AI hallucination benchmarks aim to quantify how often and severely large...

https://bravo-wiki.win/index.php/When_Lower_Hallucination_Rates_Don%E2%80%99t_Mean_Better_Models:_Why_Reasoning-Focused_AIs_Sometimes_Hallucinate_More

AI hallucination benchmarks aim to quantify how often and severely large language models generate false or misleading information—commonly known as hallucinations