Expired70% confidenceFactTime unknown
In a literary creation test, Gemini's blind evaluation judged that Kimi K2 Thinking's ci-poem in the style of 长相思 was superior to DeepSeek's work.
1
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedKimi K2.7 Code uses the MLA (Multi-head Latent Attention) mechanism, which was originally proposed by the DeepSeek team in DeepSeek-V2.65% similarUnverifiedMoonshot AI (Kimi) and DeepSeek are domestic models that support tool calling.60% similarUnverified在科幻小说《极光》飞船复刻测试中，DeepSeek V4 Pro识别出搜索结果矛盾并主动更换关键词校验，表现反超Kimi K357% similarUnverifiedDeepSeek excels in mathematical reasoning and logical analysis, while the Spark large model specializes in Chinese humanistic understanding, making the two complementary.57% similarUnverifiedIn domestic mainstream large model programming capability tests, Zhipu GLM ranks first, while DeepSeek, Kimi, and MiniMax are in the second tier, and Alibaba Tongyi and Tencent Hunyuan perform slightly worse.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/24218API
curl https://kongchang.com/api/v1/knowledge/claims/24218MCP
get_claim(id=24218)