PureDocBench - Clean - Table TEDS: leaderboard

Table recognition 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), 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 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; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 58 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 592.17#26
2TeleOCR91.12
3GLM-5.3 Flash90.76#133
4OvisOCR290.1
5WeVisDoc-4B89.23
6Qwen 3.8 27B87.69#221
7WeVisDoc-2B87.64
8Gemini 3.6 Flash86.76#81
9ABot-OCR86.39
10FD-RL86.22
11MinerU-2.5-Pro-1.2B84.68
12OCRVerse83.09
13Qwen 3.5 122B A10B83.03#346
14GPT-5.6 Sol82.87#37
15PaddleOCR-VL-1.682.7

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-table-teds · How It Works · Data refreshed daily, snapshot 2026-11-21.