i tried glm 4.7 for agents that write code. simple scripts 200-1000 LOC. extreme... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

maxdo 50 days ago | parent | context | favorite | on: MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 token...

i tried glm 4.7 for agents that write code. simple scripts 200-1000 LOC. extremely bad . Had to abandon cerebras oferning, their smart models are only on enterprise plan.

jona-f 50 days ago [–]

glm 4.7 is quite old by now. I don't even use 5.1 anymore, cause I found kimi k2.6, mimi 2.5 pro, deepseek v4 pro and qwen 3.7 all better than glm 5.1

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact