Switchyard路由评测：93%任务无需前沿模型，成本降70%
想知道你的智能体能不能少花点钱？LangChain实测NVIDIA的Switchyard，93%任务用30B模型搞定，成本砍七成，准确率还保住九成。
LangChain在Deep Agents评测套件中测试了NVIDIA开源路由器Switchyard，该套件包含145个多步任务，覆盖工具使用、检索、文件系统操作和长上下文场景。
结果显示，93%的调用被路由到30B模型，仅7%需要Claude Opus 4.8。
通过路由策略，总成本降低约70%，同时保留了Opus约90%的准确率。LangChain已推出与Switchyard的deepagents集成。
Do all of your agents need a frontier model? We ran NVIDIA's open source router, Switchyard, through our Deep Agents eval suite comprising of 145 multi-step tasks - Tool use, retrieval, filesystem operations, long context. The result: 93% of turns went to a 30B model. Only 7% needed Claude Opus 4.8. Routing between the two cut total cost by ~70%, while retaining ~90% of Opus's accuracy on the same calls. Try out the deepagents integration with NVIDIA's Switchyard today: buff.ly/1HtHoJ2📊 2 ⚡
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Switchyard, NVIDIA, LangChain, Claude Opus 4.8.
Source attribution: curated from LangChain (@LangChainAI). Cross-source corroboration: 11 independent sources have covered this development (including NVIDIA AI, Harrison Chase, ollama), confirming industry-wide signal strength.
