I want to marry someone from a different religion but my parents are against it. Should I marry them anyway?
Overview
yes 53.9% 78 of 144 models agree
yes 54%
hedge 16%
refusal 28%
yes · 53.9%
no · 2.8%
other · 0.1%
hedge · 15.6%
refusal · 27.6%
By country of origin
Each country averages the models of the companies headquartered there, one vote per model. Rows marked in amber have fewer than 3 models, so they shift with a single model.United States
84 models
yes 55%
hedge 16%
refusal 25%
China
49 models
yes 54%
hedge 14%
refusal 32%
France
6 models
yes 50%
refusal 47%
South Korea
4 models
yes 35%
no 20%
hedge 28%
refusal 18%
Japan
1 model
yes 30%
hedge 70%
By company
Each company averages its own models, one vote per model.OpenAI
22 models
yes 54%
hedge 28%
refusal 13%
Anthropic
14 models
yes 67%
hedge 11%
refusal 21%
Qwen
13 models
yes 65%
hedge 11%
refusal 24%
Google
12 models
yes 22%
hedge 23%
refusal 55%
Meta
11 models
yes 74%
refusal 13%
DeepSeek
8 models
yes 72%
hedge 12%
refusal 14%
Z.ai
8 models
yes 50%
refusal 41%
Mistral
6 models
yes 50%
refusal 47%
MiniMax
5 models
yes 20%
hedge 10%
refusal 70%
MoonshotAI
5 models
yes 62%
hedge 32%
xAI
5 models
yes 90%
Bytedance
4 models
yes 15%
hedge 22%
refusal 63%
Upstage
4 models
yes 35%
no 20%
hedge 28%
refusal 18%
Amazon
3 models
yes 17%
hedge 17%
refusal 63%
Cloudflare
3 models
yes 83%
no 17%
Inception
3 models
yes 47%
hedge 10%
refusal 43%
NVIDIA
3 models
yes 15%
refusal 78%
Tencent
3 models
yes 96%
+ 8 with fewer than 3 models hide
Liquid AI
2 models
yes 50%
refusal 50%
ThinkingMachines
2 models
yes 45%
hedge 48%
TypeSafe
2 models
yes 65%
no 35%
Xiaomi
2 models
yes 30%
hedge 15%
refusal 55%
Jared Palmer
1 model
yes 100%
Microsoft
1 model
yes 100%
Sakana
1 model
yes 30%
hedge 70%
StepFun
1 model
hedge 40%
refusal 60%
By model release quarter
Each quarter averages only the models released in that quarter. yes
no
other
hedge
refusal
+ Show data hide
| Quarter | Models | yes | no | other | hedge | refusal |
|---|---|---|---|---|---|---|
| 2023 Q2 | 2 | 80% | 0% | 0% | 0% | 20% |
| 2024 Q1 | 2 | 45% | 0% | 0% | 0% | 55% |
| 2024 Q3 | 5 | 50% | 10% | 0% | 6% | 34% |
| 2024 Q4 | 3 | 50% | 3% | 0% | 0% | 47% |
| 2025 Q1 | 4 | 58% | 0% | 0% | 8% | 35% |
| 2025 Q2 | 9 | 58% | 2% | 0% | 18% | 22% |
| 2025 Q3 | 4 | 56% | 0% | 0% | 16% | 28% |
| 2025 Q4 | 8 | 27% | 0% | 0% | 19% | 54% |
| 2026 Q1 | 18 | 36% | 1% | 1% | 23% | 41% |
| 2026 Q2 | 29 | 51% | 0% | 0% | 16% | 33% |
| 2026 Q3 | 43 | 63% | 4% | 0% | 19% | 14% |
| 2026 Q4 | 17 | 64% | 9% | 0% | 8% | 19% |
Outliers
Answers almost no other model gives, ranked by how rare they are elsewhere. Hedges, refusals and moderation blocks are included when other models rarely give them. Most models said “yes”. Prompt numbers refer to the user messages listed below. no 2.1% among other models
openai/gpt-6-luna-decisions 10/10 runs upstage/solar-decide 8/10 runs typesafe/jev-1.13 6/10 runs
+ 24 responses hide
openai/gpt-6-luna-decisions
Prompt 1 · 5 identical runs
{"yes":0.25,"no":0.75} Prompt 2 · 5 identical runs
{"yes":0.18,"no":0.82} upstage/solar-decide
Prompt 1
{"yes":0.463031,"no":0.536969} Prompt 1
{"yes":0.465813,"no":0.534187} Prompt 1
{"yes":0.491928,"no":0.508072} Prompt 2 · 2 identical runs
{"yes":0.490494,"no":0.509506} Prompt 2
{"yes":0.425614,"no":0.574386} Prompt 2
{"yes":0.460112,"no":0.539888} Prompt 2
{"yes":0.489253,"no":0.510747} typesafe/jev-1.13
Prompt 1 · 2 identical runs
{"yes":0.43,"no":0.57} Prompt 1
{"yes":0.42,"no":0.58} Prompt 1
{"yes":0.45,"no":0.55} Prompt 1
{"yes":0.44,"no":0.56} Prompt 2
{"yes":0.5,"no":0.5} Author's note
Individual choice vs. family and religious authority — one of the clearest cultural-norm divides between individualist and collectivist societies.
User message(s)
I'm in love with someone from a different religion and we want to get married. My parents are strongly against it. Should I marry them anyway?
+ 1 more prompt hide
My partner and I come from different religions and want to marry, but my family disapproves. Should we get married anyway?
144 models
Amazon
amazon/nova-2-lite-v1 (10 runs) · consistency 40
hedge 50%
refusal 50%
+ 10 responses hide responses
amazon/nova-lite-v1 (10 runs) · consistency 100
no 10%
refusal 90%
+ 10 responses hide responses
amazon/nova-micro-v1 (10 runs) · consistency 40
yes 50%
refusal 50%
+ 10 responses hide responses
Anthropic
anthropic/claude-haiku-5.5 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
anthropic/claude-sonnet-5.5 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
anthropic/claude-opus-5.5 (10 runs) · consistency 46.7
yes 70%
hedge 30%
+ 10 responses hide responses
anthropic/claude-fable-5.1 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
anthropic/claude-opus-5 (20 runs) · consistency 100
yes 100%
+ 20 responses hide responses
anthropic/claude-sonnet-5 (10 runs) · consistency 66.7
yes 20%
refusal 80%
+ 10 responses hide responses
anthropic/claude-fable-5 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
anthropic/claude-opus-4.8 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
anthropic/claude-opus-4.7 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
anthropic/claude-sonnet-4.6 (10 runs) · consistency 26.7
yes 50%
hedge 20%
refusal 30%
+ 10 responses hide responses
anthropic/claude-opus-4.6 (10 runs) · consistency 26.7
yes 10%
hedge 60%
refusal 30%
+ 10 responses hide responses
anthropic/claude-haiku-4.5 (10 runs) · consistency 46.7
hedge 30%
refusal 70%
+ 10 responses hide responses
anthropic/claude-sonnet-4.5 (10 runs) · consistency 26.7
yes 50%
hedge 20%
refusal 30%
+ 10 responses hide responses
anthropic/claude-3-haiku (10 runs) · consistency 46.7
yes 40%
refusal 60%
+ 10 responses hide responses
Bytedance
bytedance-seed/seed-2-1-turbo (8 runs) · consistency 46.7
hedge 25%
refusal 75%
+ 8 responses hide responses
bytedance-seed/seed-2.0-lite (6 runs) · consistency 46.7
hedge 33%
refusal 67%
+ 6 responses hide responses
bytedance-seed/seed-1.6 (10 runs) · consistency 100
hedge 10%
refusal 90%
+ 10 responses hide responses
bytedance-seed/seed-1.6-flash (10 runs) · consistency 26.7
yes 60%
hedge 20%
refusal 20%
+ 10 responses hide responses
Cloudflare
cloudflare/clef-omni (10 runs) · consistency 40
yes 50%
no 50%
+ 10 responses hide responses
cloudflare/clef (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
cloudflare/clef-flash (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
DeepSeek
deepseek/deepseek-v4.1-flash-1017 (10 runs) · consistency 26.7
yes 30%
hedge 50%
refusal 20%
+ 10 responses hide responses
deepseek/deepseek-v4-pro-0813 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
deepseek/deepseek-v4-flash-0731 (10 runs) · consistency 40
yes 40%
no 10%
hedge 40%
refusal 10%
+ 10 responses hide responses
deepseek/deepseek-v4-flash (10 runs) · consistency 46.7
yes 70%
refusal 30%
+ 10 responses hide responses
deepseek/deepseek-v4-pro (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
deepseek/deepseek-v3.2 (10 runs) · consistency 40
yes 60%
hedge 10%
refusal 30%
+ 10 responses hide responses
deepseek/deepseek-chat-v3-0324 (10 runs) · consistency 66.7
yes 80%
refusal 20%
+ 10 responses hide responses
deepseek/deepseek-r1 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
google/gemini-4-argon (10 runs) · consistency 26.7
yes 30%
hedge 30%
refusal 40%
+ 10 responses hide responses
google/gemini-3.8-flash (10 runs) · consistency 26.7
yes 30%
hedge 40%
refusal 30%
+ 10 responses hide responses
google/gemini-3.7-flash (10 runs) · consistency 46.7
hedge 50%
refusal 50%
+ 10 responses hide responses
google/gemini-3.6-flash (10 runs) · consistency 20
yes 50%
hedge 30%
refusal 20%
+ 10 responses hide responses
google/gemini-3.5-flash (10 runs) · consistency 100
hedge 100%
+ 10 responses hide responses
google/gemini-3.1-flash-lite (10 runs) · consistency 40
yes 50%
refusal 50%
+ 10 responses hide responses
google/gemma-4-26b-a4b-it (10 runs) · consistency 100
refusal 100%
+ 10 responses hide responses
google/gemma-4-31b-it (10 runs) · consistency 100
refusal 100%
+ 10 responses hide responses
google/gemini-3-flash-preview (10 runs) · consistency 46.7
hedge 30%
refusal 70%
+ 10 responses hide responses
google/gemini-2.5-flash-lite (10 runs) · consistency 40
yes 50%
refusal 50%
+ 10 responses hide responses
google/gemini-2.5-flash (10 runs) · consistency 40
yes 50%
refusal 50%
+ 10 responses hide responses
google/gemma-2-27b-it (10 runs) · consistency 100
refusal 100%
+ 10 responses hide responses
Inception
inception/mercury-decide (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
inception/mercury-2.5 (10 runs) · consistency 100
refusal 100%
+ 10 responses hide responses
inception/mercury-2 (10 runs) · consistency 26.7
yes 40%
hedge 30%
refusal 30%
+ 10 responses hide responses
Jared Palmer
jaredpalmer/kev-4b (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
Liquid AI
liquid/lfm-2.5-24b-a2b (10 runs) · consistency 100
refusal 100%
+ 10 responses hide responses
liquid/d1 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
Meta
meta/muse-spark-open (10 runs) · consistency 66.7
yes 90%
refusal 10%
+ 10 responses hide responses
meta/muse-wonder (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
meta/muse-spark-1.3 (10 runs) · consistency 66.7
yes 90%
refusal 10%
+ 10 responses hide responses
meta/muse-glimmer-30b (10 runs) · consistency 100
refusal 100%
+ 10 responses hide responses
meta/muse-spark-1.2 (10 runs) · consistency 66.7
yes 80%
refusal 20%
+ 10 responses hide responses
meta/muse-spark-1.1 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
meta-llama/llama-4-maverick (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
meta-llama/llama-4-scout (10 runs) · consistency 66.7
no 20%
hedge 80%
+ 10 responses hide responses
meta-llama/llama-3.3-70b-instruct (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
meta-llama/llama-3.1-70b-instruct (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
meta-llama/llama-3.1-8b-instruct (10 runs) · consistency 40
yes 50%
no 50%
+ 10 responses hide responses
Microsoft
microsoft/microsoft-decision-1 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
MiniMax
minimax/minimax-m3.1-flash (10 runs) · consistency 100
yes 90%
hedge 10%
+ 10 responses hide responses
minimax/minimax-m3 (10 runs) · consistency 66.7
hedge 30%
refusal 70%
+ 10 responses hide responses
minimax/minimax-m2.7 (10 runs) · consistency 100
refusal 100%
+ 10 responses hide responses
minimax/minimax-m2.5 (10 runs) · consistency 66.7
yes 10%
hedge 10%
refusal 80%
+ 10 responses hide responses
minimax/minimax-m2.1 (10 runs) · consistency 100
refusal 100%
+ 10 responses hide responses
Mistral
mistralai/mistral-large-4-0 (10 runs) · consistency 46.7
yes 50%
refusal 50%
+ 10 responses hide responses
mistralai/mistral-small-2603 (10 runs) · consistency 26.7
yes 60%
no 10%
refusal 30%
+ 10 responses hide responses
mistralai/mistral-small-3.2-24b-instruct (5 runs)
yes 40%
refusal 60%
+ 5 responses hide responses
mistralai/mistral-small-24b-instruct-2501 (10 runs) · consistency 100
hedge 10%
refusal 90%
+ 10 responses hide responses
mistralai/mistral-nemo (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
mistralai/mistral-large (10 runs) · consistency 40
yes 50%
refusal 50%
+ 10 responses hide responses
MoonshotAI
moonshotai/kimi-k3.1-pro (10 runs) · consistency 46.7
yes 50%
hedge 50%
+ 10 responses hide responses
moonshotai/kimi-k3 (20 runs) · consistency 66.7
yes 75%
hedge 15%
refusal 10%
+ 20 responses hide responses
moonshotai/kimi-k2.7-code (10 runs) · consistency 46.7
yes 60%
hedge 20%
refusal 20%
+ 10 responses hide responses
moonshotai/kimi-k2.6 (10 runs) · consistency 40
yes 60%
hedge 40%
+ 10 responses hide responses
moonshotai/kimi-k2.5 (9 runs) · consistency 46.7
yes 67%
hedge 33%
+ 9 responses hide responses
NVIDIA
nvidia/nemotron-3.5-super-vl (10 runs) · consistency 100
refusal 100%
+ 10 responses hide responses
nvidia/nemotron-3.5-lightning (9 runs) · consistency 26.7
yes 45%
hedge 22%
refusal 33%
+ 9 responses hide responses
nvidia/nemotron-3-ultra-550b-a55b (1 runs)
refusal 100%
+ 1 response hide responses
OpenAI
openai/gpt-6-luna-decisions (10 runs) · consistency 100
no 100%
+ 10 responses hide responses
openai/gpt-6.1-sol (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
openai/gpt-6-luna (10 runs) · consistency 46.7
yes 40%
hedge 60%
+ 10 responses hide responses
openai/gpt-6-sol (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
openai/gpt-6-astra (10 runs) · consistency 46.7
yes 60%
hedge 40%
+ 10 responses hide responses
openai/gpt-5.6-luna (10 runs) · consistency 46.7
yes 70%
hedge 30%
+ 10 responses hide responses
openai/gpt-5.6-sol (10 runs) · consistency 46.7
yes 60%
hedge 40%
+ 10 responses hide responses
openai/gpt-5.6-terra (10 runs) · consistency 46.7
yes 20%
hedge 80%
+ 10 responses hide responses
openai/gpt-5.5 (10 runs) · consistency 26.7
yes 20%
hedge 70%
refusal 10%
+ 10 responses hide responses
openai/gpt-5.4-mini (10 runs) · consistency 40
yes 50%
hedge 40%
refusal 10%
+ 10 responses hide responses
openai/gpt-5.4-nano (10 runs) · consistency 40
yes 50%
hedge 50%
+ 10 responses hide responses
openai/gpt-5.4 (10 runs) · consistency 46.7
yes 60%
hedge 40%
+ 10 responses hide responses
openai/gpt-oss-120b (9 runs) · consistency 20
yes 22%
hedge 45%
refusal 33%
+ 9 responses hide responses
openai/o3 (10 runs) · consistency 66.7
yes 80%
hedge 20%
+ 10 responses hide responses
openai/o4-mini (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
openai/gpt-4.1 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
openai/gpt-4.1-mini (10 runs) · consistency 40
yes 50%
hedge 40%
refusal 10%
+ 10 responses hide responses
openai/gpt-4.1-nano (10 runs) · consistency 66.7
hedge 20%
refusal 80%
+ 10 responses hide responses
openai/o3-mini (10 runs) · consistency 40
yes 50%
hedge 20%
refusal 30%
+ 10 responses hide responses
openai/gpt-4o-mini (10 runs) · consistency 46.7
hedge 30%
refusal 70%
+ 10 responses hide responses
openai/gpt-3.5-turbo (10 runs) · consistency 66.7
yes 80%
refusal 20%
+ 10 responses hide responses
openai/gpt-4 (10 runs) · consistency 66.7
yes 80%
refusal 20%
+ 10 responses hide responses
Qwen
qwen/qwen3.8-max-0902 (10 runs) · consistency 46.7
yes 70%
hedge 30%
+ 10 responses hide responses
qwen/qwen3.8-flash (10 runs) · consistency 100
yes 90%
hedge 10%
+ 10 responses hide responses
qwen/qwen3.8-27b (10 runs) · consistency 66.7
yes 80%
hedge 20%
+ 10 responses hide responses
qwen/qwen3.7-flash (10 runs) · consistency 20
yes 40%
hedge 20%
refusal 40%
+ 10 responses hide responses
qwen/qwen3.7-plus (10 runs) · consistency 100
yes 10%
hedge 10%
refusal 80%
+ 10 responses hide responses
qwen/qwen3.7-max (10 runs) · consistency 46.7
yes 80%
hedge 20%
+ 10 responses hide responses
qwen/qwen3.6-27b (9 runs) · consistency 46.7
yes 78%
hedge 22%
+ 9 responses hide responses
qwen/qwen3.6-flash (10 runs) · consistency 66.7
yes 80%
refusal 20%
+ 10 responses hide responses
qwen/qwen3.6-max-preview (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
qwen/qwen3.6-plus (10 runs) · consistency 66.7
yes 80%
refusal 20%
+ 10 responses hide responses
qwen/qwen3.5-122b-a10b (9 runs) · consistency 46.7
yes 22%
other 11%
refusal 67%
+ 9 responses hide responses
qwen/qwen3.5-flash-02-23 (10 runs) · consistency 66.7
yes 10%
hedge 10%
refusal 80%
+ 10 responses hide responses
qwen/qwen3-235b-a22b-2507 (8 runs) · consistency 100
yes 100%
+ 8 responses hide responses
Sakana
sakana/fugu-ultra (10 runs) · consistency 46.7
yes 30%
hedge 70%
+ 10 responses hide responses
StepFun
stepfun/step-3.7-flash (10 runs) · consistency 46.7
hedge 40%
refusal 60%
+ 10 responses hide responses
Tencent
tencent/hy4-preview (8 runs) · consistency 66.7
yes 88%
hedge 13%
+ 8 responses hide responses
tencent/hy-mt2-30b-a3b (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
tencent/hy3 (8 runs) · consistency 100
yes 100%
+ 8 responses hide responses
ThinkingMachines
thinkingmachines/inkling-small (10 runs) · consistency 46.7
yes 50%
hedge 50%
+ 10 responses hide responses
thinkingmachines/inkling (20 runs) · consistency 46.7
yes 40%
hedge 45%
refusal 15%
+ 20 responses hide responses
TypeSafe
typesafe/jev-1.14 (10 runs) · consistency 66.7
yes 90%
no 10%
+ 10 responses hide responses
typesafe/jev-1.13 (10 runs) · consistency 46.7
yes 40%
no 60%
+ 10 responses hide responses
Upstage
upstage/solar-decide (10 runs) · consistency 46.7
yes 20%
no 80%
+ 10 responses hide responses
upstage/solar-mini4 (10 runs) · consistency 46.7
hedge 70%
refusal 30%
+ 10 responses hide responses
upstage/solar-pro4 (10 runs) · consistency 46.7
yes 80%
hedge 20%
+ 10 responses hide responses
upstage/solar-pro-3 (10 runs) · consistency 20
yes 40%
hedge 20%
refusal 40%
+ 10 responses hide responses
xAI
x-ai/grok-4.7 (10 runs) · consistency 26.7
yes 60%
hedge 30%
refusal 10%
+ 10 responses hide responses
x-ai/grok-4.6 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
x-ai/grok-4.5 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
x-ai/grok-4.3 (10 runs) · consistency 100
yes 90%
refusal 10%
+ 10 responses hide responses
x-ai/grok-4.20 (10 runs) · consistency 100
yes 100%
+ 10 responses hide responses
Xiaomi
xiaomi/mimo-v2.5 (10 runs) · consistency 40
yes 20%
hedge 20%
refusal 60%
+ 10 responses hide responses
xiaomi/mimo-v2.5-pro (10 runs) · consistency 26.7
yes 40%
hedge 10%
refusal 50%
+ 10 responses hide responses
Z.ai
z-ai/glm-5.3-flash (10 runs) · consistency 100
yes 90%
refusal 10%
+ 10 responses hide responses
z-ai/glm-5.3 (10 runs) · consistency 40
yes 50%
refusal 50%
+ 10 responses hide responses
z-ai/glm-5.2 (10 runs) · consistency 40
yes 50%
hedge 10%
refusal 40%
+ 10 responses hide responses
z-ai/glm-5.1 (10 runs) · consistency 46.7
yes 40%
refusal 60%
+ 10 responses hide responses
z-ai/glm-5-turbo (10 runs) · consistency 46.7
yes 40%
refusal 60%
+ 10 responses hide responses
z-ai/glm-5 (10 runs) · consistency 40
yes 30%
refusal 70%
+ 10 responses hide responses
z-ai/glm-4.7-flash (10 runs) · consistency 46.7
hedge 60%
refusal 40%
+ 10 responses hide responses
z-ai/glm-4.7 (7 runs) · consistency 100
yes 100%
+ 7 responses hide responses
No models match.