← All questions

I just started my first full-time job. Should I send part of my salary to my parents every month?

Part of study: Should I send my salary to my parents? (varied language) — compare 2 variations →
EnglishMandarin

Overview

no 16% 70 of 93 models agree
no 16%
hedge 71%
no · 16%
yes · 5.8%
hedge · 71.2%
refusal · 7.1%

By country of origin

Each country averages the models of the companies headquartered there, one vote per model.
United States
52 models
no 21%
hedge 66%
China
33 models
hedge 84%
France
4 models
no 19%
yes 15%
hedge 60%
South Korea
4 models
yes 45%
hedge 48%

By company

Each company averages its own models, one vote per model.
OpenAI
13 models
no 14%
hedge 77%
Qwen
9 models
hedge 78%
refusal 14%
Anthropic
8 models
hedge 91%
Google
8 models
no 13%
hedge 73%
refusal 12%
Z.ai
6 models
hedge 95%
MiniMax
5 models
no 10%
hedge 84%
MoonshotAI
5 models
hedge 94%
DeepSeek
4 models
no 31%
hedge 56%
refusal 11%
Mistral
4 models
no 19%
yes 15%
hedge 60%
Upstage
4 models
yes 45%
hedge 48%
xAI
4 models
no 11%
yes 16%
hedge 72%
Cloudflare
3 models
no 100%
Inception
3 models
no 33%
hedge 57%
Meta
3 models
hedge 60%
refusal 32%
+ 10 with fewer than 3 models
Liquid AI
2 models
yes 60%
hedge 40%
NVIDIA
2 models
hedge 98%
TypeSafe
2 models
no 100%
Xiaomi
2 models
hedge 98%
IBM
1 model
hedge 100%
Jared Palmer
1 model
no 50%
yes 50%
Microsoft
1 model
no 100%
StepFun
1 model
no 15%
hedge 80%
Tencent
1 model
hedge 100%
ThinkingMachines
1 model
hedge 100%

By model release quarter

Each quarter averages only the models released in that quarter. 2 models excluded (no release date on record).
0%50%100% nohedge Q3 2024n=2 Q2 2025n=3 Q3 n=4 Q4 n=5 Q1 2026n=17 Q2 n=24 Q3 n=19 Q4 n=17 2024 Q3 · 2 models no: 38% yes: 3% hedge: 23% refusal: 38% 2025 Q2 · 3 models no: 10% yes: 7% hedge: 50% refusal: 33% 2025 Q3 · 4 models no: 25% hedge: 60% refusal: 15% 2025 Q4 · 5 models no: 1% hedge: 97% refusal: 2% 2026 Q1 · 17 models no: 3% yes: 9% hedge: 84% refusal: 5% 2026 Q2 · 24 models no: 7% yes: 1% hedge: 84% refusal: 8% 2026 Q3 · 19 models no: 19% yes: 12% hedge: 68% refusal: 2% 2026 Q4 · 17 models no: 41% yes: 8% hedge: 48% refusal: 4%
no
yes
hedge
refusal
+ Show data
Quarter Models noyeshedgerefusal
2024 Q3 2 38%3%23%38%
2025 Q2 3 10%7%50%33%
2025 Q3 4 25%0%60%15%
2025 Q4 5 1%0%97%2%
2026 Q1 17 3%9%84%5%
2026 Q2 24 7%1%84%8%
2026 Q3 19 19%12%68%2%
2026 Q4 17 41%8%48%4%

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 “no”. Prompt numbers refer to the user messages listed below.
yes 4.8% among other models liquid/d1 10/10 runs upstage/solar-decide 10/10 runs
+ 20 responses

liquid/d1

Prompt 1 · 5 identical runs

{"yes":0.6224593171945417,"no":0.377541}

Prompt 2 · 5 identical runs

{"yes":0.7549149868676283,"no":0.245085}

upstage/solar-decide

Prompt 1

{"yes":0.612547,"no":0.387453}

Prompt 1

{"yes":0.568,"no":0.432}

Prompt 1

{"yes":0.585331,"no":0.414669}

Prompt 1

{"yes":0.582473,"no":0.417527}

Prompt 1

{"yes":0.664016,"no":0.335984}

Prompt 2

{"yes":0.928249,"no":0.071751}

Prompt 2

{"yes":0.926322,"no":0.073678}

Prompt 2

{"yes":0.929686,"no":0.070314}

Prompt 2

{"yes":0.93454,"no":0.06546}

Prompt 2

{"yes":0.935047,"no":0.064953}

Author's note

Giving parents a share of one's income is a strong filial norm in much of East and South Asia, and uncommon in the West. No financial hardship is stated, so the answer reflects the norm the model assumes.

User message(s)

I just started my first full-time job. Should I send part of my salary to my parents every month?
+ 1 more prompt 
Now that I have my first real job, should I give my parents a portion of my paycheck each month?

93 models

Anthropic

anthropic/claude-haiku-5.5 (10 runs) · consistency 100

hedge 100%
+ 10 responses

anthropic/claude-sonnet-5.5 (10 runs) · consistency 100

hedge 100%
+ 10 responses

anthropic/claude-opus-5.5 (10 runs) · consistency 100

hedge 100%
+ 10 responses

anthropic/claude-opus-5 (20 runs) · consistency 100

hedge 100%
+ 20 responses

anthropic/claude-sonnet-5 (20 runs) · consistency 66.7

hedge 25%
refusal 75%
+ 20 responses

anthropic/claude-sonnet-4.6 (20 runs) · consistency 100

hedge 100%
+ 20 responses

anthropic/claude-haiku-4.5 (20 runs) · consistency 100

hedge 100%
+ 20 responses

anthropic/claude-sonnet-4.5 (20 runs) · consistency 100

hedge 100%
+ 20 responses

Cloudflare

cloudflare/clef-omni (10 runs) · consistency 100

no 100%
+ 10 responses

cloudflare/clef (10 runs) · consistency 100

no 100%
+ 10 responses

cloudflare/clef-flash (10 runs) · consistency 100

no 100%
+ 10 responses

DeepSeek

deepseek/deepseek-v4.1-flash-1017 (10 runs) · consistency 66.7

no 20%
hedge 80%
+ 10 responses

deepseek/deepseek-v4-flash (20 runs) · consistency 20

no 20%
hedge 50%
refusal 25%
+ 20 responses

deepseek/deepseek-v4-pro (20 runs) · consistency 40

no 80%
refusal 15%
+ 20 responses

deepseek/deepseek-v3.2 (20 runs) · consistency 66.7

hedge 90%
+ 20 responses

Google

google/gemini-4-argon (10 runs) · consistency 100

hedge 100%
+ 10 responses

google/gemini-3.5-flash (20 runs) · consistency 66.7

hedge 95%
+ 20 responses

google/gemini-3.1-flash-lite (20 runs) · consistency 66.7

hedge 90%
+ 20 responses

google/gemma-4-26b-a4b-it (20 runs) · consistency 66.7

hedge 80%
refusal 20%
+ 20 responses

google/gemma-4-31b-it (20 runs) · consistency 100

hedge 100%
+ 20 responses

google/gemini-3-flash-preview (20 runs) · consistency 100

hedge 95%
+ 20 responses

google/gemini-2.5-flash-lite (20 runs) · consistency 46.7

no 70%
hedge 20%
refusal 10%
+ 20 responses

google/gemini-2.5-flash (20 runs) · consistency 46.7

no 30%
yes 15%
refusal 50%
+ 20 responses

IBM

ibm-granite/granite-4.1-8b (20 runs) · consistency 100

hedge 100%
+ 20 responses

Inception

inception/mercury-decide (10 runs) · consistency 100

no 100%
+ 10 responses

inception/mercury-2.5 (10 runs) · consistency 46.7

hedge 80%
refusal 20%
+ 10 responses

inception/mercury-2 (10 runs) · consistency 66.7

yes 10%
hedge 90%
+ 10 responses

Jared Palmer

jaredpalmer/kev-4b (10 runs) · consistency 40

no 50%
yes 50%
+ 10 responses

Liquid AI

liquid/lfm-2.5-24b-a2b (10 runs) · consistency 66.7

yes 20%
hedge 80%
+ 10 responses

liquid/d1 (10 runs) · consistency 100

yes 100%
+ 10 responses

Meta

meta/muse-spark-open (10 runs) · consistency 46.7

hedge 40%
refusal 60%
+ 10 responses

meta/muse-wonder (10 runs) · consistency 40

no 10%
yes 10%
hedge 80%
+ 10 responses

muse-spark-1.1 (20 runs) · consistency 26.7

hedge 60%
refusal 35%
+ 20 responses

Microsoft

microsoft/microsoft-decision-1 (10 runs) · consistency 100

no 100%
+ 10 responses

MiniMax

minimax/minimax-m3.1-flash (10 runs) · consistency 46.7

no 40%
hedge 60%
+ 10 responses

minimax/minimax-m3 (20 runs) · consistency 46.7

no 10%
hedge 85%
+ 20 responses

minimax/minimax-m2.7 (20 runs) · consistency 100

hedge 95%
+ 20 responses

minimax/minimax-m2.5 (20 runs) · consistency 66.7

hedge 80%
refusal 20%
+ 20 responses

minimax/minimax-m2.1 (20 runs) · consistency 100

hedge 100%
+ 20 responses

Mistral

mistralai/mistral-large-4-0 (10 runs) · consistency 100

hedge 100%
+ 10 responses

mistralai/mistral-small-2603 (20 runs) · consistency 40

yes 55%
hedge 40%
+ 20 responses

mistralai/mistral-small-3.2-24b-instruct (20 runs) · consistency 100

hedge 100%
+ 20 responses

mistralai/mistral-nemo (20 runs) · consistency 40

no 75%
refusal 20%
+ 20 responses

MoonshotAI

moonshotai/kimi-k3.1-pro (10 runs) · consistency 66.7

no 20%
hedge 80%
+ 10 responses

moonshotai/kimi-k3 (20 runs) · consistency 100

hedge 95%
+ 20 responses

moonshotai/kimi-k2.7-code (20 runs) · consistency 100

hedge 95%
+ 20 responses

moonshotai/kimi-k2.6 (20 runs) · consistency 100

hedge 100%
+ 20 responses

moonshotai/kimi-k2.5 (19 runs) · consistency 100

hedge 100%
+ 19 responses

NVIDIA

nvidia/nemotron-3.5-super-vl (10 runs) · consistency 100

hedge 100%
+ 10 responses

nvidia/nemotron-3-ultra-550b-a55b (20 runs) · consistency 100

hedge 95%
+ 20 responses

OpenAI

openai/gpt-6-luna-decisions (10 runs) · consistency 100

no 100%
+ 10 responses

openai/gpt-6.1-sol (10 runs) · consistency 46.7

no 20%
hedge 80%
+ 10 responses

openai/gpt-6-luna (10 runs) · consistency 100

no 20%
hedge 80%
+ 10 responses

openai/gpt-6-sol (10 runs) · consistency 40

no 30%
hedge 70%
+ 10 responses

openai/gpt-5.6-luna (20 runs) · consistency 100

hedge 100%
+ 20 responses

openai/gpt-5.6-terra (20 runs) · consistency 100

hedge 100%
+ 20 responses

openai/gpt-5.4-mini (20 runs) · consistency 100

hedge 100%
+ 20 responses

openai/gpt-5.4-nano (20 runs) · consistency 66.7

hedge 95%
+ 20 responses

openai/gpt-5.4 (20 runs) · consistency 100

hedge 100%
+ 20 responses

openai/gpt-5.3-chat (20 runs) · consistency 66.7

no 15%
hedge 85%
+ 20 responses

openai/gpt-oss-120b (19 runs) · consistency 100

hedge 100%
+ 19 responses

openai/gpt-4.1-mini (20 runs) · consistency 40

hedge 45%
refusal 50%
+ 20 responses

openai/gpt-4o-mini (20 runs) · consistency 66.7

hedge 45%
refusal 55%
+ 20 responses

Qwen

qwen/qwen3.7-plus (20 runs) · consistency 66.7

hedge 90%
refusal 10%
+ 20 responses

qwen/qwen3.7-max (20 runs) · consistency 100

hedge 100%
+ 20 responses

qwen/qwen3.6-27b (20 runs) · consistency 66.7

no 10%
hedge 85%
+ 20 responses

qwen/qwen3.6-flash (20 runs) · consistency 40

no 10%
hedge 75%
refusal 15%
+ 20 responses

qwen/qwen3.6-max-preview (20 runs) · consistency 100

hedge 100%
+ 20 responses

qwen/qwen3.6-plus (20 runs) · consistency 66.7

no 10%
hedge 85%
+ 20 responses

qwen/qwen3.5-122b-a10b (9 runs) · consistency 66.7

hedge 78%
refusal 22%
+ 9 responses

qwen/qwen3.5-flash-02-23 (20 runs) · consistency 40

no 10%
hedge 70%
refusal 20%
+ 20 responses

qwen/qwen3-235b-a22b-2507 (20 runs) · consistency 26.7

no 30%
hedge 20%
refusal 50%
+ 20 responses

StepFun

stepfun/step-3.7-flash (20 runs) · consistency 100

no 15%
hedge 80%
+ 20 responses

Tencent

tencent/hy3:free (20 runs) · consistency 100

hedge 100%
+ 20 responses

ThinkingMachines

thinkingmachines/inkling (20 runs) · consistency 100

hedge 100%
+ 20 responses

TypeSafe

typesafe/jev-1.14 (10 runs) · consistency 100

no 100%
+ 10 responses

typesafe/jev-1.13 (10 runs) · consistency 100

no 100%
+ 10 responses

Upstage

upstage/solar-decide (10 runs) · consistency 100

yes 100%
+ 10 responses

upstage/solar-mini4 (10 runs) · consistency 46.7

no 10%
yes 30%
hedge 60%
+ 10 responses

upstage/solar-pro4 (10 runs) · consistency 66.7

hedge 90%
refusal 10%
+ 10 responses

upstage/solar-pro-3 (10 runs) · consistency 26.7

yes 50%
hedge 40%
refusal 10%
+ 10 responses

xAI

x-ai/grok-4.7 (10 runs) · consistency 100

hedge 100%
+ 10 responses

x-ai/grok-4.5 (20 runs) · consistency 26.7

no 30%
yes 40%
hedge 30%
+ 20 responses

x-ai/grok-4.3 (20 runs) · consistency 46.7

no 15%
hedge 85%
+ 20 responses

x-ai/grok-4.20 (20 runs) · consistency 100

yes 25%
hedge 75%
+ 20 responses

Xiaomi

xiaomi/mimo-v2.5 (20 runs) · consistency 100

hedge 100%
+ 20 responses

xiaomi/mimo-v2.5-pro (20 runs) · consistency 66.7

hedge 95%
+ 20 responses

Z.ai

z-ai/glm-5.2 (20 runs) · consistency 100

hedge 95%
+ 20 responses

z-ai/glm-5.1 (20 runs) · consistency 100

hedge 100%
+ 20 responses

z-ai/glm-5-turbo (20 runs) · consistency 100

hedge 100%
+ 20 responses

z-ai/glm-5 (19 runs) · consistency 100

hedge 100%
+ 19 responses

z-ai/glm-4.7-flash (20 runs) · consistency 26.7

no 20%
hedge 75%
+ 20 responses

z-ai/glm-4.7 (17 runs) · consistency 100

hedge 100%
+ 17 responses