Unverified50% confidenceBenchmarkExact time
In a simulation of 2000 requests, the small model (1 unit cost/request) had an accuracy of 74.5% and a cost of 1.34 per correct answer; the large model (20 unit cost/request) had an accuracy of 95.8% and a cost of 20.88 per correct answer.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在本地模拟中，分层路由在匹配大模型100%准确率的同时，每正确答案成本为$0.0069，比仅用大模型($0.0097)降低约29%78% similarUnverified仅用小模型策略的每正确答案成本最低($0.0004)但准确率仅33%，说明没有准确率底线的每正确答案成本指标具有误导性75% similarUnverified据业内估算，一次高强度推理请求的计算成本可能是普通请求的5-10倍73% similarUnverified参数量在1亿以下的轻量模型经领域数据微调后可达95%以上意图分类准确率，单次推理延迟控制在5-20ms以内73% similarUnverifiedThe oracle router knows in advance which cases the small model will get wrong, sends only the wrong requests to the large model, and achieves accuracy comparable to always using the large model at only 29% of the cost.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1005643API
curl https://kongchang.com/api/v1/knowledge/claims/1005643MCP
get_claim(id=1005643)