Unverified50% confidenceBenchmarkExact time
Kimi K2.7与GLM 5.2在FrontierCode Extended基准测试中均取得优异成绩
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/6/2026
First Seen
Valid until: 10/4/2026
Sources
Devin接入Kimi K2.7与GLM 5.2，双模型限时免费不消耗配额
rss6/24/2026
Related Claims
UnverifiedKimi 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%76% similarUnverifiedKimi K2在测试中表现出较快的执行速度，很快显示Complete状态72% similarUnverified相比Kimi K2.5，Kimi K2.6的API处理能力更强，运行更稳定，任务完成率显著提升72% similarUnverifiedKimi K2.5在AMM5 2025综合能力测试中获得96.1分，在GPQA Diamond高难度问题测试中获得87.6分69% 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69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/115214API
curl https://kongchang.com/api/v1/knowledge/claims/115214MCP
get_claim(id=115214)