OCRZhipu Open-Sources GLM-OCR, a 0.9B Model That Tops Document Parsing Benchmarks
Sub-1B parameter model claims #1 on OmniDocBench V1.5, rivaling Gemini-3-Pro on document understanding.
Andrés MartínezFeb 3, 20262 min
2 articles tagged with "Omnidocbench"
OCRSub-1B parameter model claims #1 on OmniDocBench V1.5, rivaling Gemini-3-Pro on document understanding.
Document ProcessingA 0.9 billion parameter model from China now leads the most comprehensive document parsing benchmark.
Get the latest AI news, reviews, and deals delivered straight to your inbox. Join 100,000+ AI enthusiasts.
By subscribing, you agree to our Privacy Policy. Unsubscribe anytime.