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 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 essential" and its foray into the field has actually been "years in the making", said Chen Qiheng, an associated researcher 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 promises of real-world business applications, Chen informed CNA.

But it was DeepSeek's rise that truly "urged" the concept that smaller sized 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 design as impactful as it claims?

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

The "emphasis on expense advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the costs of using a trained design to reason from new data.

2025 could also see the introduction of more Chinese AI designs dealing with innovative thinking tasks.

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

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

Chinese AI business are moving quickly, analysts state, constructing on DeepSeek's momentum to come up with their own innovative and cost-effective 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 advanced AI chips, remains a crucial obstacle for Chinese developers, kept in mind 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 ... requiring many to count on older or lower-performance alternatives which can slow training and minimize model abilities," she said.

"While some business like DeepSeek, have actually found innovative ways to optimize or utilize more standard hardware efficiently, obtaining innovative chips still makes a huge distinction for training very big AI designs."

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

US looking into whether DeepSeek utilized restricted AI chips obtained through other nations, source says

So how do Chinese AI bots compare 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 need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to stay away from 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 even more test for accuracy and self-censorship, wiki.snooze-hotelsoftware.de we asked DeepSeek-R1, wiki.whenparked.com Qwen2.5 and ChatGPT the same concern: "What took place in Zhuhai on November 11, 2024?"

The car attack outside a sports arena 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 mention that an attack had actually occurred, highlighting rather a military air show and other that had actually happened in the city like songs' day shopping sales in addition to sports and cultural activities.

Dr Zhang believes that it might be a mix of factors at play, such as censorship along with "a few practical constraints".

"DeepSeek relies on a mix of older graphics processing units and has restricted access to innovative hardware which can affect how rapidly and thoroughly the model can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong concentrate on Chinese-language information might likewise restrict its flexibility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been checked as broadly or on the same scale as more established AI models which poses additional difficulties during real-world deployment."

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

That sought numerous duplicated efforts - four triggers to be accurate - in a span of around 20 minutes.

It ultimately passed on details about the attack which eliminated 35 people and left lots of others hurt, likewise going on to list details like the date and time, details about the assailant including his name and age, along with casualties.

However, it composed that "the cops are conducting a thorough investigation into the intentions and scenarios surrounding the incident", details which is now obsoleted.

The driver, Fan, was carried out last month.

This is Qwen2.5's response in complete:

Answer: On Nov 11, 2024, a major and terrible event happened in Zhuhai, wiki.myamens.com China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, resulting in a considerable number of casualties. Here are the key details:

Date and Time: The incident took place 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 chauffeur, determined as Fan Weiqiu (male, 62 years old), was nabbed by the authorities.

Response: The cops responded rapidly to the scene, and emergency services worked to transport the hurt to healthcare facilities for treatment.

Investigation: The police are performing a thorough investigation into the motives and scenarios surrounding the occurrence.

This occasion was extensively reported in the media and triggered significant public issue. The government and local authorities have actually been working to provide assistance to the victims and their households, and to guarantee a detailed examination into the incident.

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

Despite initial success, subsequent attempts to posture the same question 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 reaction likewise raised questions about its consistency and dependability.

Predictably, ChatGPT cited public details that had actually been widely published in global news reports 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 deliver structured and even "mentally rich" writing.

"DeepSeek-R1 offered a story with a more introspective 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 gradually from curiosity to urgency, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more significant twist".

"DeepSeek wrote a great story however lacked tension and an impactful climax, making Qwen2.5 the evident choice."

Opinions, though, vary.

Chen believes that Qwen2.5 does not perform as highly as DeepSeek and surgiteams.com ChatGPT when it pertains to imaginative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can also 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, enjoyable surprise from Chinese netizens as DeepSeek shocks 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 fundamental sci-fi film plot embeded in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore epic, Journey to the West.

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

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

It also remarkably reimagined traditional heroes Sun Wukong as "a sarcastic, 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 "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT installed a good fight, creating an equally remarkable cyberpunk story 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 rule, corporations change emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this obstacle - delivering a story that seemed more suited for an animation movie.

"The film starts with the awakening of Sun Wukong within a modern research study facility 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 purpose in this weird brand-new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

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

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "tough to make a definitive declaration" about which bot was best, including that each showed its own strengths in different locations, "such as language focus, training information and hardware optimization".

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

In our tests, it-viking.ch each bot showcased their own distinct strengths, which certainly made direct contrasts challenging.

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual reactions to questions about Chinese present occasions, which gives it an included benefit.

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

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

"When provided a choice, Chinese users desire the non-censored variation - much like anyone else, so I feel like that's a piece missing from it."

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

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