Andrew Curran· @AndrewCurran_ · X·· 1 天前AI 评分22
AI 导读
由 AECI 测得的 Anthropic 模型基准分数自 2025 年 10 月以来已加速提升 1.9 倍。Anthropic 过去一年在基准测试上的进展，似乎与他们在 2023 年 10 月至 2025 年 10 月之间取得的进展相当（大致是从 Claude 2.1 到 Sonnet 4.5）。
正文 · 原文
'Benchmark scores of Anthropic’s models, as measured by AECI have accelerated 1.9x since October 2025. Anthropic appears to have made as much progress on benchmarks in the past year as they did between October 2023 and October 2025 (roughly, Claude 2.1 to Sonnet 4.5)'
来源：Andrew Curran · x.com