Americans Predict Chinese AI Will Overtake U.S. Models

AI is developing quickly and there are many companies who have put their names in the running to be the best.

In the U.S., the major AI models include names such as ChatGPT, Claude, Gemini, Fable, and Muse. As the country continues to put resources behind “superintelligence,” the models are becoming more effective and impressive.

However, when compared to Chinese AI models, the race doesn’t seem to favor the U.S., for models such as DeepSeek, Qwen, Kimi, and GLM are reported as being nearly as good or even better than those listed previously.

In a Blind survey conducted from September 25 to October 15, 2026, 986 respondents shared their opinions on Chinese AI and its capabilities.

When asked if they have personally used an AI tool developed by a Chinese company, 60% of people said no and 50% shared that they had tried one before. Only 17%, however, said they use Chinese models regularly.

While not many of the respondents are regular users of Chinese AI tools, they seem to have a lot of faith in the tools and the companies developing them. When asked how rapidly they think Chinese AI is closing the technology gap with leading U.S. models, 39% of respondents chose the response “very rapidly — it could reach parity within 1 year,” and 25% responded “rapidly — it could reach parity within 2–3 years.”

Even those who haven’t tried Chinese AI tools believe in the country’s ability to overtake the U.S. in the industry. There have been outcries in the media about the dangers of AI and along with that is the proposed regulation of it.

If the U.S. were to slow its AI development for safety or regulatory reasons, respondents were asked how likely it would be that China would overtake the U.S. in global AI leadership. The responses further confirmed Americans’ views of Chinese AI, with 41% saying China would very likely surpass the U.S.’s progress.

Methodology

Q1. Have you personally used an AI tool developed by a Chinese company (e.g., DeepSeek, Qwen, Kimi, GLM)?

• Yes, regularly (17%)
• Yes, a few times (18%)
• I’ve tried one, but not enough to evaluate it (15%)
• No, but I’m familiar with them (27%)
• No, I’m not familiar with them (23%)

Q2. How rapidly do you believe Chinese AI is closing the technology gap with leading U.S. models?

• Very rapidly — it could reach parity within 1 year (39%)
• Rapidly — it could reach parity within 2–3 years (25%)
• Gradually — it could reach parity within 4–5 years (7%)
• Slowly — it will take more than 5 years (5%)
• It isn’t meaningfully closing the gap (7%)
• Not sure (18%)

Q3. If the U.S. slows its AI development for safety or regulatory reasons, how likely is China to overtake the U.S. in global AI leadership?

• Very likely (41%)
• Somewhat likely (20%)
• Neither likely nor unlikely (12%)
• Somewhat unlikely (8%)
• Very unlikely (8%)
• Not sure (11%)