LlamaIndex 作者用 ParseBench 测 GPT-6.1 Sol 文档 OCR

Jerry Liu @jerryjliu0原推发布于 2026.09.30

在 X 上打开原推

we comprehensively benchmarked gpt-6.1 sol on document OCR tasks. compared to gpt-6 sol from a week ago (!), we see a sizable increase in table parsing capabilities and reading order, which is pleasantly surprising. gpt-6.1 sol has similar table parsing as gpt-6 astra. these are great results. frontier models are still typically an order of magnitude more expensive than cost-effective document parsing solutions, but this also means that there's a lot of alpha in improving capabilities at the "premium" end (>1c per page) of the spectrum too check out ParseBench: https://www.parsebench.ai/ for a comprehensive set of document parsing capabilities, check out llamaparse: https://cloud.llamaindex.ai/