Unverified50% confidenceBenchmarkExact time
Phi-2 has 2.7B parameters and on multiple benchmark tests can match models several times its size.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/17/2026
First Seen
Valid until: 12/16/2026
Sources
Related Entities
Related Claims
UnverifiedPhi-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75% similarUnverified微软的Phi系列以2.7B参数在多项基准上超越了体量大数倍的竞品65% similarUnverified研究表明当模型参数规模达到3B以上时，1.58-bit模型在多项基准测试中表现可接近甚至匹配同等规模的全精度模型65% similarVerifiedAlphaFold2 overwhelmingly surpassed all traditional methods at the CASP14 competition, with prediction accuracy approaching the level of experimental measurement.61% similarUnverifiedThe MiniCPM series achieves performance close to 7B and even 13B models on multiple benchmarks with a parameter count at the 2B–4B level60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/930483API
curl https://kongchang.com/api/v1/knowledge/claims/930483MCP
get_claim(id=930483)