Steven Gonsalvez

Software Engineer

Feels like categorising models got harder recently I used to put models in the bucket of Opus-like, Sonnet-like, or Haiku-like. But now we have Fable. Now Sonnet 5 behaves like Opus. Is GLM 5.2 Opus

Why CEREBRO kept it

Model positioning & capability category shift.

The text below is an automated extraction of the article at https://x.com/mattpocockuk/status/2072996604018143557, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (x.com).

I used to put models in the bucket of Opus-like, Sonnet-like, or Haiku-like.

But now we have Fable. Now Sonnet 5 behaves like Opus. Is GLM 5.2 Opus

> Model positioning & capability category shift.

Feels like categorising models got harder recently

I used to put models in the bucket of Opus-like, Sonnet-like, or Haiku-like.

But now we have Fable. Now Sonnet 5 behaves like Opus. Is GLM 5.2 Opus-like, or Sonnet 5-like?

So, I'm asking. How are you evaluating models?

Backlinks

Appeared in 1 briefing

Related

Shares tags: ai/llm-mechanics

Also from x.com