Datalab 出了 Marker 2，OCR 文档解析又快又准，比 MinerU 快 5 倍，比 Docling 更强，搞文档提取的别错过。
Datalab 推出 Marker 2，采用三模式管道优化文档解析。该模型在 olmOCR-bench 基准上达到 76.0 分，在单块 B200 GPU 上实现每秒 2.9 页的吞吐量，是 MinerU 管道后端的 5 倍以上。在准确率和速度上，Marker 2 均超过 Docling。文章还对比了 MinerU、Docling 和 LiteParse 的性能差异，帮助用户选择合适方案。
Datalab’s Marker 2 vs MinerU, Docling and LiteParse: 76.0 on olmOCR-bench at 5× MinerU’s Throughput
Datalab rewrote Marker as a three-mode pipeline. Version 2 hits 76.0 on olmOCR-bench and sustains 2.9 pages per second on one B200 — over 5× MinerU's pipeline backend, while beating Docling on both accuracy and speed. Here's how it compares against MinerU, Docling and LiteParse, and which one fits your use case. The post Datalab’s Marker 2 vs MinerU, Docling and LiteParse: 76.0 on olmOCR-bench at 5× MinerU’s Throughput appeared first on MarkTechPost .