Doc parsing lite mode scores 75.1 vs Azure Read's 42.3 on OmniParseBench, dominates non-Latin scripts
VikParuchuri · x · 2026-10-23
Vik Paruchuri shared new benchmark results for his document parsing tool's lite mode, along with its limitations.
- On OmniParseBench (documents without math), lite scores 75.1 vs Azure Read's 42.3, and beats Azure Layout on text.
- The gap is dramatic on non-Latin scripts: 97% on Armenian, 97% on Ethiopic, 95% on Kannada — versus Azure Layout at 21%, 14%, and 9% respectively.
- Acknowledged limitations: handwriting and complex tables (merged cells, multi-level headers) don't work as well yet; feedback is welcome as lite mode continues to improve.
Related event: Marker lite mode beats Azure Read in document parsing benchmark(2 posts)→
More from Models
- DeepSeek ships open-weight V4.1-Flash-1017, Terminal-Bench jumps 31.2 to 42.3 — petrusenko_max · 2026-10-23
- DeepSeek ships V4.1-Flash-1017: Terminal-Bench jumps 31.2→42.3, MIT-licensed — petrusenko_max · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23
- Marker's lite mode scores 75.1 vs 42.3 for Azure Read on OmniParseBench — VikParuchuri · 2026-10-23
- Datalab launches lite OCR at $0.50 per 1,000 pages, 20-30x cheaper than Azure, Google and AWS layout APIs — VikParuchuri · 2026-10-23