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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

the country 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 "strategically crucial" and its foray into the field has 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 removed in 2022 and showed promises of real-world business applications, Chen informed CNA.

But it was DeepSeek's rise that truly "encouraged" the concept that smaller players like start-up firms could 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 company just altered the rules of tech-geopolitics

The "focus on cost benefit" is a distinctive feature of Chinese AI, Chen says, with lower training and reasoning costs - the expenses of utilizing a trained model to draw conclusions from new data.

2025 could also see the development of more Chinese AI designs dealing with advanced thinking tasks.

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

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

Chinese AI business are moving rapidly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative AI to jobs and develop more sophisticated items beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a crucial obstacle 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) limit the capability of Chinese tech companies ... requiring lots of to depend on older or lower-performance alternatives which can slow training and reduce model capabilities," she said.

"While some companies like DeepSeek, have discovered innovative methods to optimize or utilize more basic hardware effectively, obtaining advanced chips still makes a huge distinction for training large AI designs."

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

US looking into whether DeepSeek utilized limited 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, topics considered delicate by the state are censored on the web so it need to come as not a 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 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 logic issues rather!"

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

The automobile attack outside a sports arena in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities just divulging the death toll a day later.

DeepSeek failed to point out that an attack had actually taken location, highlighting instead a military air show and other occasions that had actually happened in the city like singles' 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 few useful constraints".

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

"Its strong concentrate on Chinese-language data may also limit its adaptability (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek likewise hasn't yet been checked as broadly or on the exact same scale as more recognized AI designs which presents additional challenges throughout real-world release."

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

That wanted multiple duplicated efforts - 4 triggers to be precise - in a span of around 20 minutes.

It eventually passed on 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, as well as casualties.

However, it wrote that "the authorities are performing a thorough investigation into the motives and situations surrounding the event", details which is now obsoleted.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a major and awful incident took place in Zhuhai, China. According to numerous news sources, a guy called Fan Weiqiu (樊某, male, setiathome.berkeley.edu 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a substantial number of casualties. Here are the crucial details:

Date and Time: The occurrence took place on November 11, 2024, at around 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 driver, identified as Fan Weiqiu (male, 62 years old), was apprehended by the police.

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

Investigation: The authorities are performing an extensive investigation into the motives and scenarios surrounding the incident.

This event was commonly reported in the media and caused significant public issue. The federal government and regional authorities have been working to offer assistance to the victims and their households, and to guarantee a detailed examination into the event.

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

Despite preliminary success, subsequent attempts to posture the exact same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that happened in Zhuhai on November 11, 2024".

The altered action also raised concerns about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had actually been extensively released in worldwide news reports at the time of the accident - 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 introspective tone and smoother emotional shifts for a well-paced story," wrote tech writer Amanda Caswell, who specialises in AI.

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

"DeepSeek wrote an excellent story however did not have tension and an impactful climax, making Qwen2.5 the obvious 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, however we can likewise see that it is refraining from doing as strongly as others in creative writing," he informed 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 jolts international AI scene

As journalists and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi movie plot set 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 set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It included 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 brilliantly reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen battle 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 a great fight, developing a similarly significant cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

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

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

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

Realising his new truth and "looking for to comprehend his function in this odd brand-new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then embarks on a mission, navigating the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a conclusive declaration" 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 designs are not just duplicating Western paradigms, however rather evolving in affordable innovation approaches - and providing localised and improved outcomes.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and factual reactions to questions about Chinese current occasions, which offers it an included advantage.

Experts likewise weighed in on their thoughts after utilizing 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 firm Strategy Risks.

"When given an option, Chinese users desire the non-censored version - much like anybody else, so I seem 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, particularly for Chinese users.

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