PureDocBench - Real Degraded - Table TEDS: leaderboard
Table recognition 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), scored by tree-edit-distance similarity (TEDS) from 0 to 100. Higher is better.
Metric: Table Tree-Edit-Distance-based Similarity (0-100) between the predicted and reference HTML tables, 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; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 58 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 5 | 84.01 | #26 | |
| 2 | GLM-5.3 Flash | 82.45 | #133 | |
| 3 | Gemini 3.6 Flash | 81.96 | #81 | |
| 4 | Qwen 3.8 27B | 79.63 | #221 | |
| 5 | WeVisDoc-4B | 77.92 | ||
| 6 | Gemini 3.1 Pro (Preview) | 77.26 | #99 | |
| 7 | TeleOCR | 76.32 | ||
| 8 | Qwen 3.5 122B A10B | 75.44 | #346 | |
| 9 | Kimi K2.6 | Non-reasoning | 75.14 | #192 |
| 10 | WeVisDoc-2B | 74.21 | ||
| 11 | OvisOCR2 | 73.7 | ||
| 12 | MinerU-2.5-Pro-1.2B | 72.47 | ||
| 13 | FD-RL | 72.08 | ||
| 14 | PaddleOCR-VL-1.6 | 71.76 | ||
| 15 | Logics-Parsing-v2 | 71.64 |
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-table-teds · How It Works · Data refreshed daily, snapshot 2026-11-21.