OmniHandwritingOCR - English Text: leaderboard

Metric: 1-NED (%; one minus the normalized Levenshtein distance between the transcription and the ground truth, averaged over 11,859 English handwritten text images (GNHK, IAM lines); zero-shot Markdown transcription from one image with one task-neutral instruction for every system; task-specific normalization and tokenization, no semantic correction). Source: arxiv.org. Saturation forecast: Estimated already saturated. 13 models tracked.

Top models

#ModelScore
1GPT-4o81.29
2InternVL3-78B81.14
3Gemma 3 27B (IT)74.86

Interactive version: theaggregate.ai/benchmark?slug=omnihandwritingocr-english-text · How It Works · Data refreshed daily, snapshot 2026-09-29.