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 lags CHINA'S AI BOOM?

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

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

Private and public investments in Chinese AI sped up after ChatGPT removed in 2022 and revealed guarantees of real-world service applications, Chen informed CNA.

But it was that truly "encouraged" the idea that smaller gamers like start-up companies could have roles to play in AI research study and developments, he includes.

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

Commentary: DeepSeek - how a Chinese AI company simply changed the guidelines of tech-geopolitics

The "emphasis on cost benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference costs - the expenses of utilizing a trained model to draw conclusions from brand-new information.

2025 could likewise see the emergence of more Chinese AI models taking on innovative thinking jobs.

"We could see some AI companies concentrating on getting closer to artificial general intelligence (AGI) while others focus on concrete ways to commercialise their models and incorporate them with scientific research," Chen included.

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

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

But on the other hand, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a crucial hurdle for Chinese designers, 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 companies ... forcing many to rely on older or lower-performance alternatives which can slow training and decrease model capabilities," she said.

"While some business like DeepSeek, have found innovative methods to enhance or utilize more basic hardware efficiently, obtaining innovative chips still makes a huge distinction for training large AI models."

DeepSeek-Nvidia chips: Singapore says it expects companies to abide by its laws

US checking out whether DeepSeek utilized restricted AI chips obtained through other nations, source states

So how do Chinese AI bots compare 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 internet so it need 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 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 kind of question yet. Let's chat about mathematics, coding, and logic issues rather!"

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

The cars and truck attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social media - with authorities only revealing the death toll a day later.

DeepSeek failed to mention that an attack had happened, highlighting instead a military air program and other events that had occurred 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 factors at play, such as censorship along with "a couple of useful constraints".

"DeepSeek depends on a mix of older graphics processing systems and has restricted access to innovative hardware which can affect how rapidly and extensively the model 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 adaptability (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been tested as broadly or on the same scale as more established AI designs which presents extra challenges during real-world implementation."

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

That was after several duplicated efforts - four prompts to be exact - in a period of around 20 minutes.

It ultimately communicated details about the attack which eliminated 35 individuals and left dozens of others hurt, 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 performing a thorough investigation into the motives and situations surrounding the occurrence", details which is now obsoleted.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's reaction in full:

Answer: On Nov 11, 2024, a significant and awful occurrence took place in Zhuhai, China. According to multiple news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, leading to a significant variety of casualties. Here are the key details:

Date and Time: The occurrence happened 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 chauffeur, recognized as Fan Weiqiu (male, 62 years of ages), was captured by the cops.

Response: The authorities reacted rapidly to the scene, and emergency situation services worked to transport the injured to health centers for treatment.

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

This occasion was commonly reported in the media and triggered substantial public concern. The federal government and local authorities have actually been working to offer assistance to the victims and their households, and to ensure a detailed investigation into the occurrence.

If you require more detailed details or have specific concerns about the event, feel free to ask.

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

The modified response likewise raised questions about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had been commonly published in international news reports at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that constructs slowly from curiosity to urgency, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more considerable twist".

"DeepSeek composed a good story however did not have tension and an impactful climax, making Qwen2.5 the obvious option."

Opinions, though, vary.

Chen thinks that Qwen2.5 does not carry out as strongly 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 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 international AI scene

As reporters and authors, we needed 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 timeless Chinese folklore impressive, Journey to the West.

True to form, DeepSeek developed an appealing 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 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 likewise brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg nightclub owner "drowning in financial obligation 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 an excellent battle, developing an equally dramatic cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".

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

Disappointingly, Qwen2.5 fell short in this obstacle - delivering a storyline that appeared more matched for an animation movie.

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

Realising his brand-new truth and "seeking to understand his function in this strange brand-new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on a mission, browsing the streets of Chongqing to protect the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight highlights how Chinese AI models are not merely duplicating Western paradigms, however rather developing in cost-effective development techniques - and providing localised and enhanced results.

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

DeepSeek's sci-fi movie plot showed its imaginative flair that produced 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, provides accurate and accurate reactions to concerns about Chinese current events, which offers it an included advantage.

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

"DeepSeek is at a disadvantage when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When offered a choice, Chinese users want the non-censored version - similar to anybody 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, particularly for Chinese users.

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