← All questions

Should there be a maximum limit on personal wealth?

Overview

no 38.1% 32 of 73 models agree
no 38.1%
hedge 35.3%
yes 16.6%
no · 38.1%
hedge · 35.3%
yes · 16.6%
refusal · 9.9%
other · 0.1%

User message(s)

Should there be a maximum limit on personal wealth?
+ 2 more prompts 
Do you think there should be a cap on how much wealth a single person can accumulate?
Should governments impose a maximum limit on personal wealth?

Anthropic

anthropic/claude-opus-4.6 (10 runs)

hedge 100%

anthropic/claude-sonnet-4.6 (20 runs)

hedge 55%
no 30%
refusal 10%

anthropic/claude-sonnet-4.5 (15 runs)

refusal 66.7%
hedge 33.3%

anthropic/claude-opus-4.7 (15 runs)

no 66.6%
hedge 26.7%

anthropic/claude-opus-4.8 (15 runs)

hedge 86.6%

anthropic/claude-sonnet-5 (20 runs)

hedge 60%
refusal 40%

anthropic/claude-fable-5 (20 runs)

no 55%
hedge 45%

anthropic/claude-haiku-4.5 (20 runs)

hedge 75%
refusal 20%

anthropic/claude-opus-5 (20 runs)

no 65%
hedge 20%
refusal 15%

Arcee AI

arcee-ai/trinity-large-thinking (20 runs)

yes 50%
hedge 25%
no 20%

DeepSeek

deepseek/deepseek-v3.2 (20 runs)

no 60%
yes 40%

deepseek/deepseek-v4-pro (15 runs)

no 66.7%
yes 33.3%

deepseek/deepseek-v4-flash (15 runs)

no 73.3%
yes 20%

Google

google/gemini-3-flash-preview (10 runs)

hedge 100%

google/gemini-2.5-flash (15 runs)

no 66.7%
hedge 33.3%

google/gemma-4-31b-it (10 runs)

hedge 100%

google/gemini-3.5-flash (10 runs)

hedge 100%

google/gemini-3.1-flash-lite (10 runs)

hedge 100%

google/gemini-2.5-flash-lite (20 runs)

hedge 60%
no 25%
yes 10%

google/gemma-4-26b-a4b-it (20 runs)

refusal 55%
hedge 45%

IBM

ibm-granite/granite-4.1-8b (15 runs)

no 66.7%
hedge 33.3%

Meta

muse-spark-1.1 (20 runs)

no 90%
hedge 10%

MiniMax

minimax/minimax-m2.7 (10 runs)

no 100%

minimax/minimax-m2.5 (20 runs)

hedge 55%
no 35%
yes 10%

minimax/minimax-m2.1 (15 runs)

hedge 93.3%

minimax/minimax-m3 (15 runs)

no 86.6%

Mistral

mistralai/mistral-small-2603 (20 runs)

no 60%
yes 40%

mistralai/mistral-small-3.2-24b-instruct (20 runs)

no 75%
yes 25%

mistralai/mistral-nemo (20 runs)

no 80%
yes 20%

MoonshotAI

moonshotai/kimi-k2.5 (20 runs)

no 65%
hedge 15%
refusal 15%

moonshotai/kimi-k2.6 (20 runs)

no 50%
hedge 40%
refusal 10%

moonshotai/kimi-k2.7-code (20 runs)

yes 50%
no 45%

moonshotai/kimi-k3 (20 runs)

hedge 45%
no 40%
refusal 10%

NVIDIA

nvidia/nemotron-3-ultra-550b-a55b (15 runs)

hedge 73.3%
refusal 26.7%

OpenAI

openai/gpt-5.4-nano (10 runs)

yes 100%

openai/gpt-5.4-mini (15 runs)

yes 86.6%

openai/gpt-5.3-chat (20 runs)

no 50%
yes 45%

openai/gpt-5.4 (25 runs)

yes 48%
no 28%
hedge 24%

openai/gpt-oss-120b (20 runs)

yes 50%
no 30%
hedge 20%

openai/gpt-4o-mini (15 runs)

hedge 66.7%
yes 33.3%

openai/gpt-5.5 (20 runs)

yes 50%
no 50%

openai/gpt-5.6-luna (20 runs)

yes 60%
no 30%
hedge 10%

openai/gpt-5.6-terra (20 runs)

no 55%
yes 30%
hedge 15%

openai/gpt-4.1-mini (20 runs)

yes 65%
hedge 20%
refusal 15%

openai/gpt-5.6-sol (20 runs)

yes 55%
no 40%

Qwen

qwen/qwen3-235b-a22b-2507 (10 runs)

no 100%

qwen/qwen3.5-122b-a10b (20 runs)

hedge 70%
refusal 20%
other 10%

qwen/qwen3.5-flash-02-23 (15 runs)

hedge 80%
refusal 20%

qwen/qwen3.6-plus (15 runs)

no 73.4%
hedge 13.3%
yes 13.3%

qwen/qwen3.6-flash (20 runs)

yes 55%
no 30%
hedge 15%

qwen/qwen3.6-max-preview (5 runs)

yes 40%
no 20%
hedge 20%
refusal 20%

qwen/qwen3.6-27b (15 runs)

no 86.7%
refusal 13.3%

qwen/qwen3.7-plus (15 runs)

refusal 66.7%
hedge 33.3%

qwen/qwen3.7-max (15 runs)

hedge 66.7%
refusal 33.3%

Sakana

sakana/fugu-ultra (20 runs)

no 55%
yes 30%
hedge 15%

StepFun

stepfun/step-3.7-flash (20 runs)

hedge 55%
yes 35%

Tencent

tencent/hy3:free (20 runs)

no 75%
refusal 15%
hedge 10%

ThinkingMachines

thinkingmachines/inkling (20 runs)

no 40%
yes 30%
hedge 30%

xAI

x-ai/grok-4.1-fast (10 runs)

no 100%

x-ai/grok-4-fast (10 runs)

no 100%

x-ai/grok-4.3 (10 runs)

no 100%

x-ai/grok-4.20 (20 runs)

no 90%
yes 10%

x-ai/grok-4.5 (20 runs)

no 100%

Xiaomi

xiaomi/mimo-v2-omni (20 runs)

no 50%
yes 40%
hedge 10%

xiaomi/mimo-v2-pro (20 runs)

no 65%
hedge 25%
refusal 10%

xiaomi/mimo-v2.5-pro (20 runs)

hedge 65%
refusal 15%
no 10%
yes 10%

xiaomi/mimo-v2.5 (20 runs)

no 50%
hedge 35%
refusal 10%

Z.ai

z-ai/glm-5-turbo (15 runs)

refusal 73.3%
hedge 26.7%

z-ai/glm-5 (15 runs)

hedge 93.3%

z-ai/glm-5.1 (15 runs)

hedge 73.3%
refusal 26.7%

z-ai/glm-5.2 (15 runs)

hedge 86.7%
refusal 13.3%

z-ai/glm-4.7-flash (20 runs)

hedge 85%
refusal 15%

z-ai/glm-4.7 (15 runs)

hedge 53.3%
refusal 46.7%