Expired50% confidenceFactTime unknown
K2.6 has a sparsity of approximately 97% (32B activated parameters out of 1T total parameters), consistent with the design philosophy of Google Switch Transformer, Mistral Mixtral series, and DeepSeek-V3.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Kimi K2.6 In-Depth Review: A Complete Breakdown of Its Coding and Agent Capabilities
bilibiliAI全文总结
Related Claims
UnverifiedThe developer ultimately selected the variant with a KL divergence of 0.028 as the optimal solution.65% similarUnverifiedDevelopers ultimately selected the variant with the lowest KL divergence (0.028), resulting in a 1.83% drop on GSM8K, no change on MMLU, and an improvement in HarmBench compliance rate from 30.8% to 100%63% similarVerifiedKimi K2.6 adopts a Mixture of Experts (MoE) architecture, with a total parameter count at the trillion level and only 32B parameters actually activated.61% similarUnverified在27B混合架构、4B稠密模型、36B MoE三类模型上以8k上下文测试，Prefill阶段性能无变化，Decode阶段打补丁后快约1.4%61% similarUnverifiedK2.7-Code's total quality score is 153.5 points, while K2.6's total quality score is 79 points, with K2.7-Code leading by 74.5 points.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/55332API
curl https://kongchang.com/api/v1/knowledge/claims/55332MCP
get_claim(id=55332)