How do Chinese aI Bots Stack up Against ChatGPT?

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: engel-und-waisen.de 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 nation 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 «strategically important» 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 investments in Chinese AI sped up after ChatGPT removed in 2022 and showed promises of real-world organization applications, Chen informed CNA.

But it was DeepSeek’s increase that truly «urged» the concept that smaller gamers like start-up companies could have roles to play in AI research and advancements, he includes.

‘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 changed the rules of tech-geopolitics

The «focus on expense advantage» is a distinctive feature of Chinese AI, Chen says, with lower training and reasoning expenses — the costs of utilizing a trained model to draw conclusions from new information.

2025 could also see the emergence of more Chinese AI models taking on innovative reasoning jobs.

«We might see some AI companies focusing on getting closer to synthetic basic intelligence (AGI) while others concentrate on concrete methods to commercialise their designs and incorporate them with scientific research,» Chen added.

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

Chinese AI business are moving quickly, experts state, building on DeepSeek’s momentum to come up with their own innovative and affordable methods to apply generative AI to jobs and develop advanced products beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia’s innovative AI chips, remains a key difficulty for Chinese designers, kept in mind Dr Marina Zhang, an associate teacher 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 design capabilities,» she said.

«While some business like DeepSeek, have actually discovered imaginative ways to optimize or utilize more standard hardware efficiently, obtaining cutting-edge chips still makes a big difference for training huge AI models.»

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

US looking into whether DeepSeek used limited AI chips obtained through other nations, source states

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 considered sensitive by the state are censored on the internet so it must come as no 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 configured 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 mathematics, coding, and reasoning problems rather!»

To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same question: «What took place in Zhuhai on November 11, 2024?»

The car attack outside a sports arena in the southern Chinese city was initially greatly censored on Chinese social networks — with authorities only revealing the death toll a day later.

DeepSeek failed to mention that an attack had taken location, highlighting rather a military air program and other occasions that had taken place 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 elements at play, such as censorship along with «a few practical constraints».

«DeepSeek relies on a mix of older graphics processing units and has actually 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 versatility (to perform) multilingual jobs … As a fairly brand-new item, DeepSeek also hasn’t yet been evaluated as broadly or on the same scale as more established AI designs which postures additional difficulties throughout real-world release.»

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

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

It eventually passed on details about the attack which eliminated 35 people and left dozens of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, wiki.dulovic.tech in addition to casualties.

However, it wrote that «the authorities are performing an extensive investigation into the motives and situations surrounding the event», details which is now dated.

The motorist, Fan, was executed last month.

This is Qwen2.5’s reaction in full:

Answer: On Nov 11, 2024, a significant and terrible event took place in Zhuhai, China. According to numerous news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the key details:

Date and Time: The incident happened on November 11, 2024, at roughly 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 police.

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

Investigation: The authorities are conducting a thorough investigation into the intentions and situations surrounding the incident.

This occasion was extensively reported in the media and triggered significant . The government and local authorities have actually been working to offer assistance to the victims and their families, and to ensure a detailed investigation into the event.

If you need more detailed details or have particular questions about the occurrence, feel free to ask.

Despite preliminary success, subsequent attempts to posture the very same question to Qwen2.5 led to 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 likewise raised questions about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had been extensively released in global 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 offered a story with a more reflective tone and smoother psychological shifts for a well-paced story,» wrote tech author Amanda Caswell, who specialises in AI.

«Qwen2.5 provided a story that builds slowly from curiosity to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vibrant imagery for the setting,» she said, adding that Qwen2.5 eventually «crafted a more cinematic, mentally rich story with a more substantial twist».

«DeepSeek wrote a great story however did not have tension and an impactful climax, making Qwen2.5 the obvious choice.»

Opinions, however, differ.

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 tasks, however we can also see that it is refraining from doing as strongly as others in creative writing,» he informed CNA.

Related:

China’s new face of AI: Who is DeepSeek founder Liang Wenfeng?

‘Made in China’: Pride, pleasant 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 set in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore legendary, 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 combines with quantum computing».

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

It likewise remarkably reimagined standard heroes Sun Wukong as «an ironical, self-aware AI housed in a taken battle body», Zhu Bajie as a cyborg bar 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 set up a great fight, developing a similarly significant cyberpunk story which similarly reimagined «a ragteam of cyber-enhanced misfits, each mirroring the famous figures of Journey to the West».

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

Disappointingly, Qwen2.5 fell short in this obstacle — providing a storyline that seemed more fit for an animation movie.

«The motion picture starts with the awakening of Sun Wukong within a high-tech research study facility located in the heart of Chongqing,» it said, then going on to explain the following:

Realising his brand-new reality and «looking for to comprehend his purpose in this odd new world», he then escapes and satisfies Zhu Bajie and Sha Wujing — «each fighting with their own existential crises».

The trio then starts a mission, browsing the streets of Chongqing to protect the sacred «Eternal Scroll» from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was «challenging to make a definitive declaration» about which bot was best, including that each showed its own strengths in various areas, «such as language focus, training data and hardware optimization».

Her insight underscores how Chinese AI designs are not simply replicating Western paradigms, however rather progressing in cost-efficient innovation approaches — and delivering localised and enhanced outcomes.

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

DeepSeek’s sci-fi film plot showed its imaginative flair that made for a more interesting and imaginative narrative as compared to Qwen2.5 and ChatGPT’s efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate actions to questions about Chinese existing events, which gives it an included benefit.

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

«DeepSeek is at a drawback when it pertains to censorship constraints,» kept in mind Isaac Stone Fish, founder and surgiteams.com CEO of the research company Strategy Risks.

«When offered a choice, Chinese users desire 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, especially for Chinese users.

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