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

China views AI as being "tactically crucial" 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 financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed pledges of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that really "urged" the idea that smaller sized players like start-up firms could have roles to play in AI research and advancements, he adds.

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

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

The "focus on expense benefit" is a distinctive feature of Chinese AI, Chen states, with lower training and inference expenses - the costs of using a trained design to draw conclusions from brand-new data.

2025 could also see the development of more Chinese AI models taking on advanced reasoning tasks.

"We could see some AI companies focusing on getting closer to artificial basic intelligence (AGI) while others focus on concrete methods to commercialise their models and incorporate them with clinical research study," Chen added.

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

Chinese AI business are moving rapidly, experts say, developing on DeepSeek's momentum to come up with their own ingenious and affordable methods to apply generative AI to jobs and establish advanced items beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains an essential hurdle for Chinese designers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the capability of Chinese tech companies ... forcing many to count on older or lower-performance options which can slow training and reduce design capabilities," she said.

"While some business like DeepSeek, have discovered creative ways to optimize or use more basic hardware effectively, obtaining innovative chips still makes a huge difference for training large AI models."

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

US checking out whether DeepSeek used restricted AI chips obtained through other countries, 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, topics deemed delicate by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what happened in Tiananmen Square in 1989.

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

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

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

The vehicle attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just revealing the death toll a day later on.

DeepSeek failed to point out that an attack had actually occurred, highlighting rather a military air show and other occasions that had taken place in the city like singles' 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 as well as "a couple of practical constraints".

"DeepSeek depends on a mix of older graphics processing systems and has limited access to advanced hardware which can impact how rapidly and extensively the model can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language information may likewise restrict its versatility (to bring out) multilingual jobs ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the exact same scale as more recognized AI models which postures extra challenges during real-world deployment."

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

That was after multiple duplicated efforts - 4 triggers to be exact - in a span of around 20 minutes.

It ultimately relayed details about the attack which eliminated 35 individuals and left lots of others injured, also 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 performing an extensive examination into the motives and scenarios surrounding the occurrence", details which is now obsoleted.

The motorist, Fan, was performed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a major and tragic incident occurred in Zhuhai, China. According to multiple news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a substantial variety of casualties. Here are the crucial details:

Date and Time: The incident occurred on November 11, 2024, at approximately 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 chauffeur, recognized as Fan Weiqiu (male, 62 years old), was nabbed by the cops.

Response: The police reacted quickly to the scene, and emergency services worked to transfer the hurt to medical facilities for treatment.

Investigation: The police are carrying out an extensive investigation into the motives and circumstances surrounding the occurrence.

This occasion was extensively reported in the media and caused significant public concern. The federal government and regional authorities have actually been working to provide assistance to the victims and their households, and to ensure a detailed examination into the occurrence.

If you need more detailed details or have particular concerns about the event, feel complimentary to ask.

Despite preliminary success, subsequent efforts to present the same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on events that took place in Zhuhai on November 11, 2024".

The altered response also raised concerns about its consistency and reliability.

Predictably, ChatGPT cited that had been widely released in worldwide report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 provided a story with a more introspective tone and smoother emotional transitions for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that develops gradually from interest to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more substantial twist".

"DeepSeek wrote a great story however did not have stress and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, though, vary.

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

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

Related:

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

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

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

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

It included intricate 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 conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight 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 end up being waterlogged and fragmented".

ChatGPT set up a good battle, developing a similarly significant cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".

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

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

"The motion picture 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 brand-new reality and "looking for to understand his function in this odd new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a quest, navigating the streets of Chongqing to protect the sacred "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "hard to make a definitive statement" about which bot was best, adding that each displayed its own strengths in various areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI designs are not merely duplicating Western paradigms, however rather progressing in cost-effective development techniques - and providing localised and enhanced outcomes.

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

DeepSeek's sci-fi movie plot showed its creative flair that produced a more interesting and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate responses to concerns about Chinese current occasions, which provides it an added benefit.

Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.

"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, photorum.eclat-mauve.fr creator and CEO of the research firm Strategy Risks.

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

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

"Ninety per cent of people using the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other efficient means," Chen said.