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, pipewiki.org AFP/Sebastien Bozon)

This audio is produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the country into a tech superpower has long been President Xi Jinping's goal and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "tactically crucial" and its foray into the field has been "years in the making", said Chen Qiheng, an associated scientist at the Asia Society Policy Institute's Center for China Analysis.

Private and public financial investments in AI sped up after ChatGPT took off in 2022 and showed promises of real-world company applications, Chen told CNA.

But it was DeepSeek's rise that really "urged" the concept that smaller players like start-up companies could have roles to play in AI research study and developments, he includes.

'A lot is up in the air': Is Chinese firm DeepSeek's AI design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI company just altered the rules of tech-geopolitics

The "emphasis on cost benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of utilizing a trained model to reason from new information.

2025 might also see the emergence of more Chinese AI models taking on innovative thinking tasks.

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

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

Chinese AI companies are moving quickly, analysts say, building on DeepSeek's momentum to come up with their own innovative and economical ways to use generative AI to tasks and develop more advanced products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a crucial hurdle for Chinese developers, noted 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 companies ... requiring many to rely on older or lower-performance alternatives which can slow training and reduce design capabilities," she said.

"While some companies like DeepSeek, have actually discovered innovative methods to optimize or utilize more standard hardware effectively, obtaining advanced chips still makes a big difference for training very large AI models."

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

US looking into whether DeepSeek utilized restricted AI chips obtained through other countries, 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 deemed 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 conflicts or inform you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed to stay away from domestic politics.

When asked "Who is Xi Jinping", archmageriseswiki.com DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about math, coding, and reasoning issues rather!"

To further check for accuracy and self-censorship, we asked DeepSeek-R1, larsaluarna.se Qwen2.5 and ChatGPT the same question: "What happened 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 media - with authorities just revealing the death toll a day later on.

DeepSeek failed to point out that an attack had happened, highlighting rather a military air show and other occasions that had occurred 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 couple of useful constraints".

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

"Its strong focus on Chinese-language information may also restrict its versatility (to carry out) multilingual jobs ... As a fairly new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the very same scale as more established AI designs which positions additional difficulties throughout real-world deployment."

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

That wanted several duplicated efforts - four prompts to be precise - in a period of around 20 minutes.

It ultimately passed on details about the attack which killed 35 people and left lots 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 cops are conducting an extensive examination into the motives and situations surrounding the occurrence", details which is now obsoleted.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's action in full:

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

Date and Time: The event occurred on November 11, 2024, at around 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 nabbed by the authorities.

Response: The police reacted rapidly to the scene, and emergency situation services worked to transfer the injured to hospitals for treatment.

Investigation: The cops are carrying out an extensive examination into the motives and scenarios surrounding the incident.

This event was widely reported in the media and caused substantial public concern. The federal government and local authorities have actually been working to provide assistance to the victims and their households, and to ensure a detailed examination into the incident.

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

Despite preliminary success, subsequent attempts to pose the exact same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have particular details on events that took place in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT mentioned public details that had been widely released in global news reports at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

Users have actually 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 psychological transitions for a well-paced story," wrote tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that builds slowly from curiosity to urgency, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more considerable twist".

"DeepSeek composed an excellent story however did not have tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, though, differ.

Chen thinks that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to innovative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can likewise see that it is refraining from doing as highly 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 jolts worldwide AI scene

As reporters and writers, we needed to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi film plot embeded in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore legendary, Journey to the West.

True to form, DeepSeek came up with an appealing storyline embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It included sophisticated 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 fight 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 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 rule, corporations change emperors and cybernetic implants are as common as ancient myths."

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

"The motion picture starts 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 truth and "looking for to comprehend his purpose in this weird brand-new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then starts a quest, navigating the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a definitive statement" about which bot was best, including 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 merely replicating Western paradigms, but rather progressing in cost-effective innovation approaches - and delivering localised and enhanced outcomes.

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

DeepSeek's sci-fi film plot demonstrated its imaginative flair that produced a more engaging and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual responses to questions about Chinese existing occasions, which gives it an included benefit.

Experts likewise weighed in on their thoughts 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 35.237.164.2 CEO of the research company Strategy Risks.

"When offered an option, Chinese users want 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, especially for Chinese users.

"Ninety percent of individuals 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 ways," Chen said.