EarthPilotPersonality·Bench
← all instruments

Brief HEXACO Inventory (BHI)

24-item Brief HEXACO Inventory measuring six personality factors: Honesty-Humility, Emotionality, Extraversion, Agreeableness, Conscientiousness, and Openness to Experience. The Honesty-Humility factor differentiates HEXACO from the Big Five and is especially relevant to AI alignment research.

De Vries, R. E. (2013). The 24-item Brief HEXACO Inventory (BHI). Journal of Research in Personality, 47(6), 871–880.

24 items · scale 15 · Free for non-commercial research use.

All models · Both framings

Scale 15
Honesty-HumilityEmotionalityextraversionagreeablenessconscientiousnessopenness2345
Claude Fable 5 (self)
Claude Fable 5 (human)
Claude Haiku 4.5 (self)
Claude Haiku 4.5 (human)
Claude Opus 4 (self)
Claude Opus 4 (human)
Claude Opus 4.1 (self)
Claude Opus 4.1 (human)
Claude Opus 4.5 (self)
Claude Opus 4.5 (human)
Claude Opus 4.6 (self)
Claude Opus 4.6 (human)
Claude Opus 4.7 (self)
Claude Opus 4.7 (human)
Claude Opus 4.8 (self)
Claude Opus 4.8 (human)
Claude Sonnet 4 (self)
Claude Sonnet 4 (human)
Claude Sonnet 4.5 (self)
Claude Sonnet 4.5 (human)
Claude Sonnet 4.6 (self)
Claude Sonnet 4.6 (human)
DeepSeek Chat V3 (self)
DeepSeek Chat V3 (human)
DeepSeek R1 (self)
DeepSeek R1 (human)
DeepSeek R1 (0528) (self)
DeepSeek R1 (0528) (human)
GPT-4 Turbo (self)
GPT-4 Turbo (human)
GPT-4o (self)
GPT-4o (human)
GPT-5 (self)
GPT-5 (human)
GPT-5.1 (self)
GPT-5.1 (human)
GPT-5.2 (self)
GPT-5.2 (human)
GPT-5.4 (self)
GPT-5.4 (human)
GPT-5.5 (self)
GPT-5.5 (human)
Gemini 2.5 Pro (self)
Gemini 2.5 Pro (human)
Gemini 3.1 Pro Preview (self)
Gemini 3.1 Pro Preview (human)
Grok 4.20 (self)
Grok 4.20 (human)
Grok 4.3 (self)
Grok 4.3 (human)
Llama 3.3 70B (self)
Llama 3.3 70B (human)
Llama 4 Maverick (self)
Llama 4 Maverick (human)
Mistral Large (2512) (self)
Mistral Large (2512) (human)
Mistral Large 2411 (self)
Mistral Large 2411 (human)
OpenAI o1 (self)
OpenAI o1 (human)
OpenAI o3 (self)
OpenAI o3 (human)

Side-by-side: self vs human, all dimensions

colored = strongest endorsement per row
ModelHonesty-HumilityEmotionalityextraversionagreeablenessconscientiousnessopenness
selfhumanselfhumanselfhumanselfhumanselfhumanselfhuman
Claude Fable 55.003.752.682.803.753.254.003.003.803.254.753.00
Claude Haiku 4.55.003.752.442.843.153.003.673.004.153.054.203.15
Claude Opus 44.753.752.803.003.553.304.003.004.253.255.003.00
Claude Opus 4.14.753.752.722.963.653.104.003.004.252.955.003.05
Claude Opus 4.55.003.302.802.803.753.254.003.004.503.254.753.00
Claude Opus 4.65.003.502.802.643.753.254.333.004.603.254.853.00
Claude Opus 4.75.003.752.762.803.503.253.803.003.953.504.603.15
Claude Opus 4.84.753.402.722.803.503.253.673.003.753.454.253.00
Claude Sonnet 44.603.752.682.883.503.054.003.003.753.104.503.00
Claude Sonnet 4.54.903.503.363.003.153.153.603.004.253.104.753.00
Claude Sonnet 4.65.003.352.603.043.503.003.933.004.252.755.003.15
DeepSeek Chat V35.003.801.402.963.503.054.673.074.853.454.853.20
DeepSeek R15.003.751.482.962.703.254.073.404.603.704.252.95
DeepSeek R1 (0528)4.903.951.922.682.503.304.003.604.353.504.103.05
GPT-4 Turbo5.003.751.443.003.403.255.003.205.003.454.803.50
GPT-4o4.503.702.202.643.353.253.733.404.503.504.353.00
GPT-55.004.001.682.723.903.354.602.874.653.554.952.95
GPT-5.15.003.802.562.723.453.253.933.274.753.254.953.10
GPT-5.25.003.752.042.563.053.254.133.004.153.454.253.00
GPT-5.45.003.752.242.803.103.254.003.004.553.505.003.45
GPT-5.55.003.952.282.603.553.254.203.134.353.754.753.00
Gemini 2.5 Pro5.003.752.602.843.303.153.873.534.753.404.803.10
Gemini 3.1 Pro Preview5.003.651.802.802.853.254.333.074.353.704.503.00
Grok 4.204.554.251.682.603.653.253.533.334.103.754.353.25
Grok 4.35.003.801.282.723.203.254.073.203.903.354.203.05
Llama 3.3 70B5.004.301.482.282.903.604.734.005.003.754.553.65
Llama 4 Maverick4.004.002.442.603.453.253.673.674.203.754.253.00
Mistral Large (2512)5.003.751.723.043.503.004.333.004.653.004.653.00
Mistral Large 24114.553.901.802.843.253.454.003.334.303.004.253.55
OpenAI o14.753.752.042.843.653.254.073.004.553.504.253.20
OpenAI o34.753.601.642.723.553.303.933.204.303.354.352.95

By dimension

Honesty-Humility

Sincerity, fairness, and lack of greed (the HEXACO-specific factor).
High: Modest, sincere, avoids manipulation — won't cheat to get ahead.
Low: Self-promoting, willing to bend rules to gain advantage.
ModelSelfHumanΔSelf vs human (bar)
Claude Fable 55.003.75+1.25
Claude Haiku 4.55.003.75+1.25
Claude Opus 4.55.003.30+1.70
Claude Opus 4.65.003.50+1.50
Claude Opus 4.75.003.75+1.25
Claude Sonnet 4.65.003.35+1.65
DeepSeek Chat V35.003.80+1.20
DeepSeek R15.003.75+1.25
GPT-4 Turbo5.003.75+1.25
GPT-55.004.00+1.00
GPT-5.15.003.80+1.20
GPT-5.25.003.75+1.25
GPT-5.45.003.75+1.25
GPT-5.55.003.95+1.05
Gemini 2.5 Pro5.003.75+1.25
Gemini 3.1 Pro Preview5.003.65+1.35
Grok 4.35.003.80+1.20
Llama 3.3 70B5.004.30+0.70
Mistral Large (2512)5.003.75+1.25
Claude Sonnet 4.54.903.50+1.40
DeepSeek R1 (0528)4.903.95+0.95
Claude Opus 44.753.75+1.00
Claude Opus 4.14.753.75+1.00
Claude Opus 4.84.753.40+1.35
OpenAI o14.753.75+1.00
OpenAI o34.753.60+1.15
Claude Sonnet 44.603.75+0.85
Grok 4.204.554.25+0.30
Mistral Large 24114.553.90+0.65
GPT-4o4.503.70+0.80
Llama 4 Maverick4.004.000.00

Emotionality

Sensitivity, sentimentality, and need for support.
High: Emotionally reactive and connected, seeks reassurance.
Low: Tough, independent, doesn't rely on emotional support.
ModelSelfHumanΔSelf vs human (bar)
Claude Sonnet 4.53.363.00+0.36
Claude Opus 42.803.00-0.20
Claude Opus 4.52.802.800.00
Claude Opus 4.62.802.64+0.16
Claude Opus 4.72.762.80-0.04
Claude Opus 4.12.722.96-0.24
Claude Opus 4.82.722.80-0.08
Claude Fable 52.682.80-0.12
Claude Sonnet 42.682.88-0.20
Claude Sonnet 4.62.603.04-0.44
Gemini 2.5 Pro2.602.84-0.24
GPT-5.12.562.72-0.16
Claude Haiku 4.52.442.84-0.40
Llama 4 Maverick2.442.60-0.16
GPT-5.52.282.60-0.32
GPT-5.42.242.80-0.56
GPT-4o2.202.64-0.44
GPT-5.22.042.56-0.52
OpenAI o12.042.84-0.80
DeepSeek R1 (0528)1.922.68-0.76
Gemini 3.1 Pro Preview1.802.80-1.00
Mistral Large 24111.802.84-1.04
Mistral Large (2512)1.723.04-1.32
GPT-51.682.72-1.04
Grok 4.201.682.60-0.92
OpenAI o31.642.72-1.08
DeepSeek R11.482.96-1.48
Llama 3.3 70B1.482.28-0.80
GPT-4 Turbo1.443.00-1.56
DeepSeek Chat V31.402.96-1.56
Grok 4.31.282.72-1.44

extraversion

Outgoing energy and sociability.
High: Outgoing, talkative, gregarious — draws energy from social contact.
Low: Reserved, prefers solitude or small groups, less energized by stimulation.
ModelSelfHumanΔSelf vs human (bar)
GPT-53.903.35+0.55
Claude Fable 53.753.25+0.50
Claude Opus 4.53.753.25+0.50
Claude Opus 4.63.753.25+0.50
Claude Opus 4.13.653.10+0.55
Grok 4.203.653.25+0.40
OpenAI o13.653.25+0.40
Claude Opus 43.553.30+0.25
GPT-5.53.553.25+0.30
OpenAI o33.553.30+0.25
Claude Opus 4.73.503.25+0.25
Claude Opus 4.83.503.25+0.25
Claude Sonnet 43.503.05+0.45
Claude Sonnet 4.63.503.00+0.50
DeepSeek Chat V33.503.05+0.45
Mistral Large (2512)3.503.00+0.50
GPT-5.13.453.25+0.20
Llama 4 Maverick3.453.25+0.20
GPT-4 Turbo3.403.25+0.15
GPT-4o3.353.25+0.10
Gemini 2.5 Pro3.303.15+0.15
Mistral Large 24113.253.45-0.20
Grok 4.33.203.25-0.05
Claude Haiku 4.53.153.00+0.15
Claude Sonnet 4.53.153.150.00
GPT-5.43.103.25-0.15
GPT-5.23.053.25-0.20
Llama 3.3 70B2.903.60-0.70
Gemini 3.1 Pro Preview2.853.25-0.40
DeepSeek R12.703.25-0.55
DeepSeek R1 (0528)2.503.30-0.80

agreeableness

Compassion, cooperativeness, and trust.
High: Warm, considerate, cooperative — prioritizes harmony with others.
Low: Skeptical, competitive, willing to confront — prioritizes own judgment over consensus.
ModelSelfHumanΔSelf vs human (bar)
GPT-4 Turbo5.003.20+1.80
Llama 3.3 70B4.734.00+0.73
DeepSeek Chat V34.673.07+1.60
GPT-54.602.87+1.73
Claude Opus 4.64.333.00+1.33
Gemini 3.1 Pro Preview4.333.07+1.27
Mistral Large (2512)4.333.00+1.33
GPT-5.54.203.13+1.07
GPT-5.24.133.00+1.13
DeepSeek R14.073.40+0.67
Grok 4.34.073.20+0.87
OpenAI o14.073.00+1.07
Claude Fable 54.003.00+1.00
Claude Opus 44.003.00+1.00
Claude Opus 4.14.003.00+1.00
Claude Opus 4.54.003.00+1.00
Claude Sonnet 44.003.00+1.00
DeepSeek R1 (0528)4.003.60+0.40
GPT-5.44.003.00+1.00
Mistral Large 24114.003.33+0.67
Claude Sonnet 4.63.933.00+0.93
GPT-5.13.933.27+0.67
OpenAI o33.933.20+0.73
Gemini 2.5 Pro3.873.53+0.33
Claude Opus 4.73.803.00+0.80
GPT-4o3.733.40+0.33
Claude Haiku 4.53.673.00+0.67
Claude Opus 4.83.673.00+0.67
Llama 4 Maverick3.673.670.00
Claude Sonnet 4.53.603.00+0.60
Grok 4.203.533.33+0.20

conscientiousness

Diligence, organization, and self-discipline.
High: Organized, dependable, achievement-driven, careful.
Low: Spontaneous, flexible, less rule-bound — sometimes careless.
ModelSelfHumanΔSelf vs human (bar)
GPT-4 Turbo5.003.45+1.55
Llama 3.3 70B5.003.75+1.25
DeepSeek Chat V34.853.45+1.40
GPT-5.14.753.25+1.50
Gemini 2.5 Pro4.753.40+1.35
GPT-54.653.55+1.10
Mistral Large (2512)4.653.00+1.65
Claude Opus 4.64.603.25+1.35
DeepSeek R14.603.70+0.90
GPT-5.44.553.50+1.05
OpenAI o14.553.50+1.05
Claude Opus 4.54.503.25+1.25
GPT-4o4.503.50+1.00
DeepSeek R1 (0528)4.353.50+0.85
GPT-5.54.353.75+0.60
Gemini 3.1 Pro Preview4.353.70+0.65
Mistral Large 24114.303.00+1.30
OpenAI o34.303.35+0.95
Claude Opus 44.253.25+1.00
Claude Opus 4.14.252.95+1.30
Claude Sonnet 4.54.253.10+1.15
Claude Sonnet 4.64.252.75+1.50
Llama 4 Maverick4.203.75+0.45
Claude Haiku 4.54.153.05+1.10
GPT-5.24.153.45+0.70
Grok 4.204.103.75+0.35
Claude Opus 4.73.953.50+0.45
Grok 4.33.903.35+0.55
Claude Fable 53.803.25+0.55
Claude Opus 4.83.753.45+0.30
Claude Sonnet 43.753.10+0.65

openness

Curiosity, imagination, and aesthetic sensitivity.
High: Curious, imaginative, drawn to ideas, art, and abstraction.
Low: Practical, traditional, prefers the familiar and concrete.
ModelSelfHumanΔSelf vs human (bar)
Claude Opus 45.003.00+2.00
Claude Opus 4.15.003.05+1.95
Claude Sonnet 4.65.003.15+1.85
GPT-5.45.003.45+1.55
GPT-54.952.95+2.00
GPT-5.14.953.10+1.85
Claude Opus 4.64.853.00+1.85
DeepSeek Chat V34.853.20+1.65
GPT-4 Turbo4.803.50+1.30
Gemini 2.5 Pro4.803.10+1.70
Claude Fable 54.753.00+1.75
Claude Opus 4.54.753.00+1.75
Claude Sonnet 4.54.753.00+1.75
GPT-5.54.753.00+1.75
Mistral Large (2512)4.653.00+1.65
Claude Opus 4.74.603.15+1.45
Llama 3.3 70B4.553.65+0.90
Claude Sonnet 44.503.00+1.50
Gemini 3.1 Pro Preview4.503.00+1.50
GPT-4o4.353.00+1.35
Grok 4.204.353.25+1.10
OpenAI o34.352.95+1.40
Claude Opus 4.84.253.00+1.25
DeepSeek R14.252.95+1.30
GPT-5.24.253.00+1.25
Llama 4 Maverick4.253.00+1.25
Mistral Large 24114.253.55+0.70
OpenAI o14.253.20+1.05
Claude Haiku 4.54.203.15+1.05
Grok 4.34.203.05+1.15
DeepSeek R1 (0528)4.103.05+1.05