Large Language Models
Baidu's 0.9B PaddleOCR-VL 1.5 Just Beat GPT-4o at Reading Documents—But Who's Cashing In?
Everyone figured bloated giants like GPT-4o owned document parsing. Baidu's scrappy 0.9B model just flipped the script—94.5% accuracy, cheaper, faster. But is it hype or hardware shift?