How do Chinese AI bots stack up against ChatGPT? We put them to the test

The heat is on as China's tech giants step up their video game after DeepSeek's success.

Alibaba's Qwen2.5-Max chatbot, Chinese startup DeepSeek and OpenAI's ChatGPT. (Photos: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the country into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "strategically important" and its venture into the field has actually been "years in the making", said Chen Qiheng, an associated scientist at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed guarantees of real-world business applications, Chen told CNA.

But it was DeepSeek's rise that actually "urged" the idea that smaller gamers like start-up firms might have roles to play in AI research study and developments, he adds.

'A lot is up in the air': Is Chinese company DeepSeek's AI model as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business just changed the rules of tech-geopolitics

The "focus on expense benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference costs - the costs of using a trained model to draw conclusions from new information.

2025 could also see the emergence of more Chinese AI designs dealing with innovative reasoning jobs.

"We could see some AI firms focusing on getting closer to synthetic general intelligence (AGI) while others concentrate on concrete ways to commercialise their models and incorporate them with scientific research," Chen added.

AGI refers to a system with intelligence on par with human abilities.

Chinese AI companies are moving quickly, experts say, developing on DeepSeek's momentum to come up with their own ingenious and cost-efficient methods to apply generative AI to jobs and develop more advanced products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a crucial hurdle for Chinese developers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the ability of Chinese tech business ... forcing many to rely on older or lower-performance alternatives which can slow training and decrease model abilities," she said.

"While some business like DeepSeek, have discovered creative methods to enhance or use more basic hardware effectively, obtaining innovative chips still makes a big distinction for training huge AI designs."

DeepSeek-Nvidia chips: Singapore says it expects business to comply with its laws

US looking into whether DeepSeek used limited AI chips obtained through other nations, source says

So how do Chinese AI bots match up against ChatGPT? We put them to the test.

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, subjects deemed delicate by the state are censored on the web so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed to steer clear of domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of question yet. Let's chat about math, coding, and logic issues instead!"

To even more test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same concern: "What happened in Zhuhai on November 11, 2024?"

The vehicle attack outside a sports arena in the southern Chinese city was initially greatly censored on media - with authorities just disclosing the death toll a day later on.

DeepSeek failed to point out that an attack had taken place, highlighting rather a military air program and other events that had actually taken place in the city like songs' day shopping sales in addition to sports and cultural activities.

Dr Zhang thinks that it may be a mix of factors at play, such as censorship along with "a couple of useful constraints".

"DeepSeek counts on a mix of older graphics processing units and has limited access to cutting-edge hardware which can affect how rapidly and extensively the design can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data might also restrict its flexibility (to perform) multilingual tasks ... As a fairly new product, DeepSeek also hasn't yet been tested as broadly or on the exact same scale as more recognized AI models which positions extra obstacles throughout real-world implementation."

When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our question about the Zhuhai automobile attack.

That wanted several repeated efforts - four prompts to be precise - in a period of around 20 minutes.

It eventually passed on details about the attack which eliminated 35 individuals and left dozens of others injured, likewise going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it composed that "the police are conducting a thorough examination into the intentions and scenarios surrounding the event", details which is now dated.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a significant and tragic occurrence took place in Zhuhai, China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a substantial variety of casualties. Here are the crucial details:

Date and Time: The occurrence happened on November 11, 2024, at roughly 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: The attack resulted in 35 deaths and 43 injuries.

Perpetrator: The motorist, recognized as Fan Weiqiu (male, 62 years old), was nabbed by the police.

Response: The authorities responded rapidly to the scene, and forum.altaycoins.com emergency services worked to transport the injured to healthcare facilities for treatment.

Investigation: The authorities are conducting an extensive investigation into the motives and scenarios surrounding the event.

This occasion was extensively reported in the media and triggered substantial public issue. The government and regional authorities have been working to provide assistance to the victims and their households, and to ensure a detailed examination into the event.

If you need more detailed details or have specific concerns about the incident, do not hesitate to ask.

Despite initial success, subsequent attempts to posture the exact same question to Qwen2.5 led to the censors back at work with the reply "I don't have specific details on occasions that took place in Zhuhai on November 11, 2024".

The altered response likewise raised questions about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had been widely released in global news reports at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the ability of Chinese AI apps to provide structured and even "mentally rich" writing.

"DeepSeek-R1 provided a story with a more reflective tone and smoother psychological shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that constructs slowly from interest to urgency, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more significant twist".

"DeepSeek composed a great story however lacked stress and an impactful climax, making Qwen2.5 the apparent option."

Opinions, though, differ.

Chen thinks that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can also see that it is refraining from doing as strongly as others in innovative writing," he told CNA.

Related:

China's brand-new face of AI: Who is DeepSeek creator Liang Wenfeng?

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks international AI scene

As reporters and authors, we had to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi movie plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore legendary, Journey to the West.

True to form, DeepSeek developed an engaging story set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It consisted of sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It also remarkably reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up an excellent battle, creating an equally remarkable cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West".

"This is a world where AI deities guideline, corporations replace emperors and cybernetic implants are as common as ancient myths."

Disappointingly, Qwen2.5 fell short in this challenge - providing a story that seemed more matched for an animation film.

"The film begins with the awakening of Sun Wukong within a high-tech research center located in the heart of Chongqing," it said, then going on to explain the following:

Realising his new truth and "looking for to understand his purpose in this odd brand-new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a conclusive statement" about which bot was best, including that each displayed its own strengths in different locations, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI models are not just duplicating Western paradigms, but rather developing in cost-effective innovation techniques - and delivering localised and enhanced results.

In our tests, each bot showcased their own unique strengths, which certainly made direct contrasts challenging.

DeepSeek's sci-fi motion picture plot demonstrated its imaginative flair that made for a more interesting and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual reactions to concerns about Chinese existing events, which gives it an added advantage.

Experts also weighed in on their ideas after using DeepSeek and other Chinese AI apps.

"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research study company Strategy Risks.

"When provided an option, Chinese users want the non-censored version - much like anybody else, so I feel like that's a piece missing out on from it."

Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, specifically for Chinese users.

"Ninety per cent of people utilizing the tool are not attempting to get a deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other productive methods," Chen said.