Unverified50% confidenceBenchmarkExact time
The 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.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
Unverified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78% similarUnverified修复前模型每约29次下一token预测中约有1次的选择与数学上应有结果不同75% similarUnverifiedIn the most difficult single-concept quantitative category, most models' accuracy falls below 30%74% similarUnverifiedEven well-prompted, schema-constrained models with 8 billion to 14 billion parameters still have an error rate of a few percent on real-world inputs—this is a rate to design around, not a bug to eliminate.74% similarUnverified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%73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1005659API
curl https://kongchang.com/api/v1/knowledge/claims/1005659MCP
get_claim(id=1005659)