Dr. DocBench - Text Edit Distance: leaderboard

Metric: Normalized Levenshtein edit distance of the extracted page text against the expert transcription, times 100 (0-100), 4,514 expert-annotated difficult pages sampled by parser failure from long books in 52 subject domains; each page parsed with the model's own document-to-markdown prompt (specialized parsers through their official APIs); lower is better. Source: arxiv.org. Saturation forecast: Around December 2026. 12 models tracked.

Top models

#ModelScore
1GPT-5.519
2Kimi K2.519
3Gemini 3.1 Pro (Preview)22
4Claude Opus 4.622
5Qwen 3.5 122B A10B23
6Qwen 3.5 Plus25
7Qwen 3.5 Flash26
8GPT-4o37
9Nemotron Nano 12B v2 VL62

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