PureDocBench - Real Degraded - Text Edit Distance: leaderboard
Text normalized edit distance on the real degraded track of PureDocBench (2026), a document-parsing benchmark of 1,475 source-traceable pages (pages captured by phone from prints, photocopies and screens, or as compressed screenshots). 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 real degraded track (the same pages through four physical acquisition chains: phone photos of prints and of photocopies, screen photographs, and screenshots with social-media compression) 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.8 27B | 27.4 | #232 |
| 2 | Qwen 3.5 122B A10B | 28.1 | #350 |
| 3 | Qwen 3.5 27B | 28.3 | #380 |
| 4 | Qwen 3.5 397B A17B | 28.7 | #270 |
| 5 | Claude Opus 5 | 29.4 | #26 |
| 6 | FD-RL | 29.8 | |
| 7 | Gemini 3.1 Pro (Preview) | 30 | #102 |
| 8 | Logics-Parsing-v2 | 30.4 | |
| 9 | Qwen 3.5 35B A3B | 31 | #494 |
| 10 | Gemini 3.6 Flash | 31 | #84 |
| 11 | GLM-5.3 Flash | 31.1 | #137 |
| 12 | Dots.mocr | 31.2 | |
| 13 | OvisOCR2 | 32 | |
| 14 | Qwen 3.5 9B | 33.2 | #838 |
| 15 | WeVisDoc-4B | 33.3 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=puredocbench-real-degraded-text-edit-distance · How It Works · Data refreshed daily, snapshot 2026-11-22.