Nace AI 推出文档解析模型 Drex,每千页 7 美元
really cool launch.
Nace AI 推出文档解析模型 Drex,在把 PDF 或扫描件转成文本后,由这个小模型逐块比对原始页面图像,只把不匹配的部分送回修正,成本为每千页 7 美元。Drex 回答“某行 OCR 结果是否与图像一致”这类窄问题约需 50 毫秒、每百万次回答约 2 美元,单页修正中位耗时下降 28% 至 38%,修正失败则回退到原始识别结果。该系统在 Parse Index 上得分 0.834,高于 GPT-6 Astra(low)的 0.813,成本为每千页 7 美元对 70.57 美元。
查看原帖隆重推出用于文档处理的 Drex 📑 由决策驱动的解析,在错误到达你的智能体之前就将其捕获。 → 在我们的解析排行榜上排名第一 → 击败 GPT-6 Astra、Claude Opus 4.7 以及所有测试过的解析器 → 在 RealDocBench 上修正速度快 38% 立即试用:https://t.co/eTUlO9j0wU
查看原文
Introducing Drex for Document Processing 📑 Decision-powered parsing that catches errors before they reach your agents. → #1 on our parsing leaderboard → Beats GPT-6 Astra, Claude Opus 4.7 & every parser tested → 38% faster corrections on RealDocBench Try it: https://t.co/eTUlO9j0wU
正文
really cool launch.
Brilliant use of Decision models.
@NaceAI built a document reader that proofreads itself. After it turns a PDF or scan into text, a small model called Drex compares each block with the original page image and sends only the mismatches back for correction, all for $7 per 1,000 pages.
Standard OCR flattens tables and drops ticked boxes, while frontier models help but get expensive at volume.
Drex instead answers narrow questions, such as whether an OCR line matches the image, in about 50 milliseconds for about $2 per million answers.
Because only doubted text gets rewritten, median correction time per page fell 28% to 38%, and failed fixes revert to the original reading.
The system scores 0.834 on the Parse Index, beating GPT-6 Astra (low) at 0.813 while costing $7 per 1,000 pages against $70.57.
https://t.co/wnYo5UWUwz
AI 热点