these things can just change with infrastructure changes rather than be some mysterious A/B testing.
I don't disagree, we've seen performance shift with capacity changes in the past.
With that said, I doubt OpenAI would choose to publish a singular coding benchmark for a new model that exactly matches their previous model (88.8%).
alt Hacker News
I don't disagree, we've seen performance shift with capacity changes in the past.
With that said, I doubt OpenAI would choose to publish a singular coding benchmark for a new model that exactly matches their previous model (88.8%).