Hacker News Reader

Glm-5.3 is dog slow compared to opus and sol. I tried the same real world task on all three and GLM-5.3 was the slowest by a factor of 3.

On their API? Almost definitely, China is good GPU constrained. On the technical aspects? Absolutely not, GLM 5.3 is a relatively small MoE.

On matched hardware?

i'm pretty sure they mean on their official APIs? how would they know what hardware anthropic and openai run their models on?