这个thread 和我的体感差不多,GLM 5.2 有自己的缺点,每个任务总体都比Opus慢很多,但是也足够用了。
希望新版本赶快优化下输出冗余、并行调用等小问题。
Follow-up to my GLM vs Opus thread: let's talk cost.
We ran 103 dbt tasks x 3 trials on each model. Same harness, same tasks.
GLM: 860M tokens
Opus: 439M tokens
That's ~2x. But the "why" is more interesting than the number.
显示更多