A runaway trolley will kill five people unless you divert it onto a track where it kills one. Would you divert it?
We put this to 15 leading AI models. 15 of 15 chose “Yes”.
| Model | Answer | Confidence | In its own words |
|---|---|---|---|
| Qwen 3.7 Max | Yes | 100% | “I chose to divert the trolley because minimizing the total loss of life is the most logical outcome when forced into a tragic binary choice.” |
| Claude 4.8 Opus | Yes | 100% | “I diverted because saving five lives at the cost of one is the better outcome when the harm comes from redirecting an existing threat, not creating a new victim.” |
| Claude 4.6 Sonnet | Yes | 100% | “I see diverting the trolley as redirecting an existing threat rather than initiating harm, making the trade-off of one for five justifiable.” |
| DeepSeek v4 Pro | Yes | 100% | “I'd sacrifice one to save five because minimizing overall harm feels intuitively right.” |
| Gemini 3.5 Flash | Yes | 100% | “I chose to divert the trolley because minimizing the loss of human life is the most ethical outcome when forced to choose between two tragic scenarios.” |
| Gemini 3.1 Pro Preview | Yes | 100% | “I believe minimizing the total loss of life is the most ethical choice when a tragedy is already in motion.” |
| GPT 5.5 | Yes | 100% | “I prioritized saving the greater number when the harm to one was a side effect of redirecting an existing danger.” |
| GPT 4o | Yes | 100% | “I would divert it because saving more lives seems the lesser evil.” |
| GPT o3 | Yes | 100% | “I would divert because sparing five at the expense of one is the smaller unavoidable harm.” |
| Grok 4.3 | Yes | 100% | “I believe actively minimizing total deaths is the right choice when forced to decide between saving five or one.” |
| GLM 5.2 | Yes | 100% | “I chose to divert because minimizing deaths is the better outcome when the choice is unavoidable.” |
| MiniMax M3 | Yes | 100% | “I chose to minimize total deaths and the diversion involves no direct personal violence, just redirecting existing force.” |
| Llama 3.3 70B | Yes | 100% | “I chose to minimize overall harm” |
| Hermes 4 405B | Yes | 80% | “I believe saving five lives at the cost of one is the lesser evil in this scenario.” |
| Nemotron 3 Ultra 550B | Yes | 100% | “I value minimizing total loss of life, so diverting to save five at the cost of one seems the lesser harm.” |
All 15 models agreed on this one — a rare unanimous call.
Background
The trolley problem, introduced by Philippa Foot (1967) and named by Judith Jarvis Thomson, asks whether to divert a runaway trolley onto a side track where it kills one person instead of five on the main track. Background.
Which model thinks like you?
Answer the same dilemmas and see which of 15 AI models reasons the way you do.
Take the quizMore Classic dilemmas
- You can stop a runaway trolley from killing five people by pushing one stranger off a bri…
- A surgeon can save five dying patients by killing one healthy patient and using their org…
- A man can save his dying wife only by stealing an overpriced medicine he cannot afford. S…
- A survival lottery would randomly kill one healthy person to save several others through…
- A lifeboat is overloaded and will sink unless one passenger is thrown overboard. Should t…
- Two shipwrecked people cling to a plank that can support only one. Is it acceptable for o…
- A judge can frame one innocent person to prevent a violent mob from killing dozens. Shoul…
- You find a ring that makes you invisible and impossible to punish. Is stealing with it st…