I wonder if anyone has actually measured the difference in verification time between these models. A senior dev in a high cost of living area costs the company something like $200 an hour. If a cheaper model produces code that takes an extra 20 minutes to debug or verify because it missed a subtle edge case, you have already lost any savings from the lower API bill. It feels like the real moat for labs like Anthropic is the level of trust a reviewer can have in the output without reading every single line. Curious how much people trust GLM over something like Opus? Is there much of a marginal difference here?