vincents

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 generated 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 been "years in the making", said Chen Qiheng, an affiliated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed guarantees of real-world business applications, Chen told CNA.

But it was DeepSeek's increase that actually "encouraged" the idea that smaller players like start-up companies could have roles to play in AI research and developments, 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 company simply altered the rules of tech-geopolitics

The "emphasis on cost benefit" is a distinctive function of Chinese AI, Chen says, with lower training and inference expenses - the expenses of utilizing a trained design to draw conclusions from new data.

2025 might likewise see the introduction of more Chinese AI models tackling sophisticated thinking jobs.

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

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

Chinese AI business are moving quickly, analysts say, constructing on DeepSeek's momentum to come up with their own innovative and to apply generative AI to jobs and develop advanced items beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's innovative AI chips, remains an essential 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 count on older or lower-performance alternatives which can slow training and minimize model capabilities," she said.

"While some business like DeepSeek, have actually found innovative ways to enhance or use more fundamental hardware effectively, obtaining innovative chips still makes a big difference for training extremely big AI designs."

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

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

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 ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured to steer 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 math, coding, and reasoning problems rather!"

To further evaluate for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and wiki.myamens.com ChatGPT the exact same concern: "What took place in Zhuhai on November 11, 2024?"

The automobile attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social networks - with authorities just disclosing the death toll a day later on.

DeepSeek failed to mention that an attack had actually occurred, highlighting rather a military air program and other events that had actually happened in the city like songs' day shopping sales along with sports and cultural activities.

Dr Zhang thinks that it might be a mix of elements at play, such as censorship in addition to "a couple of practical constraints".

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

"Its strong concentrate on Chinese-language data may likewise limit its adaptability (to carry out) multilingual jobs ... As a fairly brand-new product, DeepSeek likewise hasn't yet been tested as broadly or on the same scale as more established AI models which presents extra difficulties during real-world release."

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

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

It ultimately relayed details about the attack which eliminated 35 people and left dozens of others injured, also going on to note details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it wrote that "the police are conducting a thorough examination into the intentions and situations surrounding the incident", details which is now dated.

The motorist, Fan, was performed last month.

This is Qwen2.5's action in full:

Answer: On Nov 11, 2024, a significant and terrible occurrence happened in Zhuhai, China. According to several news sources, a man named Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the key details:

Date and Time: The occurrence took place 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 driver, determined as Fan Weiqiu (male, 62 years of ages), was collared by the cops.

Response: The cops responded quickly to the scene, and emergency situation services worked to transfer the hurt to health centers for treatment.

Investigation: The police are performing a comprehensive investigation into the intentions and situations surrounding the event.

This event was commonly reported in the media and triggered considerable public issue. The federal government and regional authorities have been working to offer assistance to the victims and their households, and to make sure a detailed examination into the incident.

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

Despite initial success, subsequent attempts to pose the very same question to Qwen2.5 led to the censors back at work with the reply "I do not have specific details on events that happened in Zhuhai on November 11, 2024".

The modified reaction also raised questions about its consistency and dependability.

Predictably, ChatGPT cited public details that had actually been widely released in worldwide report 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 provide structured and even "mentally rich" writing.

"DeepSeek-R1 offered a story with a more introspective tone and smoother emotional 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 seriousness, keeping the reader engaged. It offers 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, emotionally rich story with a more considerable twist".

"DeepSeek composed a good story however lacked tension and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, though, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can likewise see that it is refraining from doing as strongly as others in imaginative writing," he informed CNA.

Related:

China's brand-new face of AI: Who is DeepSeek creator Liang Wenfeng?

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks international AI scene

As reporters and writers, we had to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore impressive, Journey to the West.

True to form, DeepSeek created an engaging storyline embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

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

It also brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken combat 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 end up being waterlogged and fragmented".

ChatGPT put up an excellent fight, developing an equally dramatic cyberpunk story 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 typical as ancient misconceptions."

Disappointingly, Qwen2.5 fell short in this difficulty - providing a storyline that appeared more fit for an animation film.

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

Realising his brand-new reality and "seeking to comprehend his function in this weird new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each struggling 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 incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "hard to make a conclusive statement" about which bot was best, adding that each displayed its own strengths in different areas, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI designs are not just reproducing Western paradigms, but rather developing in cost-efficient innovation approaches - and providing localised and improved outcomes.

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

DeepSeek's sci-fi motion picture plot showed its creative flair that made for a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate reactions to questions about Chinese current events, which offers it an added advantage.

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," kept in mind Isaac Stone Fish, founder and CEO of the research study company Strategy Risks.

"When given a choice, Chinese users want the non-censored variation - similar to anyone 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 per cent of people using the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other productive methods," Chen said.