Translation conveys meaning across languages, but does it preserve the personality a character conveys? We introduce an evaluation framework for quantifying how well translation systems maintain perceived character personality, the personality impression a reader forms from a character’s dialogue, described along the five Big Five dimensions; we use these dimensions as descriptive labels for the impression, not as a psychometric measurement of the character. Our framework applies personality predictors to both source and translated utterances, measuring cross-lingual consistency via Spearman rank correlation at the speaker level. We study entertainment subtitle translation, where every utterance is produced by a named character, and compare evaluation conditions that include, shuffle, or withhold the character names. We evaluate five MT systems, including dedicated MT APIs (Google Translate, DeepL) and LLMs (GPT-4o, Qwen3- 32B, Aya-expanse-32B), and additionally report human translation as a reference condition on GAME OF THRONES (English→12 target languages, 11 characters) and ONE PIECE (Japanese→English, 15 characters). Under our evaluation protocol, measured personality consistency varies across systems and language pairs, and high BLEU/COMET translation quality does not reliably imply high personality consistency.