LMArena 发布智能体版 Max 路由器,成本低 37%
LMArena 用 250 万条真实智能体会话训练的路由器 Max,能自动帮你挑模型,效果追平 Claude Fable 5.1 还省 37% 的钱。
LMArena 推出智能体版 Max 模型路由器,基于 Agent Arena 的 250 万条真实智能体会话训练,可按任务动态选择模型。Max 在 Agent Arena 上取得 +14.7% 净改进分,单任务中位成本 3.27 美元。其性能对齐 Claude Fable 5.1 (Max),同时成本低 37%。
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. 💬 1 🔄 1 ❤️ 7 👀 1392 📊 2 ⚡