Unverified60% confidenceFactTime unknown
与前代K2.5相比，K2.6的LCP Mark从29.5飙升到55.9，近乎翻倍
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026
Sources
Kimi K2.6开源实测：300个Agent协同的调度能力到底多强
bilibiliAi学习的老章
Related Entities
Related Claims
UnverifiedK2.7 Code在MLS Bench Lite基准测试上相比K2.6提升31.5%（从26.7提升至35.1），是所有测试中提升幅度最大的69% similarUnverified与前代K2.5相比，K2.6的Apex Agents评分提升了2.4倍69% similarUnverifiedKimi K2.7 Code在MCP Mark Verified基准测试上得分81.1，相比K2.6的72.8提升11.4%65% similarUnverified据官方数据，K3相比K2整体推理效率提升约2.5倍64% similarPartially Verified与K2.6相比，K2.7 Code在Kimi Code Bench VR基准测试上提升21.8%（从50.9提升至62.0）64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/4034API
curl https://kongchang.com/api/v1/knowledge/claims/4034MCP
get_claim(id=4034)