{"id":"2603.04417","title":"Same Input, Different Scores: A Multi Model Study on the Inconsistency of LLM Judge","url":"https://codeofpaper.com/paper/2603.04417","arxiv_url":"https://arxiv.org/abs/2603.04417","published":"2026-02-04","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}