PureDocBench - Clean - Text Edit Distance: leaderboard
Text 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: Text normalized edit distance (%): edit distance between the predicted and reference text divided by the longer length, 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 | 12 | |
| 2 | Dots.mocr | 15.1 | |
| 3 | OvisOCR2 | 15.2 | |
| 4 | Qwen 3.8 27B | 18 | #232 |
| 5 | MinerU2.5-2509-1.2B | 18.4 | |
| 6 | Claude Opus 5 | 19.1 | #26 |
| 7 | FD-RL | 19.3 | |
| 8 | WeVisDoc-4B | 20.4 | |
| 9 | Logics-Parsing-v2 | 21.3 | |
| 10 | WeVisDoc-2B | 21.7 | |
| 11 | GLM-5.3 Flash | 21.8 | #137 |
| 12 | MinerU-2.5-Pro-1.2B | 22.2 | |
| 13 | ABot-OCR | 22.4 | |
| 14 | Qwen 3.5 122B A10B | 22.6 | #350 |
| 15 | Qwen 3.5 27B | 22.7 | #380 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=puredocbench-clean-text-edit-distance · How It Works · Data refreshed daily, snapshot 2026-11-22.