Expired50% confidenceBenchmarkExact time
A China Academy of Information and Communications Technology (CAICT) special MCP testing report shows that a 27B local large model released by Shanghai Yuandian Xinhui ranked second in a comprehensive multi-tool collaboration evaluation, with a total score surpassing lightweight models with more than 200 billion parameters.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/10/2026
First Seen
Valid until: 9/24/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedA model with approximately 27B parameters achieved a score of 52 running on a laptop, demonstrating that high-quality models are penetrating edge and lightweight devices.69% 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63% similarUnverifiedThe MiniCPM series achieves performance close to 7B and even 13B models on multiple benchmarks with a parameter count at the 2B–4B level62% similarUnverifiedFrom the dimension of instruction following, the 27B local model performs closer to the user's original intent than the flagship Opus, but this may simply be because the boundary of its inferential capability is more conservative.62% similarUnverifiedQwen2.5-7B-Instruct 在多项中文基准测试上的表现接近甚至超过早期 70B 级别的模型62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/890134API
curl https://kongchang.com/api/v1/knowledge/claims/890134MCP
get_claim(id=890134)