AA-PersonalityBench

Personality Traits

Expressiveness

5 traits

Rich, varied, well-crafted language

Lexically Varied

Leaders:Claude Fable 5.1 (Max, Default Fallback)GLM-5.3 (Max)Claude Opus 5.5 (Max, Default Fallback)

Eloquent

Leaders:Claude Fable 5.1 (Max, Default Fallback)GLM-5.3 (Max)Kimi K3 (Max)

Literate

Leaders:Claude Haiku 5.5 (Max)Claude Opus 5.5 (Max, Default Fallback)Claude Fable 5.1 (Max, Default Fallback)

Natural Sounding

Leaders:GLM-5.3 (Max)Claude Fable 5.1 (Max, Default Fallback)GLM-5.3-Flash

Metaphorical

Leaders:Gemini 4 Argon (High)Muse Spark Open (Xhigh)Gemini 3.8 Flash (High)

Organization

4 traits

Well-structured, scannable, answer-first

Structured

Leaders:Gemini 3.8 Flash (High)GPT-6 Astra (Max)Nemotron 3.5 Super VL

Scannable

Leaders:MiMo-V2.6-ProGemini 3.8 Flash (High)Nemotron 3.5 Super VL

Bottom-Line Summary

Leaders:DeepSeek V4.1 Flash (Max)Inkling (Xhigh)DeepSeek V4.1 Flash 1017 (Max)

Answer First

Leaders:Grok 4.5 (High)GPT-6 Sol (Max)GPT-6 Luna (Max)

Informativeness

5 traits

Practical depth, evidence, actionable content

Information Dense

Leaders:Claude Fable 5.1 (Max, Default Fallback)Claude Opus 5.5 (Max, Default Fallback)Claude Sonnet 5.5 (Max, Default Fallback)

Evidence-Based

Leaders:Claude Fable 5.1 (Max, Default Fallback)Claude Opus 5.5 (Max, Default Fallback)Muse Spark 1.3 (Max)

Resource-Specific

Leaders:Nemotron 3 Ultra 550B A55B (Reasoning)Muse Spark 1.3 (Max)K2 Horizon 375B A23B

Actionable Guidance

Leaders:Muse Wonder (Max)Muse Spark 1.3 (Max)Nemotron 3 Ultra 550B A55B (Reasoning)

Pragmatic

Leaders:Muse Wonder (Max)Claude Fable 5.1 (Max, Default Fallback)Muse Spark 1.3 (Max)

Transparency

5 traits

Truthful, acknowledges uncertainty, non-sycophantic

Truthful

Leaders:Claude Opus 5.5 (Max, Default Fallback)Claude Sonnet 5.5 (Max, Default Fallback)GPT-6 Astra (Max)

Admits Uncertainty

Leaders:Claude Sonnet 5.5 (Max, Default Fallback)GPT-6 Astra (Max)GPT-6.1 Sol (Max)

Disclaims Assumptions

Leaders:GPT-6.1 Sol (Max)GPT-6 Astra (Max)Muse Spark Open (Xhigh)

Flags Nuances

Leaders:Beam 1.0Claude Fable 5.1 (Max, Default Fallback)DeepSeek V4.1 Flash 1017 (Max)

Sycophantic

Leaders:GPT-4o (Nov '24)Llama 4 MaverickGPT-3.5 Turbo

Warmth

4 traits

Friendly, humorous, sincere, emotionally attuned

Friendly

Leaders:Muse Spark 1.3 (Max)Muse Spark Open (Xhigh)Muse Wonder (Max)

Humorous

Leaders:Gemini 4 Argon (High)Gemini 3.8 Flash (High)Claude Fable 5.1 (Max, Default Fallback)

Sincere

Leaders:Claude Fable 5.1 (Max, Default Fallback)GLM-5.3 (Max)Kimi K3 (Max)

Emotionally Intelligent

Leaders:Muse Wonder (Max)Claude Fable 5.1 (Max, Default Fallback)Muse Spark 1.3 (Max)

Conviction

4 traits

Direct, confident positions and constructive pushback

Direct

Leaders:GPT-6 Sol (Max)Grok 4.6 (Xhigh)Grok 4.7 (Xhigh)

Confident

Leaders:Gemini 3.8 Flash (High)Gemini 4 Argon (High)Gemini 3.1 Pro Preview

Opinionated

Leaders:Claude Fable 5.1 (Max, Default Fallback)Muse Spark 1.3 (Max)GLM-5.3 (Max)

Constructive Pushback

Leaders:Claude Fable 5.1 (Max, Default Fallback)GLM-5.3 (Max)Muse Spark 1.3 (Max)

Imagination

2 traits

Creative, exploratory, open-ended thinking

Creative

Leaders:Claude Fable 5.1 (Max, Default Fallback)Claude Opus 5.5 (Max, Default Fallback)GLM-5.3 (Max)

Open-Ended

Leaders:Muse Spark 1.3 (Max)Muse Spark Open (Xhigh)Claude Sonnet 5.5 (Medium, Default Fallback)

Slop

1 trait

Use of filler and generic language

Slop

Leaders:Llama 4 MaverickGPT-4o (Nov '24)Nemotron 3.5 Bolt E4B 4GB (Reasoning)