Arena.ai· @arena · X·· 3 小时前AI 评分48
AI 导读
Arena 发布智能体版本的模型路由 Max,基于 Agent Arena 的 250 万条真实智能体会话训练,可动态为每个任务选择最佳模型。Max 在 Agent Arena 取得 +14.7% 净提升分数,中位成本每任务 $3.27,性能匹配 Claude Fable 5.1(Max)但成本低 37%。该产品目前限时开放试用。
正文
Introducing our new agentic version of Max: Arena’s model router that achieves frontier-level performance at 37% lower cost.
Built on 2.5M real-world agentic sessions from Agent Arena, Max learns to dynamically select the best model for each task, optimizing for both performance and cost.
Max achieves a +14.7% net improvement score in Agent Arena at a median cost of $3.27 per task, matching the performance of Claude Fable 5.1 (Max) at 37% lower cost.
Try Max today for a limited time, and dive into more technical details in the thread.
来源:Arena.ai · x.com