研究发现同一批 AI 模型每月评分持续走低
原标题：People rate the exact same AI chatbots more harshly each month, so a chatbot that never changes star...
71AI 研判分
一项基于 Chatbot Arena 126 万次盲测投票的研究发现，对于完全相同的冻结模型对，用户给出“两个都差”评价的比例每月上升 1.71 个百分点，基线为 17.1%。但 2024 年较强模型在决定性投票中的胜率基本不变，说明模型排名保持稳定，变化的是用户评判尺度而非模型能力。
报道正文
Rohan Paul (@rohanpaul_ai) · 2026-11-13 16
People rate the exact same AI chatbots more harshly each month, so a chatbot that never changes starts to look worse.
They studied 1,260,967 blind votes on Chatbot Arena, where people compare answers from 2 anonymous models. They kept only pairs of frozen models, such as dated snapshots and fixed open weights, so the models never changed.
On the same pair, "both are bad" votes rose 1.71 percentage points a month, on a 17.1% average. Yet in 2024 the stronger model won about the same share of decisive votes, so rankings held.
