X · @llama_index
· Infrastructure
RT Jerry Liu: It's kind of crazy how well LiteParse does on markdown document parsing even compared against frontier VLMs – when it doesn't use VLMs o…
RT Jerry LiuIt's kind of crazy how well LiteParse does on markdown document parsing even compared against frontier VLMs - when it doesn't use VLMs or any AI/OCR models at all. It's pure code. On ParseBench, it outperforms Qwen 3.5-9B / GLM-OCR. There's still a gap vs. models like Gemma 4 and PaddleOCR-VL especially on