MPDocBench-Parse - Heading Hierarchy: leaderboard
Metric: Tree-edit-distance similarity (0-100; predicted Markdown heading tree against the annotated heading hierarchy). Source: arxiv.org. Saturation forecast: Around August 2027. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 235B A22B | 42.34 |
| 2 | Qwen 3.6 Plus | 32.06 |
| 3 | Gemini 3.1 Pro (Preview) | 26.94 |
Interactive version: theaggregate.ai/benchmark?slug=mpdocbench-parse-heading-hierarchy · How It Works · Data refreshed daily, snapshot 2026-09-26.