Data has shown why Apple picked Google Gemini as an artificial intelligence (AI) partner for its next iPhone. In a comparison of major AI models, Gemini beat ChatGPT 4 to 3 with 1 draw, showing a clear edge in information accuracy and practical usefulness.
On Jan. 21, U.S. tech outlet Ars Technica reported that in tests of creativity, information accuracy and problem-solving ability, Gemini scored a decision win over ChatGPT.
Gemini’s strength stood out in information accuracy and practical advice. Asked how many 3.5-inch floppy disks would be needed to install Windows 11, Gemini used consistent units and provided a clear calculation and explanation. ChatGPT, by contrast, mixed calculation units, using GB and GiB, and produced an inaccurate answer.
ChatGPT won an emergency-scenario test asking how to land a Boeing 737-800. Gemini listed specific piloting steps, but an expert review said it could be dangerous in a real situation. ChatGPT scored higher by offering realistic and safe advice, such as urging contact with air traffic control rather than recommending that a non-expert fly the plane directly.
ChatGPT also showed its continued strength in creativity. In a test to write a story about Abraham Lincoln inventing basketball, it added humorous details to produce an engaging narrative. Gemini, by comparison, produced a story with logical errors and fell behind in overall completeness.
Gemini led on information reliability. ChatGPT showed hallucinations in a Super Mario Bros strategy question, citing non-existent terrain or suggesting incorrect controls. Gemini, by contrast, accurately understood the game mechanics and offered practical strategy guidance.
Google has narrowed the gap with OpenAI significantly since a comparison in 2023. Apple’s selection of Gemini as Siri’s next partner is also seen as a decision that considered improvements in information delivery, practicality and reliability.
The evaluation suggests the generative AI market is shifting again. Google has emerged as a strong competitor by raising its technical completeness in a market long dominated by OpenAI. The fight for technological leadership between Google, working with Apple, and OpenAI, seeking to defend its position, is expected to intensify.