Tencent's WeVisDoc-4B hits 95.38 on OmniDocBench as two new OCR models land on Hugging Face
NielsRogge · x · 2026-09-18
Two new OCR models landed on Hugging Face: Tencent's WeVisDoc (2B and 4B, Apache 2.0) and jinaai/jina-ocr-v1 (non-commercial license). Per the OmniDocBench v1.6 benchmark on Papers with Code, WeVisDoc-4B leads with an overall score of 95.38, though the current SOTA remains NaviDC-OCR.
More from Models
- Databricks claims its agents match Claude and GPT-5.6 Luna at twice the speed, per its own tests — emmanuelvivier · 2026-09-18
- Dev surveys Jev demos: self-driving cars, rockets, new languages and more — iannuttall · 2026-09-18
- What should we call the class of models competing with JEV? — altryne · 2026-09-18
- Armin Ronacher floats replacing MCP with codemode + OpenAPI + RAG over API docs — mitsuhiko · 2026-09-18
- Opus 4.8 predicted to win a cult following among devs like GPT-4o did — RileyRalmuto · 2026-09-18
- Chinese coding models use 2-3x the tokens, so cheaper per token isn't cheaper overall — craigbalding · 2026-09-18