fr-bench-pdf2md - Tiny Text: leaderboard
Metric: Unit-test pass rate (%) of the model's Markdown conversion on fr-bench-pdf2md's tiny-text (dense pages of small or low-resolution print) pages (difficult French PDF pages from CCPDF and Gallica, chosen where two OCR models disagreed most), checking text presence, reading order and table structure after category-specific normalization; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 83.1 | #64 |
| 2 | Gemini 3 Flash (Preview) | 80.4 | #78 |
| 3 | Gemini 2.5 Flash Lite | 58.9 | #413 |
| 4 | GPT-5.2 | 53.5 | #105 |
| 5 | GPT-5 Mini | 50.6 | #176 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=fr-bench-pdf2md-tiny-text · How It Works · Data refreshed daily, snapshot 2026-10-11.