PureDocBench - Clean - Reading Order Edit Distance: leaderboard
Reading-order normalized edit distance on the clean track of PureDocBench (2026), a document-parsing benchmark of 1,475 source-traceable pages (pages rendered straight from their HTML/CSS source). Percent; lower is better.
Metric: Reading-order normalized edit distance (%) between the predicted and reference block sequences, times 100, on the clean track (pages rendered straight from their HTML/CSS source) 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 | TeleOCR | 15.7 | |
| 2 | Dots.mocr | 27.3 | |
| 3 | OvisOCR2 | 28.2 | |
| 4 | Qwen 3.8 27B | 30.5 | #221 |
| 5 | MinerU2.5-2509-1.2B | 32.7 | |
| 6 | WeVisDoc-4B | 33.2 | |
| 7 | FD-RL | 33.4 | |
| 8 | Claude Opus 5 | 33.6 | #26 |
| 9 | Logics-Parsing-v2 | 34.2 | |
| 10 | MinerU-2.5-Pro-1.2B | 34.6 | |
| 11 | WeVisDoc-2B | 34.7 | |
| 12 | Youtu-Parsing | 35.8 | |
| 13 | olmOCR-2 | 35.8 | |
| 14 | Qwen 3.5 27B | 36.2 | #375 |
| 15 | Qwen 3.5 397B A17B | 36.6 | #264 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=puredocbench-clean-reading-order-edit-distance · How It Works · Data refreshed daily, snapshot 2026-11-21.