以后看模型排名不只凭喜好，还能按事实准确性排序。GPT-5.5 狂飙 13 名，Claude 也被挤到第二，快去 Arena 开开关看看。
Arena 推出基于人类偏好和事实性加权组合的新排名。系统随机抽取对战并提取网络可验证声明，已标注超 200 万条声明（Text Arena 130 万+，Search Arena 70 万+）。启用事实性后，Claude Fable 5 降至第 2，GPT-5.5 跃升 13 位至第 7，Muse Spark 跌 13 位至第 20。Meta 整体排名从第 2 跌至第 5，Anthropic 仍居榜首，开源模型中 Xiaomi 从第 9 升至第 6。
Introducing factuality in the Arena: a new ranking of models according to a weighted combination of ...
Introducing factuality in the Arena: a new ranking of models according to a weighted combination of human preference and factuality. Model rankings are now viewable according to a weighted combination of human preference and factuality. Factuality is live in our Text and Search Arenas as a non-default toggle. We audit model responses by randomly sampling battles and extracting web-verifiable claims. We then verify these claims and compare the average correctness between model responses. To power these rankings, we’ve labeled over 2 million claims made by LLMs in real-world conversations, 1.3+ million from Text Arena, and 700k+ from Search Arena. Notable highlights with factuality enabled in the Text Arena: - Claude Fable 5 moves down slightly to spot #2 - GPT-5.5 saw the largest increase, moving up 13 spots into the #7 spot - Muse Spark dropped the most from #7 to #20 (-13pt) By labs, Meta saw the largest drop from #2 to #5 , while Anthropic overall held the #1 spot. Looking at only open model providers, Xiaomi saw the largest improvement, jumping from #9 to #6 . Learn more about the findings and methodology in this thread. 💬 1 🔄 0 ❤️ 8 👀 1511 📊 2 ⚡