ModelScope(@ModelScope2022):Jina-OCR-v1 parses entire pages into structured Markdown at 2.57 pages per second.🚀 🤖 https://t.co/MhOQjjK0Ms 📄 https://t.co/j7WwUmerzw 🏆 Scores 91.14 on OmniDocBench v1.6 and 83.4 on olmOCR-Bench, 7.4 points above DeepSeek-OCR on the latter. ⚡ Delivers the highest throughput among 14 evaluated systems at concurrency 32. 📑 Preserves text, formulas, tables, and reading order in a single pass. 🧠 The 3.4B MoE activates only 570M parameters per token, while FastMTP accelerates decoding without changing the autoregressive output. 📜 CC BY-NC 4.0. Commercial use requires permission.

ModelScope@ModelScope2022

2026.09.28 06:35

Jina-OCR-v1 parses entire pages into structured Markdown at 2.57 pages per second.🚀 🤖 📄 🏆 Scores 91.14 on OmniDocBench v1.6 and 83.4 on olmOCR-Bench, 7.4 points above DeepSeek-OCR on the latter. ⚡ Delivers the highest throughput among 14 evaluated systems at concurrency 32. 📑 Preserves text, formulas, tables, and reading order in a single pass. 🧠 The 3.4B MoE activates only 570M parameters per token, while FastMTP accelerates decoding without changing the autoregressive output. 📜 CC BY-NC 4.0. Commercial use requires permission.