Has anybody here experience with Kimi Code (K2.7 Code model)? How is it compared to Claude (Opus 4.8) and GLM 5.2? #asknostr
Kimi 2.7 is okayish compared to GLM 5.2. GLM seems to be better. Don’t see the need to switch to Kimi.
For tasks that don’t require GLM’s expertise, I use DeepSeek-V4-Pro which is much much cheaper and would be comparable to Kimi K2.7 (benchmarks are lower but cannot beat on costs).
My current stack is:
Fable 5 - very very high end task planning.
GPT 5.5 - for high end execution.
GLM 5.2 - medium to high end execution (70% of my usage rn)
Deekseek V4 Pro - low to medium (20% of my usage)
And finally.
DeepSeek V4 Flash - low, grunt agentic work.
For tasks that don’t require GLM’s expertise, I use DeepSeek-V4-Pro which is much much cheaper and would be comparable to Kimi K2.7 (benchmarks are lower but cannot beat on costs).
My current stack is:
Fable 5 - very very high end task planning.
GPT 5.5 - for high end execution.
GLM 5.2 - medium to high end execution (70% of my usage rn)
Deekseek V4 Pro - low to medium (20% of my usage)
And finally.
DeepSeek V4 Flash - low, grunt agentic work.
❤️1