{"id":"2604.27470","title":"HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats","url":"https://codeofpaper.com/paper/2604.27470","arxiv_url":"https://arxiv.org/abs/2604.27470","published":"2026-04-30","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}