[oofbaroomf]

Interesting how Sonnet has a higher SWE-bench Verified score than Opus. Maybe says something about scaling laws.

[somebodythere]

My guess is that they did RLVR post-training for SWE tasks, and a smaller model can undergo more RL steps for the same amount of computation.

[benoittravers]

Do you have the link to that benchmark? Can’t see where Sonnet is highlighted.