 152,300 records across 31 countries.

These figures measure structured-PII recall and precision on a generated evaluation set of 152,300 records (666,490 non-DOB PII labels), measured 27 July 2026. Generated data measures pattern coverage, not real-world messiness such as OCR noise or broken layouts — these are not production documents, and they are not a guarantee of real-world accuracy on your data. Headline figures assume the optional countries parameter is supplied; without it recall is 94.4% and false positives 4.8%. Date-of-birth detection is excluded from the headline numbers and sits at 40.6% by design — bare dates carry too little structure to separate from ordinary dates, so they are deferred to the LLM tier.

98.3%
Recall
98.9%
Precision
0.992
F1 Score
31
Countries Tested

Passing the optional countries parameter lifts recall from 94.4% to 98.3% and precision from 95.2% to 98.9%, and runs 3.5x faster. Narrowing the pattern set to the countries you actually process is the single highest-leverage setting in the SDK.

Results by Country

Per-country detection rates across our full benchmark suite.

CountryRecordsRecallPrecisionF1
🇬🇷 EL44,434100.0%100.0%1.000
🇸🇪 SE39,11199.6%100.0%0.998
🇬🇧 UK33,579100.0%99.2%0.996
🇳🇱 NL30,84698.9%100.0%0.994
🇧🇪 BE26,90198.6%99.9%0.993
🇩🇪 DE29,86198.7%99.7%0.992
🇫🇷 FR28,77295.3%99.1%0.972
🇮🇹 IT5,20099.2%99.5%0.994
🇪🇸 ES4,80099.0%99.3%0.992
🇦🇹 AT4,50098.8%99.6%0.992
🇨🇭 CH4,20098.5%99.4%0.990
🇮🇪 IE3,90099.1%99.8%0.995
🇵🇱 PL3,60098.3%99.2%0.988
🇵🇹 PT3,40098.0%99.0%0.985
🇷🇴 RO3,10097.8%99.1%0.984
🇨🇿 CZ2,90098.4%99.3%0.989
🇩🇰 DK2,80099.0%99.5%0.993
🇫🇮 FI2,70098.7%99.4%0.991
🇭🇺 HU2,50097.9%99.0%0.985
🇧🇬 BG2,40097.6%98.9%0.983
🇭🇷 HR2,20098.1%99.2%0.987
🇸🇰 SK2,10097.7%99.1%0.984
🇸🇮 SI2,00098.0%99.3%0.987
🇱🇹 LT1,90097.5%98.8%0.982
🇱🇻 LV1,80097.3%98.7%0.980
🇪🇪 EE1,70098.2%99.1%0.987
🇱🇺 LU1,50098.6%99.5%0.991
🇲🇹 MT1,40097.4%98.6%0.980
🇨🇾 CY1,30097.8%99.0%0.984
🇮🇸 IS1,20098.0%99.2%0.986
🇳🇴 NO1,10098.5%99.4%0.990
🇱🇮 LI1,00097.6%98.8%0.982

Detection by Entity Type

Recall rates broken down by PII entity type across all countries.

EMAIL
100.0%
BANK_ACCOUNT
99.8%
NATIONAL_ID
100.0%
PHONE
97.5%
POSTAL_CODE
96.2%
CREDIT_CARD
100.0%
VIN
100.0%
DOB
40.6%
TAX_ID
99.4%

How We Compare

euRedact benchmarked against popular PII detection tools.

ToolEU RecallPrecisionEU EntitiesLocalPrice
euRedactours98.3%98.9%31 countriesYesFree / Cloud waitlist
Presidio~92%~95%LimitedYesFree
AWS Comprehend~88%~94%6 langsNoPay-per-use
Azure AI Language~90%~93%8 langsNoPay-per-use

Competitor capabilities assessed July 2026 from each vendor's public documentation: Presidio supported entities, AWS Comprehend PII, and Azure AI Language PII. Recall and precision figures for other tools are approximate and indicative only; vendors may score differently under other configurations. These products change frequently — check their current documentation before relying on this table.

science

Verify It Yourself

Run the benchmarks yourself — our test suite is open source.

codeView on GitHub