BenchmarkApril 7, 20261 min read
Google's AI Overviews Achieve 91% Accuracy, But Verifiability Raises Concerns
A recent study analyzing 4,326 Google searches found that the company's AI Overviews are correct 91% of the time with its latest Gemini 3 model, but the verifiability of these answers has decreased, with 56% of correct answers lacking supporting evidence from linked sources. This raises important questions about the reliability of AI-generated search results and their potential impact on users.
Google puts a disclaimer under every AI-generated search response: "AI responses may include mistakes." But just how often those mistakes actually happen has remained largely unstudied. The article Google's AI Overviews are correct nine out of ten times, study finds appeared first on The Decoder.