[leerob]

We've found it to be a strong mix of speed and intelligence. It scores higher than Sonnet 4.5 on Terminal-Bench 2, maybe we will post more on this later.

[enraged_camel]

Yeah, please do. Because when the AI labs you are competing with are posting extensive benchmarks and you just say "well we used our own internal benchmark" it is a bit sus, especially given the fact that the price has tripled.

[fishpham]

You should! This blog post doesn't really give any reason to use it besides "it's better on Cursor's internal benchmark". A full model card would be great.

[rubslopes]

The way benchmarks for Composer have been presented since v1 feels unusually cautious. To users, that reads as “the model isn’t very good”.