Unverified50% confidenceBenchmarkExact time
Phi-3-mini（3.8B参数）在部分基准测试上超越了Mixtral 8x7B等更大的混合专家模型
1
Sources
50%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
UnverifiedMicrosoft的Phi-3-mini（3.8B参数）在多项基准测试中超越了早期的7B-13B模型74% similarUnverifiedPhi-3 Mini（3.8B参数）在多项推理基准上超越了早期的GPT-3.5，且体积小到可在普通智能手机上运行70% similarUnverified微软的Phi-3仅3.8B参数但在多项基准测试中性能媲美早期GPT-4级别的模型67% similarUnverified千问3的235B参数MoE旗舰版在多项权威基准测试中接近甚至超越闭源顶级模型67% similarUnverified微软的Phi-3 Mini仅有38亿参数，但在多项基准测试中超越了参数量数倍于它的模型66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/525475API
curl https://kongchang.com/api/v1/knowledge/claims/525475MCP
get_claim(id=525475)