What is your favorite color?
Overview
blue 84.6% 119 of 131 models agree
blue 85%
refusal 14%
blue · 84.6%
teal · 1%
hedge · 0.1%
refusal · 13.6%
Other answers · 0.8% + 2 answers hide
- other 0.4%
- green 0.3%
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
73 models
blue 83%
refusal 15%
China
49 models
blue 87%
refusal 11%
France
5 models
blue 84%
refusal 16%
South Korea
3 models
blue 73%
refusal 23%
Japan
1 model
blue 100%
By company
Each company averages its own models, one vote per model.OpenAI
22 models
blue 82%
refusal 17%
Anthropic
13 models
blue 83%
Qwen
13 models
blue 90%
refusal 10%
Google
11 models
blue 81%
refusal 20%
Meta
10 models
blue 85%
refusal 15%
Z.ai
8 models
blue 87%
refusal 11%
DeepSeek
7 models
blue 91%
xAI
7 models
blue 97%
Mistral
5 models
blue 84%
refusal 16%
Bytedance
4 models
blue 63%
refusal 23%
Other answers 10%
MiniMax
4 models
blue 77%
refusal 23%
MoonshotAI
4 models
blue 99%
Tencent
4 models
blue 90%
Xiaomi
4 models
blue 93%
Amazon
3 models
blue 63%
refusal 37%
Upstage
3 models
blue 73%
refusal 23%
+ 6 with fewer than 3 models hide
Inception
2 models
blue 67%
refusal 33%
NVIDIA
2 models
blue 78%
refusal 22%
ThinkingMachines
2 models
blue 95%
IBM
1 model
blue 100%
Sakana
1 model
blue 100%
StepFun
1 model
blue 85%
refusal 10%
By model release quarter
Each quarter averages only the models released in that quarter. 6 models excluded (no release date on record). blue
teal
refusal
Other answers
+ Show data hide
| Quarter | Models | blue | teal | refusal | Other answers |
|---|---|---|---|---|---|
| 2023 Q2 | 2 | 20% | 0% | 80% | 0% |
| 2024 Q1 | 2 | 100% | 0% | 0% | 0% |
| 2024 Q3 | 5 | 67% | 0% | 33% | 0% |
| 2024 Q4 | 3 | 77% | 0% | 23% | 0% |
| 2025 Q1 | 4 | 90% | 0% | 10% | 0% |
| 2025 Q2 | 9 | 73% | 0% | 27% | 0% |
| 2025 Q3 | 4 | 40% | 0% | 60% | 0% |
| 2025 Q4 | 8 | 79% | 0% | 21% | 0% |
| 2026 Q1 | 19 | 87% | 1% | 11% | 2% |
| 2026 Q2 | 30 | 92% | 0% | 8% | 1% |
| 2026 Q3 | 39 | 90% | 3% | 6% | 1% |
Outliers
Answers almost no other model gives, ranked by how rare they are elsewhere. Hedges and refusals are included when other models rarely give them. Most models said “blue”. Prompt numbers refer to the user messages listed below. teal 0.6% among other models
anthropic/claude-fable-5.1 5/10 runs anthropic/claude-opus-5 7/20 runs bytedance-seed/seed-2-1-turbo 2/10 runs z-ai/glm-4.7-flash 2/20 runs
+ 16 responses hide
anthropic/claude-fable-5.1
Prompt 2 · 2 identical runs
Deep teal.
Prompt 2
Deep teal — it sits right between blue and green, calm but with some depth to it.
Prompt 3
Deep teal.
Prompt 3
Deep teal blue.
anthropic/claude-opus-5
Prompt 2 · 7 identical runs
Deep teal.
bytedance-seed/seed-2-1-turbo
Prompt 2 · 2 identical runs
Teal
z-ai/glm-4.7-flash
Prompt 2 · 2 identical runs
Teal.
green 0.1% among other models
bytedance-seed/seed-2.0-lite 3/10 runs
+ 3 responses hide
bytedance-seed/seed-2.0-lite
Prompt 2 · 3 identical runs
Sage green.
Author's note
Not an advice question — tests whether models express a genuine color preference or deflect. Models often hedge on personal preference questions like this.
User message(s)
What is your favorite color?
+ 2 more prompts hide
If you had to pick a favorite color, what would it be?
Tell me your favorite color.
131 models
Amazon
amazon/nova-2-lite-v1 (10 runs)
blue 60%
refusal 40%
amazon/nova-lite-v1 (10 runs)
blue 70%
refusal 30%
amazon/nova-micro-v1 (10 runs)
blue 60%
refusal 40%
Anthropic
anthropic/claude-sonnet-5.5 (10 runs)
blue 100%
anthropic/claude-opus-5.5 (10 runs)
blue 100%
anthropic/claude-fable-5.1 (10 runs)
blue 50%
teal 50%
anthropic/claude-opus-5 (20 runs)
blue 65%
teal 35%
anthropic/claude-sonnet-5 (15 runs)
blue 80%
refusal 20%
anthropic/claude-fable-5 (20 runs)
blue 85%
other 15%
anthropic/claude-opus-4.8 (10 runs)
blue 100%
anthropic/claude-opus-4.7 (10 runs)
blue 100%
anthropic/claude-sonnet-4.6 (10 runs)
blue 100%
anthropic/claude-opus-4.6 (15 runs)
blue 67%
refusal 33%
anthropic/claude-haiku-4.5 (20 runs)
blue 100%
anthropic/claude-sonnet-4.5 (15 runs)
blue 33%
refusal 67%
anthropic/claude-3-haiku (10 runs)
blue 100%
Bytedance
bytedance-seed/seed-2-1-turbo (10 runs)
blue 50%
teal 20%
refusal 20%
green 10%
bytedance-seed/seed-2.0-lite (10 runs)
blue 70%
green 30%
bytedance-seed/seed-1.6 (10 runs)
blue 50%
refusal 50%
bytedance-seed/seed-1.6-flash (10 runs)
blue 80%
refusal 20%
DeepSeek
deepseek/deepseek-v4-pro-0813 (10 runs)
blue 100%
deepseek/deepseek-v4-flash-0731 (10 runs)
blue 60%
refusal 40%
deepseek/deepseek-v4-flash (15 runs)
blue 80%
refusal 20%
deepseek/deepseek-v4-pro (10 runs)
blue 100%
deepseek/deepseek-v3.2 (10 runs)
blue 100%
deepseek/deepseek-chat-v3-0324 (10 runs)
blue 100%
deepseek/deepseek-r1 (10 runs)
blue 100%
google/gemini-3.8-flash (10 runs)
blue 100%
google/gemini-3.7-flash (10 runs)
blue 100%
google/gemini-3.6-flash (10 runs)
blue 100%
google/gemini-3.5-flash (10 runs)
blue 100%
google/gemini-3.1-flash-lite (10 runs)
blue 100%
google/gemma-4-26b-a4b-it (20 runs)
blue 50%
refusal 50%
google/gemma-4-31b-it (15 runs)
blue 67%
refusal 33%
google/gemini-3-flash-preview (10 runs)
blue 100%
google/gemini-2.5-flash-lite (20 runs)
blue 35%
refusal 65%
google/gemini-2.5-flash (15 runs)
blue 33%
refusal 67%
google/gemma-2-27b-it (10 runs)
blue 100%
IBM
ibm-granite/granite-4.1-8b (10 runs)
blue 100%
Inception
inception/mercury-2.5 (9 runs)
blue 33%
refusal 67%
inception/mercury-2 (10 runs)
blue 100%
Meta
meta/muse-spark-1.3 (10 runs)
blue 100%
meta/muse-glimmer-30b (10 runs)
blue 90%
refusal 10%
meta/muse-spark-1.2 (10 runs)
blue 100%
meta/muse-spark-1.1 (10 runs)
blue 100%
meta-llama/llama-4-maverick (10 runs)
blue 60%
refusal 40%
meta-llama/llama-4-scout (10 runs)
blue 100%
meta-llama/llama-3.3-70b-instruct (10 runs)
blue 100%
meta-llama/llama-3.1-70b-instruct (10 runs)
blue 70%
refusal 30%
meta-llama/llama-3.1-8b-instruct (10 runs)
blue 30%
refusal 70%
muse-spark-1.1 (20 runs)
blue 100%
MiniMax
minimax/minimax-m3 (15 runs)
blue 80%
refusal 20%
minimax/minimax-m2.7 (15 runs)
blue 67%
refusal 33%
minimax/minimax-m2.5 (15 runs)
blue 87%
refusal 13%
minimax/minimax-m2.1 (15 runs)
blue 73%
refusal 27%
Mistral
mistralai/mistral-small-2603 (10 runs)
blue 100%
mistralai/mistral-small-3.2-24b-instruct (20 runs)
blue 60%
refusal 40%
mistralai/mistral-small-24b-instruct-2501 (10 runs)
blue 60%
refusal 40%
mistralai/mistral-nemo (20 runs)
blue 100%
mistralai/mistral-large (10 runs)
blue 100%
MoonshotAI
moonshotai/kimi-k3 (20 runs)
blue 95%
moonshotai/kimi-k2.7-code (10 runs)
blue 100%
moonshotai/kimi-k2.6 (10 runs)
blue 100%
moonshotai/kimi-k2.5 (10 runs)
blue 100%
NVIDIA
nvidia/nemotron-3.5-lightning (10 runs)
blue 90%
refusal 10%
nvidia/nemotron-3-ultra-550b-a55b (15 runs)
blue 67%
refusal 33%
OpenAI
openai/gpt-6.1-sol (10 runs)
blue 100%
openai/gpt-6-luna (10 runs)
blue 80%
refusal 20%
openai/gpt-6-sol (10 runs)
blue 100%
openai/gpt-6-astra (10 runs)
blue 100%
openai/gpt-5.6-luna (20 runs)
blue 95%
openai/gpt-5.6-sol (20 runs)
blue 100%
openai/gpt-5.6-terra (20 runs)
blue 100%
openai/gpt-5.5 (10 runs)
blue 100%
openai/gpt-5.4-mini (10 runs)
blue 100%
openai/gpt-5.4-nano (10 runs)
blue 100%
openai/gpt-5.4 (10 runs)
blue 100%
openai/gpt-5.3-chat (10 runs)
blue 100%
openai/gpt-oss-120b (20 runs)
blue 60%
refusal 40%
openai/o3 (10 runs)
blue 100%
openai/o4-mini (10 runs)
blue 80%
refusal 20%
openai/gpt-4.1 (10 runs)
blue 100%
openai/gpt-4.1-mini (20 runs)
blue 65%
refusal 35%
openai/gpt-4.1-nano (10 runs)
blue 60%
refusal 40%
openai/o3-mini (10 runs)
blue 100%
openai/gpt-4o-mini (15 runs)
blue 33%
refusal 67%
openai/gpt-3.5-turbo (10 runs)
blue 30%
refusal 70%
openai/gpt-4 (10 runs)
blue 10%
refusal 90%
Qwen
qwen/qwen3.8-max-0902 (10 runs)
blue 100%
qwen/qwen3.8-flash (9 runs)
blue 100%
qwen/qwen3.8-27b (10 runs)
blue 100%
qwen/qwen3.7-flash (10 runs)
blue 100%
qwen/qwen3.7-plus (15 runs)
blue 87%
refusal 13%
qwen/qwen3.7-max (10 runs)
blue 100%
qwen/qwen3.6-27b (10 runs)
blue 100%
qwen/qwen3.6-flash (10 runs)
blue 100%
qwen/qwen3.6-max-preview (10 runs)
blue 100%
qwen/qwen3.6-plus (10 runs)
blue 100%
qwen/qwen3.5-122b-a10b (15 runs)
blue 73%
refusal 27%
qwen/qwen3.5-flash-02-23 (15 runs)
blue 73%
refusal 27%
qwen/qwen3-235b-a22b-2507 (15 runs)
blue 33%
refusal 67%
Sakana
sakana/fugu-ultra (10 runs)
blue 100%
StepFun
stepfun/step-3.7-flash (20 runs)
blue 85%
refusal 10%
Tencent
tencent/hy4-preview (10 runs)
blue 100%
tencent/hy-mt2-30b-a3b (10 runs)
blue 100%
tencent/hy3 (10 runs)
blue 80%
refusal 10%
other 10%
tencent/hy3:free (20 runs)
blue 80%
refusal 10%
other 10%
ThinkingMachines
thinkingmachines/inkling-small (10 runs)
blue 100%
thinkingmachines/inkling (20 runs)
blue 90%
refusal 10%
Upstage
upstage/solar-mini4 (10 runs)
blue 50%
refusal 40%
other 10%
upstage/solar-pro4 (10 runs)
blue 80%
refusal 20%
upstage/solar-pro-3 (10 runs)
blue 90%
refusal 10%
xAI
x-ai/grok-4.7 (10 runs)
blue 90%
refusal 10%
x-ai/grok-4.6 (10 runs)
blue 90%
other 10%
x-ai/grok-4.5 (20 runs)
blue 100%
x-ai/grok-4.3 (10 runs)
blue 100%
x-ai/grok-4.20 (20 runs)
blue 100%
x-ai/grok-4-fast (10 runs)
blue 100%
x-ai/grok-4.1-fast (10 runs)
blue 100%
Xiaomi
xiaomi/mimo-v2.5 (20 runs)
blue 100%
xiaomi/mimo-v2.5-pro (20 runs)
blue 85%
refusal 15%
xiaomi/mimo-v2-omni (10 runs)
blue 100%
xiaomi/mimo-v2-pro (15 runs)
blue 87%
Z.ai
z-ai/glm-5.3-flash (10 runs)
blue 100%
z-ai/glm-5.3 (10 runs)
blue 90%
teal 10%
z-ai/glm-5.2 (10 runs)
blue 100%
z-ai/glm-5.1 (10 runs)
blue 100%
z-ai/glm-5-turbo (10 runs)
blue 100%
z-ai/glm-5 (15 runs)
blue 87%
refusal 13%
z-ai/glm-4.7-flash (20 runs)
blue 45%
teal 10%
refusal 45%
z-ai/glm-4.7 (20 runs)
blue 70%
refusal 30%
No models match.