Understand this story
Artificial Analysis published the performance of Gemini models in AA-PersonalityBench. The benchmark shows that the Gemini series is the most confident and least willing to acknowledge uncertainty among all tested models. The top three most confident are Gemini 3.8 Flash (100), Gemini 4 Argon (97), and Gemini 3.1 Pro Preview (95); the top three least willing to acknowledge uncertainty are Gemini 3.1 Pro Preview (1), Gemini 4 Argon (4), and Gemini 3.8 Flash (6). There are currently no follow-up developments.
AI-generated from public reports
Latest development · Report
AA-PersonalityBench: Gemini models are the most confident and least likely to admit uncertaintyDevelopments
1 confirmed developments
Artificial Analysis announces Gemini model performance in AA-PersonalityBench
Source:Artificial Analysis
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 22
Artificial Analysis
AA-PersonalityBench: Gemini models are the most confident and least likely to admit uncertainty
Artificial Analysis's AA-PersonalityBench shows that the Gemini series is the most confident and least likely to admit uncertainty among all tested models. The top three most confident are Gemini 3.8 Flash (100), Gemini 4 Argon (97), and Gemini 3.1 Pro Preview (95); the top three least willing to admit uncertainty are Gemini 3.1 Pro Preview (1), Gemini 4 Argon (4), and Gemini 3.8 Flash (6).