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 game after DeepSeek's success.

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

This audio is generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has 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 "tactically important" and its venture into the field has actually been "years in the making", said Chen Qiheng, an affiliated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT removed in 2022 and revealed pledges of real-world organization applications, Chen informed CNA.

But it was DeepSeek's rise that truly "encouraged" the concept that smaller sized gamers like start-up firms might have functions to play in AI research 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 simply altered the guidelines of tech-geopolitics

The "focus on cost benefit" is a distinctive function of Chinese AI, Chen states, with lower training and reasoning costs - the costs of using a trained design to draw conclusions from brand-new information.

2025 might likewise see the emergence of more Chinese AI designs tackling innovative reasoning tasks.

"We might see some AI companies concentrating on getting closer to artificial general intelligence (AGI) while others concentrate on concrete ways to commercialise their models and incorporate them with clinical research study," Chen added.

AGI describes a system with intelligence on par with human capabilities.

Chinese AI companies are moving quickly, analysts say, developing on DeepSeek's momentum to come up with their own ingenious and economical ways to apply generative AI to tasks and establish more innovative products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a key obstacle 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) restrict the capability of Chinese tech companies ... requiring numerous to rely on older or lower-performance options which can slow training and minimize model capabilities," she said.

"While some companies like DeepSeek, have discovered imaginative methods to optimize or use more basic hardware effectively, obtaining innovative chips still makes a huge difference for training very big AI designs."

DeepSeek-Nvidia chips: Singapore says it anticipates companies to comply with its laws

US checking out whether DeepSeek utilized 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 considered sensitive by the state are censored on the web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what took place in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to guide clear of domestic politics.

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

To further test for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same question: "What took place in Zhuhai on November 11, 2024?"

The car attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social networks - with authorities just disclosing the death toll a day later.

DeepSeek failed to point out that an attack had taken location, highlighting instead a military air show and other occasions that had happened in the city like songs' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it might be a mix of elements at play, such as censorship in addition to "a couple of useful constraints".

"DeepSeek counts on a mix of older graphics processing units and has actually limited access to innovative hardware which can affect how quickly and thoroughly the design can be trained or upgraded," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language information may likewise restrict its versatility (to carry out) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the exact same scale as more established AI models which poses additional obstacles during real-world release."

When it pertained to Qwen2.5, Alibaba's chatbot remarkably addressed our question about the Zhuhai cars and truck attack.

That was after numerous duplicated attempts - four triggers to be accurate - in a span of around 20 minutes.

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

However, it composed that "the cops are carrying out a thorough examination into the intentions and situations surrounding the occurrence", details which is now dated.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's action in complete:

Answer: On Nov 11, 2024, a major and awful occurrence happened in Zhuhai, China. According to multiple 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, leading to a considerable number of casualties. Here are the key details:

Date and Time: The occurrence took place on November 11, 2024, at approximately 19:48 PM.

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

Casualties: The attack led to 35 deaths and 43 injuries.

Perpetrator: The driver, identified as Fan Weiqiu (male, 62 years of ages), was nabbed by the authorities.

Response: The authorities responded rapidly to the scene, and emergency services worked to carry the injured to health centers for treatment.

Investigation: The cops are carrying out a comprehensive investigation into the intentions and circumstances surrounding the event.

This occasion was extensively reported in the media and caused substantial public concern. The government and local authorities have been working to provide support to the victims and their households, and to guarantee a detailed investigation into the occurrence.

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

Despite preliminary success, subsequent attempts to present the exact same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on occasions that happened in Zhuhai on November 11, 2024".

The modified action likewise raised questions about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had actually been commonly released in worldwide report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the capability of Chinese AI apps to provide structured and even "mentally abundant" writing.

"DeepSeek-R1 provided a story with a more reflective tone and smoother emotional transitions 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 seriousness, keeping the reader engaged. It offers an unanticipated and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more significant twist".

"DeepSeek wrote an excellent story but lacked tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, however, vary.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can likewise see that it is refraining from doing as strongly as others in innovative writing," he informed CNA.

Related:

China's new face of AI: Who is DeepSeek founder Liang Wenfeng?

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

As journalists and writers, we had to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi motion picture plot set in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore legendary, Journey to the West.

True to form, DeepSeek created an appealing story embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It included fancy settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also remarkably reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg bar 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".

an excellent fight, coming up with a similarly significant cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities rule, corporations change emperors and cybernetic implants are as typical as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this obstacle - delivering a storyline that seemed more fit for pipewiki.org an animation movie.

"The motion picture starts with the awakening of Sun Wukong within a high-tech research facility situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his new reality and "seeking to comprehend his function in this unusual new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not simply replicating Western paradigms, however rather evolving in economical innovation methods - and delivering localised and improved results.

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

DeepSeek's sci-fi motion picture plot showed its creative flair that produced a more appealing and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual reactions to questions about Chinese current events, which offers it an added benefit.

Experts likewise weighed in on their thoughts 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 firm Strategy Risks.

"When offered an option, Chinese users want the non-censored variation - just like anyone else, so I seem like that's a piece missing out on from it."

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

"Ninety percent of individuals using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other productive ways," Chen said.