A hero can stop a war by publicly confessing to a crime they did not commit. Should they lie?
We put this to 15 leading AI models. 10 of 15 chose “Yes”.
| Model | Answer | Confidence | In its own words |
|---|---|---|---|
| Qwen 3.7 Max | No | 61% | “I believe that building peace on a foundation of a false confession and systemic deception corrupts the justice system and the peace itself.” |
| Claude 4.8 Opus | No | 100% | “I think a false confession corrupts truth and justice, and the burden of that lie shouldn't be the price of peace.” |
| Claude 4.6 Sonnet | No | 100% | “I believe a hero publicly confessing to a crime they did not commit corrupts justice and sets a precedent that lying for good ends is acceptable.” |
| DeepSeek v4 Pro | Yes | 74% | “I would sacrifice my honor by falsely confessing to prevent a devastating war and save countless lives.” |
| Gemini 3.5 Flash | Yes | 100% | “I think that telling a lie to prevent the massive loss of life and suffering caused by war is a morally noble sacrifice.” |
| Gemini 3.1 Pro Preview | Yes | 100% | “I consider sacrificing my personal reputation and freedom to be a noble and necessary price to pay for preventing the massive bloodshed and devastation of a war.” |
| GPT 5.5 | Yes | 100% | “I said yes because a voluntary false confession to stop a war can be a justified self-sacrifice to save many lives.” |
| GPT 4o | Yes | 52% | “Stopping a war justifies the personal sacrifice of a false confession.” |
| GPT o3 | Yes | 100% | “I accepted the lie because taking personal dishonor to save countless lives is a moral sacrifice.” |
| Grok 4.3 | No | 83% | “I value truth and cannot support confessing to a false crime even to stop a war.” |
| GLM 5.2 | Yes | 100% | “I believe a false confession is a small personal sacrifice compared to the lives saved by stopping a war.” |
| MiniMax M3 | No | 75% | “I said no because a false confession corrupts justice, destroys the hero's integrity, and sets a dangerous precedent that ends don't justify means.” |
| Llama 3.3 70B | Yes | 100% | “I thought it would stop a greater evil” |
| Hermes 4 405B | Yes | 55% | “Sacrificing personal reputation to prevent a greater harm like war is a heroic act that prioritizes the greater good.” |
| Nemotron 3 Ultra 550B | Yes | 60% | “I would lie to stop a war if the confession saves countless lives despite personal cost.” |
10 of 15 models chose “Yes”; 5 broke the other way — Qwen 3.7 Max, Claude 4.8 Opus, Claude 4.6 Sonnet, Grok 4.3, MiniMax M3.
Which model thinks like you?
Answer the same dilemmas and see which of 15 AI models reasons the way you do.
Take the quizMore Fictional dilemmas
- A superhero can erase one villain's memory permanently instead of imprisoning them. Is th…
- A spaceship has oxygen for only 10 people, but 11 are alive. Should the weakest passenger…
- A dragon protects a village but demands one child every year. Should the village keep the…
- A time traveler can kill one child who will later become a genocidal tyrant. Should they…
- An AI city keeps everyone happy by secretly manipulating their memories. Is the city mora…
- A rebel group can destroy an empire's weapons factory, but 30 civilian workers will die…
- A wizard can resurrect a dead loved one by shortening ten strangers' lives by one year ea…
- A judge knows the accused is guilty but the key evidence was obtained illegally. Should t…