The paper releases the first public, rule-complete benchmark for LLM reasoning over NordDRG hospital payment logic, with top models scoring 13/13 on logic tasks and 7/13 on full grouper emulation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The NordDRG AI Benchmark for Large Language Models
The paper releases the first public, rule-complete benchmark for LLM reasoning over NordDRG hospital payment logic, with top models scoring 13/13 on logic tasks and 7/13 on full grouper emulation.