PureDocBench - Real Degraded - Reading Order Edit Distance: leaderboard
Reading-order 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: Reading-order normalized edit distance (%) between the predicted and reference block sequences, 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: Around 2030. 58 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | TeleOCR | 35.2 | |
| 2 | Qwen 3.8 27B | 36.4 | #221 |
| 3 | Gemini 3.1 Pro (Preview) | 38.6 | #99 |
| 4 | Qwen 3.5 27B | 39 | #375 |
| 5 | FD-RL | 39.1 | |
| 6 | Dots.mocr | 39.3 | |
| 7 | Qwen 3.5 397B A17B | 39.9 | #264 |
| 8 | Claude Opus 5 | 40 | #26 |
| 9 | Qwen 3.5 122B A10B | 40.1 | #346 |
| 10 | Gemini 3.6 Flash | 40.6 | #81 |
| 11 | OvisOCR2 | 40.7 | |
| 12 | WeVisDoc-4B | 41.1 | |
| 13 | Logics-Parsing-v2 | 41.6 | |
| 14 | Qwen 3.5 35B A3B | 41.9 | #492 |
| 15 | GLM-5.3 Flash | 42.3 | #133 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=puredocbench-real-degraded-reading-order-edit-distance · How It Works · Data refreshed daily, snapshot 2026-11-21.