Skip to benchmark content
← Leaderboard

OpenDisclosure Redaction

SystemMaintainer

OpenDisclosure's model and rule engine, run together by the benchmark harness.

Vendor
OpenDisclosure
Provider
Mistral La Plateforme
Region
EU
Version
pilot 2026-10-14
Composition
Mistral Small 2603 at Mistral EU, with OpenDisclosure's rule engine and detector stages

F2 score

74.3%95% CI 68.0%–79.4%

Leak recall

72.8%95% CI 65.8%–78.6%

Over-redaction

19.1%95% CI 15.3%–24.7%

Output precision

66.1%95% CI 56.3%–72.7%

Cost per 1,000 pages

EUR 0.5195% CI not applicable · measured list-price cost

Recall by bucket

Universal identifiers
75.6%95% CI 66.7%–82.9%
Names
92.2%95% CI 86.3%–95.8%
Contextual personal data
56.6%95% CI 45.4%–64.6%

Breakdowns

Groups below the reporting floor are not shown.

LanguageDocumentsF2RecallOver-redaction
de2473.3%71.7%19.1%
en2478.1%78.3%22.6%
es2276.2%74.6%16.5%
fr2080.7%80.5%18.5%
it2359.5%57.4%29.9%
nl2275.4%73.7%16.8%

Provenance

Dataset version and split
1.0.0-r3+labels.20261006.1 · tuning
Scoring
1.3
Harness version
pilot-2026-10-15
Run date
2026-10-14
Documents
135
Pages
892
Repeats
1
Price date
2026-09-29
Spend
EUR 0.46
Credits
None · paid by OpenDisclosure

Cite this

@misc{eu-redaction-opendisclosure-redaction,
  author = {OpenDisclosure},
  title = {EU Redaction Benchmark: OpenDisclosure Redaction},
  year = {2026},
  url = {https://opendisclosure.eu/benchmark/systems/opendisclosure-redaction/},
  note = {r3-tuning-pilot-2026-10-15; tuning split; scoring 1.3}
}
Download JSON