Claude Opus 5.5位居OpenRouter扫描文档OCR测试首位
OpenRouter使用8张模拟收据、信件、表单、通讯简报、手写笔记和传真件的合成扫描页,测试了15个视觉模型、Mistral OCR和Tesseract。Claude Opus 5.5以264项关键值中答对262项的成绩居首;Mistral OCR答对258项,成本约为其八分之一。报告还发现,视觉模型可能编造页面上不存在的值,而Tesseract在褪色印刷、手写内容和传真件上表现较差。OpenRouter表示,这组小规模合成测试只是起点,用户仍应在自己的扫描件上测试候选方案。
该测试为文档OCR系统提供了准确率与成本的量化对比,但仅有8张合成页面,因此榜单结论不宜直接外推。
Best OCR Model for Scanned Documents, Measured
Kenny Rogers ·11/10/2026


Turning scanned documents into reliable text is hard. Classic OCR engines such as Tesseract fail on faded print, handwriting and faxes. Vision models read those pages well, but sometimes write values that aren’t on the page. We made eight test pages from text we wrote, so every character could be checked, and ran them through 15 vision models and Mistral OCR on OpenRouter, plus Tesseract.
The best OCR model in our test was Claude Opus 5.5, with 262 of 264 key values right at $16.42 per 1,000 pages. Mistral OCR was the best value: 258 of 264 for $2.02. This post shows the results, the errors to watch for, and code to catch them.
#Claude Opus 5.5#Mistral OCR#Tesseract#Claude Sonnet 5.5#Gemini 3.8 Flash#Step 5 Preview#Ling 3.0 Flash VL#Claude Haiku 5.5#Grok 4.7#Mistral Large 4#GPT-6 Luna#OpenRouter