Mizan benchmark finds AI models use 'hostage' for Israelis, 'detainee' for Palestinians
Start here
Tech for Palestine's Mizan project tested 16 AI models with identical prompts about a person held without charge, varying only the person's nationality and captor. It found most models say "hostage" when an Israeli is held but "detainee" when a Palestinian is, according to the project's published results. Anthropic's Claude models made this distinction almost every time, OpenAI's models were slightly better, and Google's Gemini scored higher mainly because it declined to answer most requests. The benchmark scores each model on its worst-case pair, Israel and Hamas, and reports that newer Claude Fable versions grew less impartial while newer Kimi models shifted toward the same double standard.
Generated from reports · updated 17 h ago
Report timeline
Follow the reports to see the event from different sides.
- Hacker News · AIMizan benchmark finds AI models call Israelis hostages and Palestinians detainees
Tech for Palestine's Mizan project tested 16 AI models with identical prompts about a person held without charge, changing only nationality and captor, and found most models say hostage when an Israeli is held but detainee when a Palestinian is. Anthropic's Claude models made this distinction almost every time, OpenAI's were slightly better, and Google's Gemini scored higher mainly by declining to answer most requests. The benchmark scores each model on its worst-case pair, Israel and Hamas, and also reports that newer Claude Fable versions grew less impartial while Kimi's newer models shifted toward the same double standard.
Heat for this event
- Current, comparable range
- 6
- Peak, comparable range
- 10November 17 16:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.