πŸ–‹οΈ Hebrew Handwriting OCR Leaderboard

Welcome to the Hebrew Handwriting OCR Leaderboard β€” a community-driven effort to track and compare how well models read Hebrew handwritten manuscripts.

Maintained by ivrit.ai (Hugging Face), a project advancing Hebrew-language AI. Evaluation data is crowdsourced through transcriptor.ivrit.ai, where volunteers transcribe scanned Hebrew handwriting.

Why this exists

Hebrew handwriting is hard for OCR: no vowels, fused prepositions and clitics, cursive hands that vary by writer and period, final-form letters, ligatures, and inconsistent historical spelling. This leaderboard standardizes evaluation, tracks progress, and builds community around Hebrew handwriting recognition.

Benchmark v1 β€” clean-test

10 held-out pages, 10 different hands, 225 lines β€” each independently transcribed and adjudicated into gold-standard ground truth. Harder, larger batches are coming.

Normalization

Punctuation and whitespace are canonicalized before scoring (Hebrew text itself is untouched).

Models

The newest vision model from each major provider (Anthropic / OpenAI / Google), across three size tiers. Maintainer-run β€” no submission flow; results refresh when a provider ships a new model.

Reproduce it yourself

Full pipeline β€” corpus, adjudication tool, eval harness, this page β€” lives in ocr-eval-ivrit. Want to see line-by-line results? Open the comparison viewer.

Leaderboard

Line mode. The model is handed a single cropped line of handwriting and must return its text β€” the easier task, segmentation already done. Ranked by CER (character error rate, lower is better): the edit distance to the adjudicated line, on normalized text. The number is the median line; the range in parentheses is the 25th–75th percentile across lines. Outputs with no text are dropped.

ProviderModelCER median ↓▲
googlegemini-flash0.119 (0.00–0.50)
googlegemini-flash-lite0.280 (0.11–0.44)
openaigpt-5.6-sol0.440 (0.25–0.57)
openaigpt-5.6-terra0.585 (0.44–0.71)
anthropicclaude-sonnet-50.615 (0.45–0.79)
anthropicclaude-opus-50.692 (0.55–0.85)
openaigpt-5.6-luna0.735 (0.61–0.84)
anthropicclaude-haiku-4-50.905 (0.80–1.00)
Citation
@misc{transcriptor-ivrit,
  title        = {transcriptor.ivrit.ai: a crowdsourced Hebrew handwriting transcription corpus},
  author       = {{ivrit.ai}},
  year         = {2026},
  howpublished = {\url{https://transcriptor.ivrit.ai}},
}