Expired65% confidenceOpinionTime unknown
The official API version of Kimi K2.5 has the strongest front-end capabilities among domestic models, with some interfaces comparable to Gemini 3.0 Pro.
1
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
6/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 8/31/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedKimi K2.5 reached the level of Gemini 3 Pro on the SWE (software engineering) benchmark.78% similarUnverifiedMoonshot AI acknowledged that Kimi K3's overall capabilities have not yet surpassed the top models from Anthropic and OpenAI, but that it has surpassed all other competitors except those two companies' strongest models.68% similarUnverifiedMoonshot AI released the new Kimi K3 large model, which reportedly topped evaluation leaderboards immediately upon its release.68% similarUnverifiedThe frontend generation test also compared a suspected Gemini 3 refer model, Kimi KL, and Haiku 4.5, with GPT 5.1 leading in instruction following and visual quality.67% similarUnverifiedTesters believe that Kimi K2.6's Web Coding capability has at least reached the level of Gemini 2.5 Pro.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/38131API
curl https://kongchang.com/api/v1/knowledge/claims/38131MCP
get_claim(id=38131)