But why GPT 5.6 Sol is so behind on the benchmarks? In real-world projects, it is the best frontier model to me in terms of accuracy, speed and consistency. It can just be compared to Fable 5, but I prefer GPT 5.6 Sol because of inference speed.
I've never trusted on model cards though. I'm sorry.
Another benefit is that fast mode can be used on subscription, but Anthropic's won't
Exactly! And they should also release the new inference engine in this month. Anyway, I am curious to try Opus 5, considering that previous versions (e.g., 4.8) were disappointing