Unverified50% confidenceFactExact time
The test used the minimax_h3_fl2va_int8_convrot model.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/31/2026
First Seen
Valid until: 11/29/2026
Sources
Related Entities
Related Claims
UnverifiedThe MiniCPM series achieves performance close to 7B and even 13B models on multiple benchmarks with a parameter count at the 2B–4B level71% similarUnverifiedPhi-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68% similarUnverifiedIt is recommended to start testing this tuning-type LoRA at a weight of around 0.5 and proceed in small steps.65% similarUnverifiedQwen3's 235B-parameter MoE flagship model approaches or surpasses closed-source top-tier models on multiple authoritative benchmarks.65% similarUnverifiedMicrosoft's Phi-3-mini (3.8B parameters) surpassed earlier 7B–13B models on multiple benchmark tests.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/828665API
curl https://kongchang.com/api/v1/knowledge/claims/828665MCP
get_claim(id=828665)