Hacker News Reader

In my workplace, its availability. We have to use US-only models for government-compliance reasons, so we have access to Opus 4.6 and GPT 5.4, but only Gemini 2.5 which isn't in the same class as the first two.

Because Claude is so much more expensive, and I rarely need the best.

gpt-5.4 is really good now also for tricky problems. Just for the unsolvable problems we take opus-4.6. Or if someone pays for it.

Have you used gemini models for code work? Claude and Codex are miles ahead in terms of quality and how thorough they are