Unverified60% confidenceFactTime unknown
Kimi K2.6在SWE-Bench Pro测试中获得58.6%的分数，位居开源模型第一
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026
Sources
Kimi K2.6深度评测：编程与Agent能力全面拆解
bilibiliAI全文总结
Related Entities
Related Claims
UnverifiedKimi K2.6连续数周在SWE-Bench排行榜上稳居榜首75% similarUnverifiedKimi's own K2.6 version ranked only 13th on the same SWE-bench leaderboard, while Composer 2.5 trained on the open-source K2 ranked third.73% 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%72% similarUnverifiedKimi K2.6 在前端开发测试中部分场景超越了Claude Opus 472% similarUnverifiedKimi K2.6在SWE Bench Pro、深度搜索问答和Humanity's Last Exam等顶级基准测试上与GPT 5.4、Claude Opus 4.6和Gemini 3.1 Pro等闭源模型竞争71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/4293API
curl https://kongchang.com/api/v1/knowledge/claims/4293MCP
get_claim(id=4293)