Unverified60% confidenceFactExact time
Kimi 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%
2
Sources
60%
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
Partially 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）77% similarUnverifiedKimi K2.7与GLM 5.2在FrontierCode Extended基准测试中均取得优异成绩76% 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74% similarUnverifiedKimi K2.6在SWE-Bench Pro测试中获得58.6%的分数，位居开源模型第一72% similarUnverifiedK2.7 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70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/41729API
curl https://kongchang.com/api/v1/knowledge/claims/41729MCP
get_claim(id=41729)