Agents
LlamaIndex가 문서 파싱 전용 4B 비전언어모델 OCRia-1 공개. 자체 ParseBench 87.4점(회사 측 평가), 표·차트에 강하고 LlamaParse에서 같은 가격. https://www.llamaindex.ai/blog/parse-…
LlamaIndex가 문서 파싱 전용 4B 비전언어모델 OCRia-1 공개. 자체 ParseBench 87.4점(회사 측 평가), 표·차트에 강하고 LlamaParse에서 같은 가격. https://www.llamaindex.ai/blog/parse-ocria-1 https://x.com/jerryjliu0/status/2113291928292790725
LlamaIndex가 문서 파싱 전용 4B 비전언어모델 OCRia-1 공개. 자체 ParseBench 87.4점(회사 측 평가), 표·차트에 강하고 LlamaParse에서 같은 가격. https://www.llamaindex.ai/blog/parse-ocria-1 https://x.com/jerryjliu0/status/2113291928292790725 Today we’re releasing OCRia-1, a frontier VLM for document parsing that sets a new SOTA in accuracy, cost, and latency. It not only sets a new high score on ParseBench (87.4), but also leads in three 3rd-party benchmarks: olmOCR-bench* (83.5 overall, 92.9 on tables!), PulseBench-…
Related
- More about OCRia-1: https://llamaindex.ai/blog/parse-ocria-1 Signup: https://cloud.llamaindex.ai Book a demo: https://llamaindex.ai/contact
- This is a huge moment for LlamaIndex and an incredible milestone for our research team: introducing OCRia-1, our new document parsing model.…
- @jerryjliu0 We also automatically update the ParseBench leaderboard on Kaggle :) https://www.kaggle.com/benchmarks/llamaindex-org/parsebench
Source: Jerry Liu (X) | 2026-10-22