You can't even run a benchmark without a basic harness, of course the harness has some effect.

Yep. It's a state machine; change the state, change the result. https://arxiv.org/html/2605.23950v1 | https://arxiv.org/pdf/2505.15146 | https://medium.com/@amontzamir/youre-praising-the-wrong-thin...