Partially Verified65% confidenceFactExact time
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）
3
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Kimi K2.7 Code Deep Dive: The Cost-Performance Battle of a Trillion-Parameter Coding Model
bilibiliAI睡前简报6/13/2026
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77% 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%77% similarUnverifiedK2.7 Code目前尚未公布SWE-Bench成绩，所有性能数据均为月之暗面自报，此前K2.6曾出现自报成绩与第三方复现相差15-20个百分点的情况70% similarUnverifiedK2.7-Code总质量得分为153.5分，K2.6总质量得分为79分，K2.7-Code领先74.5分69% similarVerifiedKimi K2.7 Code的思维链token使用量相比K2.6减少约30%68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/41727API
curl https://kongchang.com/api/v1/knowledge/claims/41727MCP
get_claim(id=41727)