evals: judge behavior instead of matching source text (#97826)
Makes a few of the evals judge what the code actually does rather than
how it happens to be written, so correct solutions stop failing on
style. One of them was already being vetoed by leftover assertions the
judge was meant to replace.
---------
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
