PureDocBench - Digital Degraded - Text Edit Distance: leaderboard

Text normalized edit distance on the digital degraded track of PureDocBench (2026), a document-parsing benchmark of 1,475 source-traceable pages (pages under simulated aging, binding, photocopy, compression and lighting degradations). Percent; lower is better.

Metric: Text normalized edit distance (%): edit distance between the predicted and reference text divided by the longer length, times 100, on the digitally degraded track (the same pages under ten simulated scene templates such as aging, binding, photocopying, compression, lighting and geometric artifacts) of 1,475 source pages in 10 domains and 66 subcategories, rendered from LLM-written HTML/CSS with source-linked annotations for text, formulas, tables and reading order; lower is better. Source: arxiv.org. Saturation forecast: Not forecast. 58 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1OvisOCR219.6
2Dots.mocr19.8
3Qwen 3.8 27B20.6#221
4TeleOCR20.9
5FD-RL21.4
6Qwen 3.5 122B A10B22#346
7WeVisDoc-4B23.4
8Qwen 3.5 27B23.6#375
9GLM-5.3 Flash24.2#133
10Qwen 3.5 397B A17B24.4#264
11Qwen 3.5 35B A3B24.5#492
12MinerU2.5-2509-1.2B24.5
13Logics-Parsing-v224.8
14WeVisDoc-2B25.5
15Qwen 3.5 9B26#828

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=puredocbench-digital-degraded-text-edit-distance · How It Works · Data refreshed daily, snapshot 2026-11-21.