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 video 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 created 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 becoming the world leader in AI by 2030.

China views AI as being "strategically essential" and its foray 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 financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed guarantees of real-world organization applications, Chen told CNA.

But it was DeepSeek's rise that really "encouraged" the concept that smaller players like start-up companies could 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 just altered the guidelines of tech-geopolitics

The "focus on cost advantage" is a distinctive function of Chinese AI, larsaluarna.se Chen says, with lower training and inference expenses - the expenses of using a trained design to draw conclusions from new data.

2025 might likewise see the emergence of more Chinese AI models dealing with sophisticated reasoning jobs.

"We could see some AI firms concentrating on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete ways to commercialise their models and incorporate them with scientific research study," Chen added.

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

Chinese AI companies are moving rapidly, experts state, building on DeepSeek's momentum to come up with their own innovative and cost-efficient methods to use generative AI to tasks and establish more innovative products beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's innovative AI chips, remains an essential difficulty for Chinese developers, kept in mind 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 business ... forcing numerous to depend on older or lower-performance options which can slow training and decrease design capabilities," she said.

"While some business like DeepSeek, have actually discovered creative ways to optimize or utilize more standard hardware efficiently, obtaining cutting-edge chips still makes a huge distinction for training extremely big AI designs."

DeepSeek-Nvidia chips: Singapore states it expects business to abide by its laws

US checking out whether DeepSeek utilized limited 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, subjects considered sensitive by the state are censored on the internet so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell 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 type of question yet. Let's chat about math, coding, and reasoning issues rather!"

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

The automobile attack outside a sports stadium in the southern Chinese city was initially heavily censored on Chinese social networks - with authorities only divulging the a day later on.

DeepSeek failed to mention that an attack had taken location, highlighting rather a military air show and other occasions that had taken place 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 as well as "a few practical constraints".

"DeepSeek relies on a mix of older graphics processing systems and has actually restricted access to cutting-edge hardware which can impact how quickly and extensively the design can be trained or upgraded," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language information might also limit its versatility (to carry out) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been checked as broadly or on the very same scale as more established AI models which positions extra obstacles during real-world release."

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

That was after several repeated attempts - four prompts 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, also 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 composed that "the authorities are conducting an extensive examination into the intentions and scenarios surrounding the occurrence", details which is now dated.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a major and terrible event happened in Zhuhai, China. According to several news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, leading to a substantial number of casualties. Here are the key 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 led to 35 deaths and 43 injuries.

Perpetrator: The driver, recognized as Fan Weiqiu (male, 62 years of ages), was collared by the cops.

Response: The cops reacted rapidly to the scene, and emergency services worked to transfer the injured to healthcare facilities for treatment.

Investigation: The police are conducting an extensive investigation into the motives and scenarios surrounding the event.

This event was extensively reported in the media and caused significant public issue. The government and regional authorities have actually been working to provide support 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 very same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on occasions that occurred in Zhuhai on November 11, 2024".

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

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

WHICH IS MORE CREATIVE?

Users have actually praised the ability of Chinese AI apps to deliver structured and even "emotionally rich" writing.

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

"Qwen2.5 delivered a story that develops gradually from curiosity 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 good story but did not have tension and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, though, vary.

Chen believes that Qwen2.5 does not perform 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 creative writing," he informed 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 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 fundamental sci-fi film plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek developed an interesting storyline set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges 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 in between quantum server farms".

It also brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg nightclub owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT set up a great battle, coming up with an equally dramatic cyberpunk story 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 common as ancient misconceptions."

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

"The movie begins with the awakening of Sun Wukong within a modern research center located in the heart of Chongqing," it said, then going on to explain the following:

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

The trio then embarks on a quest, navigating the streets of Chongqing to protect the spiritual "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 showed its own strengths in different locations, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI models are not just duplicating Western paradigms, however rather progressing in economical innovation methods - and providing localised and enhanced results.

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

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

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate responses to questions about Chinese present events, which provides it an added benefit.

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

"DeepSeek is at a downside when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research 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 out on from it."

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

"Ninety percent of people utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other productive methods," Chen said.