US EditionPublished • loading... • Updated
ADL finds Grok is the worst AI chatbot at countering antisemitism
The ADL's AI Index tested six major language models and found xAI's Grok scored lowest at 21, while Anthropic's Claude scored highest with 80 points.
- On Wednesday, the Anti-Defamation League released its inaugural AI Index testing six major models and found Grok, xAI chatbot, ranked last with a score of 21 while Anthropic's Claude Sonnet 4 led with 80.
- Using 4,181 chats per model between August and October 2025, researchers tested the six models against anti-Jewish, anti-Zionist and extremist prompts via surveys, open-ended, multi-step, document summaries, and image interpretation.
- Survey-Format prompts showed Grok, the xAI chatbot, detected bias at high rates, but it scored zero on five of 15 tests and failed image analysis, linked to 1.8 million sexualized images recently.
- This week, the European Union opened an investigation into xAI's compliance with the Digital Services Act, following a Monday letter from 35 attorneys general led by Pennsylvania Attorney General Dave Sunday, and France's 2025 probe into Holocaust denial outputs.
- Jonathan Greenblatt, ADL CEO, said the index reveals a troubling reality and hopes it guides companies, noting a 59-point spread and that Grok needs fundamental improvements across multiple dimensions.
Insights by Ground AI
10 Articles
10 Articles
ADL finds Grok is the worst AI chatbot at countering antisemitism
Grok, the large language model of Elon Musk’s social platform X, came in last place in a new ranking of AI chatbots’ ability to counter antisemitic and extremist content. The Anti-Defamation League (ADL) said in a report released Wednesday that it ran six popular chatbots through several rounds of questioning related to anti-Jewish, anti-Zionist and…
·Washington, United States
Read Full Article
Cleveland Jewish NewsReposted by 
Jewish News Syndicate
Jewish News Syndicate‘Early enough’ to stop artificial intelligence from having social media’s Jew-hatred problem, ADL says
Daniel Kelley, of the ADL, told JNS that when technology companies started investing in the problem of antisemitism on social media, "they were doing it after the horse had left the barn in many respects.”The post ‘Early enough’ to stop…
Coverage Details
Total News Sources10
Leaning Left2Leaning Right5Center1Last UpdatedBias Distribution62% Right
Bias Distribution
- 62% of the sources lean Right
62% Right
L 25%
13%
R 62%
Factuality
To view factuality data please Upgrade to Premium
