Landing AI tops DocVQA with a record 99.16% accuracy
Landing AI just set a new state of the art on DocVQA with 99.16% accuracy, beating both Qwen2-VL and human baselines. The team decoupled parsing from querying: its DPT-2 model extracts layout and text into structured data once, leaving downstream questions entirely to an LLM. The parse-once approach cuts costs and makes every answer fully traceable.