human eval

Everyone quotes benchmark scores; few read them honestly. The signal is naming what each probes and why leaderboard numbers run ahead of real-world ability. The follow-up the interviewer is holding back is how you would detect contamination.

For open-ended generation there's no ground-truth string to match, so accuracy is meaningless. The field uses a layered mix of automatic, model-based, and human metrics. Here is how to assemble a credible eval.