OmnisBench
Open, reproducible benchmark for LLM routing efficiency: verify routing-savings claims yourself. On a fresh split the models can't have memorised, ideal routing beats the frontier model at about 60% lower cost, and every number re-grades offline. Apache-2.0.
原文来源AI 开源 Releases
查看官方原文
Open, reproducible benchmark for LLM routing efficiency: verify routing-savings claims yourself. On a fresh split the models can't have memorised, ideal routing beats the frontier model at about 60% lower cost, and every number re-grades offline. Apache-2.0.