I don't buy it. Open AI doesn't come close to passing my credibility check. I don't believe their metrics.

OpenAI is not the only company making LLMs, there are plenty now, you can use Gemini 2.5 Pro for example. And of course you can just try a SOTA model like Gemini 2.5 Pro for free, you don't have to trust anything.

You don't have to. Just try it yourself.