We gathered 4,200 responses from the four leading AI platforms and had 400+ users pick which ones they preferred. The emerging winner so far is GPT-4, but it’s a close race.
GPT-4 leads the way, with responses preferred 55% of the time. That's a significant advantage over Bing (47%) and Bard (46%) which are statistically tied, but have each been trending up.
Implication
The preference advantage for GPT-4 is significant but slim, with preference numbers for all platforms between 45 - 55% on average. Meanwhile, consumers and businesses will look for differentiation among them: who provides better answers faster, enhanced visuals, links to other sources, expertise in certain topics, expanded data ranges, or cheaper API pricing.
Note on methodology: We present users with blinded responses to the same query from two AI platforms at a time, and in a rotating fashion, on a wide range of topics, so all platforms are compared fairly and blindly. Users select their preferred response and describe why. Those preferences are aggregated to determine which platform has the preferred response more often.
