METATR - Printed: leaderboard
Metric: Character error rate (%) on the printed documents, METATR v1.0 (documents from public collections in 29 languages and many scripts and layouts), page-level transcription with the generic instruction (or the recommended OCR prompt of an OCR-tuned model), default hyperparameters, standardized text normalization; can exceed 100 when the output inserts text; lower is better. Source: arxiv.org. Saturation forecast: Around March 2027. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 17.6 |
| 2 | Claude Opus 4.5 | 53.5 |
| 3 | Mistral Large 3 | 56.6 |
| 4 | Mistral Medium 3 | 57.9 |
| 5 | GPT-5.1 | 58.9 |
| 6 | Mistral Small 3.1 | 66.1 |
Interactive version: theaggregate.ai/benchmark?slug=metatr-printed · How It Works · Data refreshed daily, snapshot 2026-10-07.