ResearchBenchmarksHuman Evaluation of Personality Expression on BIG5-CHAT (test)For AI assistantsMarkdownContent indexHuman Evaluation of Personality Expression on BIG5-CHAT (test)Follow50.2Win RateBIG5-CHAT47.70448.3524949.648Oct 21, 2024Evaluation resultsMethodMethodLinksWin RateDraw RateLoss RateCohen's KappaBIG5-CHATEvaluation Criterion=E...Evaluation Criterion=Expressiveness2024.1050.239.8100.5BIG5-CHATEvaluation Criterion=R...Evaluation Criterion=Realism2024.1047.842.2100.55