Reference-free evaluation of LLM-generated code is essential when execution-based testing is unavailable or costly. We compare two paradigms: $explicit LLM-as-a-Judge$ scoring, which assigns a quality score to a solution, and $log-probability scoring$, which uses $code mid task)$ as an instruction-free signal.Across HumanEval-X, we find that the two approaches capture $qualitatively different aspects$ of code correctness. Explicit judges --- particularly larger models --- perform strongly on generated code, reflecting their ability to reason about task-solution alignment, but fail to distinguish correct solutions from minimally mutated ones. Log-probability exhibits the opposite pattern: weaker performance on generated code, but consistent pairwise separation of canonical from mutated solutions.These results reveal a $discrimination-ranking dissociation$ and show that the two paradigms provide complementary, non-interchangeable signals: explicit judges capture semantic correctness, while log-probability captures local structural consistency.