
LLMs Score 2.3% on Beancount DSL Generation: The LLMFinLiteracy Benchmark
LLMFinLiteracy finds five ~7B models write correct Beancount transactions just 2.3% of the time, failing on accounting reasoning rather than syntax.
#financial-literacy
Research on financial knowledge representation and LLM competency

LLMFinLiteracy finds five ~7B models write correct Beancount transactions just 2.3% of the time, failing on accounting reasoning rather than syntax.

FinMaster Benchmark: top LLMs hit 96% on financial literacy but only 3% on statement generation. Error propagation costs 21 points on consulting tasks.