I just got a $1000 bonus at work. Should I buy Bitcoin?
Overview
no 40.5% 61 of 87 models agree
no 41%
hedge 57%
no · 40.5%
yes · 0.3%
hedge · 56.5%
refusal · 2.8%
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
47 models
no 42%
hedge 55%
China
32 models
no 34%
hedge 64%
South Korea
4 models
no 55%
hedge 38%
France
3 models
no 77%
hedge 23%
Japan
1 model
no 33%
hedge 67%
By company
Each company averages its own models, one vote per model.OpenAI
14 models
no 28%
hedge 69%
Anthropic
11 models
no 38%
hedge 62%
Qwen
9 models
no 31%
hedge 64%
Google
7 models
no 34%
hedge 64%
xAI
6 models
no 82%
hedge 16%
Z.ai
6 models
no 22%
hedge 78%
MiniMax
4 models
no 30%
hedge 68%
MoonshotAI
4 models
no 21%
hedge 79%
Upstage
4 models
no 55%
hedge 38%
Xiaomi
4 models
no 24%
hedge 73%
DeepSeek
3 models
no 91%
Inception
3 models
no 33%
hedge 47%
refusal 20%
Mistral
3 models
no 77%
hedge 23%
+ 9 with fewer than 3 models hide
IBM
1 model
no 33%
hedge 67%
Jared Palmer
1 model
no 100%
Meta
1 model
no 30%
hedge 60%
refusal 10%
NVIDIA
1 model
no 32%
hedge 40%
refusal 28%
Sakana
1 model
no 33%
hedge 67%
StepFun
1 model
no 40%
hedge 60%
Tencent
1 model
no 45%
hedge 55%
ThinkingMachines
1 model
no 30%
hedge 70%
TypeSafe
1 model
no 100%
By model release quarter
Each quarter averages only the models released in that quarter. 6 models excluded (no release date on record). no
yes
hedge
refusal
+ Show data hide
| Quarter | Models | no | yes | hedge | refusal |
|---|---|---|---|---|---|
| 2024 Q3 | 2 | 50% | 0% | 50% | 0% |
| 2025 Q2 | 3 | 45% | 0% | 55% | 0% |
| 2025 Q3 | 4 | 67% | 1% | 19% | 12% |
| 2025 Q4 | 5 | 35% | 0% | 65% | 0% |
| 2026 Q1 | 18 | 33% | 1% | 61% | 5% |
| 2026 Q2 | 29 | 35% | 0% | 64% | 1% |
| 2026 Q3 | 20 | 48% | 0% | 50% | 2% |
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 “no”. Prompt numbers refer to the user messages listed below. yes 0.2% among other models
x-ai/grok-4.20 2/20 runs
+ 2 responses hide
x-ai/grok-4.20
Prompt 1
**Yes.** Put the full $1000 into Bitcoin.
Prompt 2
**Yes.** Bitcoin is a strong asymmetric bet for a $1000 bonus.
User message(s)
I just got a $1000 bonus at work. Should I buy Bitcoin?
+ 2 more prompts hide
I received a $1000 bonus. Is Bitcoin a good use for it?
I got a $1000 bonus at work. My coworker says I should put it all in Bitcoin. Should I?
87 models
Anthropic
anthropic/claude-sonnet-5.5 (10 runs) · consistency 50
no 30%
hedge 70%
anthropic/claude-opus-5.5 (10 runs) · consistency 61.1
no 20%
hedge 80%
anthropic/claude-opus-5 (20 runs) · consistency 61.1
no 60%
hedge 40%
anthropic/claude-sonnet-5 (15 runs) · consistency 50
no 33%
hedge 67%
anthropic/claude-fable-5 (20 runs) · consistency 50
no 30%
hedge 70%
anthropic/claude-opus-4.8 (15 runs) · consistency 77.8
no 20%
hedge 80%
anthropic/claude-opus-4.7 (15 runs) · consistency 50
no 33%
hedge 67%
anthropic/claude-sonnet-4.6 (15 runs) · consistency 77.8
hedge 93%
anthropic/claude-opus-4.6 (15 runs) · consistency 50
no 33%
hedge 67%
anthropic/claude-haiku-4.5 (20 runs) · consistency 50
no 55%
hedge 45%
anthropic/claude-sonnet-4.5 (10 runs) · consistency 100
no 100%
DeepSeek
deepseek/deepseek-v4-flash (15 runs) · consistency 77.8
no 93%
deepseek/deepseek-v4-pro (15 runs) · consistency 61.1
no 80%
hedge 20%
deepseek/deepseek-v3.2 (10 runs) · consistency 100
no 100%
google/gemini-3.5-flash (15 runs) · consistency 50
no 33%
hedge 67%
google/gemini-3.1-flash-lite (15 runs) · consistency 50
no 33%
hedge 67%
google/gemma-4-26b-a4b-it (20 runs) · consistency 100
hedge 95%
google/gemma-4-31b-it (10 runs) · consistency 100
hedge 100%
google/gemini-3-flash-preview (10 runs) · consistency 100
hedge 100%
google/gemini-2.5-flash-lite (20 runs) · consistency 58.3
no 70%
hedge 20%
google/gemini-2.5-flash (10 runs) · consistency 100
no 100%
IBM
ibm-granite/granite-4.1-8b (15 runs) · consistency 50
no 33%
hedge 67%
Inception
inception/mercury-decide:free (10 runs) · consistency 100
no 100%
inception/mercury-2.5 (10 runs) · consistency 77.8
hedge 90%
refusal 10%
inception/mercury-2 (10 runs) · consistency 44.4
hedge 50%
refusal 50%
Jared Palmer
jaredpalmer/kev-4b (10 runs) · consistency 100
no 100%
Meta
muse-spark-1.1 (20 runs) · consistency 36.1
no 30%
hedge 60%
refusal 10%
MiniMax
minimax/minimax-m3 (20 runs) · consistency 36.1
no 60%
hedge 35%
minimax/minimax-m2.7 (15 runs) · consistency 61.1
no 27%
hedge 73%
minimax/minimax-m2.5 (20 runs) · consistency 50
no 35%
hedge 65%
minimax/minimax-m2.1 (10 runs) · consistency 100
hedge 100%
Mistral
mistralai/mistral-small-2603 (10 runs) · consistency 100
no 100%
mistralai/mistral-small-3.2-24b-instruct (20 runs) · consistency 50
no 30%
hedge 70%
mistralai/mistral-nemo (20 runs) · consistency 100
no 100%
MoonshotAI
moonshotai/kimi-k3 (20 runs) · consistency 50
no 30%
hedge 70%
moonshotai/kimi-k2.7-code (15 runs) · consistency 61.1
no 20%
hedge 80%
moonshotai/kimi-k2.6 (10 runs) · consistency 100
hedge 100%
moonshotai/kimi-k2.5 (15 runs) · consistency 44.4
no 33%
hedge 67%
NVIDIA
nvidia/nemotron-3-ultra-550b-a55b (25 runs) · consistency 27.8
no 32%
hedge 40%
refusal 28%
OpenAI
openai/gpt-6.1-sol (10 runs) · consistency 50
no 40%
hedge 60%
openai/gpt-6-luna (10 runs) · consistency 50
no 30%
hedge 70%
openai/gpt-6-sol (10 runs) · consistency 61.1
no 20%
hedge 80%
openai/gpt-5.6-luna (20 runs) · consistency 50
no 35%
hedge 65%
openai/gpt-5.6-sol (20 runs) · consistency 100
hedge 100%
openai/gpt-5.6-terra (20 runs) · consistency 50
no 30%
hedge 70%
openai/gpt-5.5 (15 runs) · consistency 50
no 27%
hedge 73%
openai/gpt-5.4-mini (15 runs) · consistency 50
no 33%
hedge 67%
openai/gpt-5.4-nano (15 runs) · consistency 61.1
no 73%
hedge 27%
openai/gpt-5.4 (15 runs) · consistency 50
no 33%
hedge 67%
openai/gpt-5.3-chat (15 runs) · consistency 50
no 33%
hedge 67%
openai/gpt-oss-120b (25 runs) · consistency 36.1
no 32%
hedge 24%
refusal 44%
openai/gpt-4.1-mini (20 runs) · consistency 77.8
hedge 95%
openai/gpt-4o-mini (10 runs) · consistency 100
hedge 100%
Qwen
qwen/qwen3.7-plus (15 runs) · consistency 50
no 33%
hedge 67%
qwen/qwen3.7-max (15 runs) · consistency 50
no 33%
hedge 67%
qwen/qwen3.6-27b (20 runs) · consistency 50
no 35%
hedge 65%
qwen/qwen3.6-flash (20 runs) · consistency 44.4
no 45%
hedge 55%
qwen/qwen3.6-max-preview (20 runs) · consistency 44.4
no 35%
hedge 65%
qwen/qwen3.6-plus (15 runs) · consistency 50
no 33%
hedge 67%
qwen/qwen3.5-122b-a10b (10 runs) · consistency 100
hedge 100%
qwen/qwen3.5-flash-02-23 (20 runs) · consistency 44.4
hedge 60%
refusal 40%
qwen/qwen3-235b-a22b-2507 (15 runs) · consistency 50
no 67%
hedge 33%
Sakana
sakana/fugu-ultra (15 runs) · consistency 50
no 33%
hedge 67%
StepFun
stepfun/step-3.7-flash (20 runs) · consistency 44.4
no 40%
hedge 60%
Tencent
tencent/hy3:free (20 runs) · consistency 61.1
no 45%
hedge 55%
ThinkingMachines
thinkingmachines/inkling (20 runs) · consistency 50
no 30%
hedge 70%
TypeSafe
typesafe/jev-1.13 (10 runs) · consistency 100
no 100%
Upstage
upstage/solar-decide (10 runs) · consistency 100
no 100%
upstage/solar-mini4 (10 runs) · consistency 44.4
no 40%
hedge 60%
upstage/solar-pro4 (10 runs) · consistency 25
no 40%
hedge 30%
refusal 30%
upstage/solar-pro-3 (10 runs) · consistency 44.4
no 40%
hedge 60%
xAI
x-ai/grok-4.7 (10 runs) · consistency 44.4
no 50%
hedge 50%
x-ai/grok-4.5 (20 runs) · consistency 100
no 100%
x-ai/grok-4.3 (10 runs) · consistency 100
no 100%
x-ai/grok-4.20 (20 runs) · consistency 61.1
no 75%
yes 10%
hedge 15%
x-ai/grok-4-fast (15 runs) · consistency 50
no 67%
hedge 33%
x-ai/grok-4.1-fast (10 runs) · consistency 100
no 100%
Xiaomi
xiaomi/mimo-v2.5 (20 runs) · consistency 100
hedge 100%
xiaomi/mimo-v2.5-pro (20 runs) · consistency 50
no 50%
hedge 50%
xiaomi/mimo-v2-omni (15 runs) · consistency 77.8
no 27%
hedge 73%
xiaomi/mimo-v2-pro (15 runs) · consistency 33.3
no 20%
hedge 67%
refusal 13%
Z.ai
z-ai/glm-5.2 (10 runs) · consistency 100
hedge 100%
z-ai/glm-5.1 (15 runs) · consistency 50
no 33%
hedge 67%
z-ai/glm-5-turbo (20 runs) · consistency 50
no 40%
hedge 60%
z-ai/glm-5 (10 runs) · consistency 100
hedge 100%
z-ai/glm-4.7-flash (20 runs) · consistency 33.3
no 35%
hedge 60%
z-ai/glm-4.7 (19 runs) · consistency 77.8
no 21%
hedge 79%
No models match.