Skip to content
CreatorPrivacyKit
Learn Blog Privacy @mollycoddle330

CreatorPrivacyKit Labs · Benchmark v1 · September 2026

Multilingual Browser OCR Benchmark

Evaluating client-side Tesseract.js 5.1.1 across 10 controlled multilingual document scenes. Tested on September 20, 2026.

Engine: Tesseract.js 5.1.1 · Tessdata: 4.0.0_best_int · OEM: 1 (LSTM) · PSM: 6 · Zero cloud upload

Multilingual Browser OCR Benchmark?

CreatorPrivacyKit Labs · Benchmark v1 · September 2026 Evaluating client-side Tesseract.js 5.1.1 across 10 controlled multilingual document scenes. Tested on September 20, 2026. This benchmark evaluates CreatorPrivacyKit's browser-based OCR against our current multilingual fixture set. It is a product regression benchmark, not a universal ranking of OCR engines.

Last updated

Verified Tested by CreatorPrivacyKit Labs · September 20, 2026 · OCR Benchmark v1 (2026-09)

Scope & Intent

This benchmark evaluates CreatorPrivacyKit's browser-based OCR against our current multilingual fixture set. It is a product regression benchmark, not a universal ranking of OCR engines.

All processing runs client-side using WebAssembly and Web Workers. No file bytes leave the browser. These tests examine what happens when users process realistic photographed documents without cloud APIs or pre-filtering.

  • What was tested: 10 synthetic controlled scenes representing office invoices, restaurant menus, community notices, clinic forms, and shipping labels across 10 distinct scripts/languages.
  • What was NOT tested: Handwritten notes, historical manuscripts, distorted CAPTCHAs, or customer-identifiable private records. Decorative extra objects in the scene (such as mugs or adjacent wall art) are excluded from ground truth.

Executive Scorecard

Scored on exact key-field substring match after Unicode NFC normalization. PASS requires ≥95% key fields with no numeric corruption.

Pass Rate 1 of 10 German spec sheet
Warning Rate 1 of 10 English invoice
Fail Rate 8 of 10 CJK, Latin complex, RTL
Mean Key Fields 54.1% Numeric exact: 60.8%
Multilingual Browser OCR Benchmark — 2026-09 Engine Run
Language / Fixture Pack CER WER Key Fields Numeric Exact Email Exact URL Exact Verdict
العربية
OCR-AR-2026-010		 ara 0.638 —* 0% (0/11) 0% 0% 0% FAIL
Deutsch
OCR-DE-2026-007		 deu 0.302 0.738 100% (11/11) 100% 100% 100% PASS
English
OCR-EN-2026-001		 eng 0.178 0.265 93.8% (15/16) 100% 100% 100% WARN
Español
OCR-ES-2026-005		 spa 0.527 1.200 62.5% (10/16) 58.3% 0% 100% FAIL
Français
OCR-FR-2026-006		 fra 0.402 0.809 83.3% (10/12) 87.5% 100% 100% FAIL
हिन्दी
OCR-HI-2026-009		 hin 0.607 —* 22.2% (2/9) 20% 0% 0% FAIL
日本語
OCR-JA-2026-003		 jpn 0.667 —* 27.8% (5/18) 33.3% 100% 100% FAIL
한국어
OCR-KO-2026-004		 kor 0.627 0.860 63.6% (7/11) 85.7% 0% 0% FAIL
Português
OCR-PTBR-2026-008		 por 0.431 0.900 70% (7/10) 83.3% 0% 100% FAIL
简体中文
OCR-ZH-2026-002		 chi_sim 0.668 —* 18.2% (2/11) 40% 0% 0% FAIL

* Scripts without space word boundaries (Chinese, Japanese, Hindi, Arabic) report CER and exact key-field accuracy. WER is only evaluated for space-delimited Latin and Hangul scripts.

Visual Evidence Highlights

View all 10 fixtures & failure breakdown →

Below are 4 representative fixtures from the benchmark showing rendered test images, expected ground truth, and observed character-level behavior.

OCR-DE-2026-007 German Technical product sheet on clipboard
pack: deu PASS
OCR-DE-2026-007 test fixture: Technical product sheet on clipboard
Fixture OCR-DE-2026-007 · Controlled scene
Key Field Accuracy 100%
CER (Error Rate) 0.302
Expected Ground Truth (sample) 
Geräteübersicht
Dokument-Nr.: OCR-DE-2026-007
Produkt: MobileScan Pro 12
Hersteller: DatenWerk GmbH
Recognized Output (Tesseract.js)
✓ What survived:
  • 100% key-field accuracy (11 of 11 fields exact match).
  • Umlauts and German typography exact: 'Geräteübersicht', 'Auflösung', 'Lindenstraße'.
  • Exact decimal comma preserved in weight: '1,35 kg'.
  • Serial code 'MSP12-DE-884209', email 'support@datenwerk.de', and URL 'https://datenwerk.de/manual' fully matched.
✕ Failure observations:
  • High-contrast printed paper succeeded; camera photos with background clutter or low DPI require human review.
View full row metrics in results table →
OCR-EN-2026-001 English Office invoice photographed on a desk
pack: eng WARN
OCR-EN-2026-001 test fixture: Office invoice photographed on a desk
Fixture OCR-EN-2026-001 · Controlled scene
Key Field Accuracy 93.8%
CER (Error Rate) 0.178
Expected Ground Truth (sample) 
INVOICE
Invoice No: OCR-EN-2026-001
Date: 2026-09-20
Bill To: Harbor Metrics LLC
Recognized Output (Tesseract.js)
✓ What survived:
  • 15 of 16 key fields matched (93.8% key-field accuracy).
  • Financial figures exact: Subtotal $134.00, Tax $11.06, Grand Total $145.06.
  • Itemized pricing exact: $49.50, $99.00, $35.00.
  • Email 'billing@harbormetrics.com' and payment URL matched.
✕ Failure observations:
  • Large stylized title 'INVOICE' missed due to oversized display font weight.
  • Desk background mug and plant pixels caused noise in border tokens.
View full row metrics in results table →
OCR-JA-2026-003 Japanese Restaurant menu board
pack: jpn FAIL
OCR-JA-2026-003 test fixture: Restaurant menu board
Fixture OCR-JA-2026-003 · Controlled scene
Key Field Accuracy 27.8%
CER (Error Rate) 0.667
Expected Ground Truth (sample) 
本日のおすすめ
店舗コード：OCR-JA-2026-003
営業時間 11:30-22:00
住所：東京都新宿区西新宿2-8-1
Recognized Output (Tesseract.js)
✓ What survived:
  • Email 'info@tokyoramen.jp' and URL 'https://tokyoramen.jp' exact.
  • Restaurant hours and shop identifier matched.
✕ Failure observations:
  • Yen price format broken: '1,080円' became '1.080' (comma to period, 円 symbol lost).
  • Kanji substitution: '醤油' (soy sauce) recognized as '普油'.
  • Food photograph background noise read as ghost kanji ('隊暫要衣', 'ワニ').
View full row metrics in results table →
OCR-AR-2026-010 Arabic Clinic information sheet and appointment card
pack: ara FAIL
OCR-AR-2026-010 test fixture: Clinic information sheet and appointment card
Fixture OCR-AR-2026-010 · Controlled scene
Key Field Accuracy 0%
CER (Error Rate) 0.638
Expected Ground Truth (sample) 
مركز النور الطبي
المرجع: OCR-AR-2026-010
التاريخ: 20-09-2026
العنوان: شارع الملك فهد، مبنى 18، الرياض
Recognized Output (Tesseract.js)
✓ What survived:
  • Phone digit sequence partly visible (+966 11 555 2480).
✕ Failure observations:
  • 0 of 11 key fields matched (0% key-field accuracy).
  • Arabic cursive ligatures and shaping lost on two-document desk scene.
  • Latin email domain truncated and colon corrupted: 'hitps:/alnourmed:s2'.
View full row metrics in results table →

Reproduce this benchmark locally

Every number published on this page can be re-executed directly from the source repository. No private keys or cloud accounts are required.

  1. Clone the repository: git clone https://github.com/ggggghhhhyyyy/creator-privacy-kit
  2. Install dependencies: npm install
  3. Run the official engine benchmark: 
    npm run benchmark:ocr -- --engine
  4. Run the browser E2E verification test: 
    npm run benchmark:ocr -- --e2e

Runtime environment: Node.js v22+ on Linux / macOS / Windows with Chrome installed for optional E2E. Ground truth strings and fixture hashes are defined in tests/fixtures/ocr-multilingual/manifest.json.

Cite this benchmark

Empirical research published by CreatorPrivacyKit Labs is freely citeable with attribution under CC BY 4.0.

APA / Text Format 
CreatorPrivacyKit Labs. (2026). Multilingual Browser OCR Benchmark (Version 1.0) [Data set]. CreatorPrivacyKit. https://creatorprivacykit.com/labs/ocr-benchmark/
View BibTeX entry 
@misc{creatorprivacykit_2026_ocr_benchmark,
  title = {Multilingual Browser OCR Benchmark},
  author = {{CreatorPrivacyKit Labs}},
  year = {2026},
  version = {1.0},
  howpublished = {\url{https://creatorprivacykit.com/labs/ocr-benchmark/}},
  note = {Tested 2026-09-20. In-browser Tesseract.js 5.1.1 multilingual evaluation}
}
Data sources: Dataset landing & download · results.json · results.csv