AI 导读
Arena 分析 26K+ 会话发现，Agent Arena 头部 10 个智能体每生成 1 个 token 约处理 93 个输入 token，这是各实验室竞相降低缓存输入成本的原因。视频以 Anthropic 的 Opus 5.5 和 Google DeepMind 的 Gemini 4 Argon 的真实会话演示缓存工作方式，详细分析见 @DawidGalarowicz 的文章。
正文
The top 10 agents in Agent Arena process about 93 input tokens for every token they generate, according to our analysis of 26K+ sessions.
This is why labs are racing to lower the cost of cached input.
The video below shows how caching works in practice, with real sessions from Opus 5.5 by @AnthropicAI and Gemini 4 Argon by @GoogleDeepMind.
Dive into the details of the hidden AI price war: article by @DawidGalarowicz below.
https://x.com/i/article/2116183418220511232在 X 查看被引用的帖子
来源：Arena.ai · x.com