[grantpitt]

do say more

[GodelNumbering]

Makes it sound like a one trick pony

[jascha_eng]

Anthropic is leaning into agentic coding and heavily so. It makes sense to use swe verified as their main benchmark. It is also the one benchmark Google did not get the top spot last week. Claude remains king that's all that matters here.

[Mkengin]

I am eagerly awaiting swe-rebench results for November with all the new models: https://swe-rebench.com/

[grantpitt]

well, it's a big trick