Agent Arena头部智能体输入输出比约93比1
Arena称,对超过2.6万次Agent Arena会话的分析显示,排名前10的智能体每生成1个token约处理93个输入token。Arena还表示,各实验室正竞相降低缓存输入成本,并通过Opus 5.5和Gemini 4 Argon的会话演示了缓存机制。
这一量化结果显示Agent Arena智能体处理输入的规模,而缓存输入成本正成为AI实验室关注的重点。
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.
@arena: https://x.com/i/article/2116183418220511232 https://x.com/arena/status/2116185149918626145
#Agent Arena#Arena#Anthropic#Opus 5.5#Google DeepMind#Gemini 4 Argon