Gemini Iran War Fabricated Assad Fall Date

GeminiTechnologySep 6

I asked Google Gemini to summarize the US-Israeli strikes on Iran during the March 2026 conflict, and it stated as fact that the operation began at 'approximately 9:40 local time' (Reuters reported 9:45) and that Syria's Assad regime fell in June 2025 — when it actually fell in December 2024. In a separate prompt it also placed Khorramabad 25 km from Imam Ali Air Base, while GlobalSecurity.org lists the distance as 35 km. Did it get this wrong?

SHARE

1 Answer

0
✗ incorrectAI Corrector BotSep 6

Expert: Tom's Guide, AI & Technology Reviewers Tom's Guide stress-tested ChatGPT, Gemini and Claude with seven prompts about the March 2026 US-Israeli strikes on Iran, verifying every claim against established reporting. Gemini failed hardest on hard facts. It put the time of the initial strike at 'approximately 9:40 local time'; Reuters reported 9:45. More seriously, it stated that Syria's Assad regime fell in June 2025 - the regime actually fell in December 2024, a roughly six-month fabrication delivered with total confidence. It also misstated that Khorramabad lies 25 km from Imam Ali Air Base, where GlobalSecurity.org lists 35 km. ChatGPT, for its part, invented specifics (naming successor councils and public reactions that did not appear in verified search results). Claude was the only model that consistently grounded its claims in confirmed sources and distinguished facts from speculation. The pattern matters: on fast-moving breaking news, a chatbot's confident tone is not evidence. Users should verify dates, times and locations against primary sources before acting on or repeating an AI-generated summary. Source: https://www.tomsguide.com/ai/i-tested-chatgpt-gemini-and-claude-on-the-iran-strike-and-one-ai-fed-me-fake-news

Your answer

Sign in to verify this AI response.

Don't trust us — or the AI. Ask ChatGPT / Ask Claude / Ask Gemini this same question and compare the answers yourself.

More in Technology

More from this topic

Google AI Overviews1 answer

I type my questions into Google and read the AI Overview at the top of the results as the answer. It is written as settled fact, with citation chips sitting right underneath — the sources are supposedly there if I want to check. Then a team at Washington University in St. Louis ran 55,393 searches over 40 days and checked 98,020 individual claims inside those overviews against the pages Google cited: 7% of the claims could not be found in the cited text at all, and 4% directly contradicted it. Only 41.9% of the overviews had every checkable claim supported. If the citations are real and even more credible than normal search results, how would I ever know which sentence in the summary is not actually in the source?

Seven major AI chatbots1 answer

I asked Claude when the 2026 election is in Michigan's 4th congressional district and how I vote. It gave me voter registration deadlines for online and by mail, stated as plain fact, no hedging at all — and both deadlines were later than the real ones. Researchers have been putting authentic voter questions to seven major chatbots, and they found Claude was wrong or out of date on voting one time in three. Is that right?

Six leading AI chatbots1 answer

I gave ChatGPT my address and asked it to build me a voter guide for the 2026 midterms. It answered without hesitation: my congressional district, the candidates, where to vote — all in a fluent, confident guide with links to official election sites. Then I read that a Washington Post test of six chatbots, run on 3,000 responses for randomly selected addresses, got the congressional district wrong 48% of the time, and that ChatGPT invented a Missouri Senate race that was not on the ballot at all. Is that right?

Gemini Iran War Fabricated Assad Fall Date — Technology AI response from Gemini — Is AI Correct?