Expired80% confidenceFactTime unknown
Kimi K2.5 reached the level of Gemini 3 Pro on the SWE (software engineering) benchmark.
1
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe 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.78% 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.75% similarUnverifiedTesters believe that Kimi K2.6's Web Coding capability has at least reached the level of Gemini 2.5 Pro.74% similarUnverifiedMoonshot AI released the new Kimi K3 large model, which reportedly topped evaluation leaderboards immediately upon its release.70% similarVerifiedOn the SWE-Bench Verified benchmark, Gemini 2.5 Pro ranked second only to Claude 3.7 Sonnet.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/3913API
curl https://kongchang.com/api/v1/knowledge/claims/3913MCP
get_claim(id=3913)