如果你看重模型回答的准确性，LMSys 新出的事实性排名很有参考价值。Claude Opus 5 这次在最重视事实的榜单上拿了第一，比之前只看人类偏好的排名更实在。
LMSys Chatbot Arena 引入新排名“Factuality”，结合人类偏好与事实准确性。Claude Opus 5 with Max reasoning 在 Text Arena 中位居第一。该排名通过抽取响应、提取可验证声明并逐对检查正确性来审计对战。Factuality 现已作为非默认切换选项在 Text 和 Search Arena 中上线。
In the Text Arena, Claude Opus 5 with Max reasoning ranks #1 with factuality on. Factuality is a n...
In the Text Arena, Claude Opus 5 with Max reasoning ranks #1 with factuality on. Factuality is a new ranking that combines human preference with factual accuracy. We audit battles by sampling responses, extracting verifiable claims, and checking correctness head-to-head. Live now as a non-default toggle in Text & Search Arenas. Read more about factuality at: arena.ai/blog/factualit… 💬 1 🔄 1 ❤️ 12 👀 1803 📊 3 ⚡