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 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 "tactically 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 took off in 2022 and revealed promises of real-world organization applications, wavedream.wiki Chen informed CNA.

But it was DeepSeek's rise that actually "encouraged" the idea that smaller sized players like start-up firms might have functions to play in AI research 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 simply changed the rules of tech-geopolitics

The "emphasis on expense benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference expenses - the expenses of using a trained design to draw conclusions from new information.

2025 might also see the emergence of more Chinese AI designs dealing with innovative reasoning tasks.

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

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

Chinese AI business are moving rapidly, experts state, developing on DeepSeek's momentum to come up with their own innovative and economical methods to use generative AI to jobs and develop more advanced items beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a crucial hurdle for Chinese developers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the ability of Chinese tech business ... forcing numerous to depend on older or lower-performance options which can slow training and minimize design capabilities," she said.

"While some business like DeepSeek, have actually discovered innovative ways to optimize or utilize more standard hardware efficiently, obtaining innovative chips still makes a big difference for training extremely large AI designs."

DeepSeek-Nvidia chips: Singapore states it anticipates business to adhere to its laws

US checking out whether DeepSeek utilized limited 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 considered sensitive by the state are censored on the web so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed to avoid 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 problems rather!"

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

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

DeepSeek failed to point out that an attack had happened, highlighting rather a military air show and other occasions that had taken place in the city like singles' day shopping sales as well as sports and cultural activities.

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

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

"Its strong focus on Chinese-language information might likewise limit its flexibility (to bring out) multilingual jobs ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the same scale as more established AI models which poses extra difficulties during real-world release."

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

That was after numerous duplicated attempts - four triggers to be exact - in a span of around 20 minutes.

It eventually communicated details about the attack which eliminated 35 people and left lots of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, wakewiki.de as well as casualties.

However, it wrote that "the authorities are conducting a thorough investigation into the intentions and situations surrounding the incident", details which is now outdated.

The chauffeur, Fan, kousokuwiki.org was executed last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a major and tragic event took place in Zhuhai, China. According to multiple news sources, genbecle.com a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a considerable number of casualties. Here are the essential 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 driver, recognized as Fan Weiqiu (male, 62 years old), was collared by the authorities.

Response: The police reacted quickly to the scene, and emergency situation services worked to transfer the injured to medical facilities for treatment.

Investigation: The cops are conducting an extensive investigation into the motives and circumstances surrounding the event.

This event was commonly reported in the media and triggered substantial public issue. The government and local authorities have actually been working to provide assistance to the victims and their families, and to guarantee a detailed investigation into the event.

If you require more detailed details or have particular concerns about the incident, feel totally free to ask.

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

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

Predictably, ChatGPT cited public details that had actually been extensively released in global report at the time of the accident - so no surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that constructs gradually from curiosity to seriousness, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more significant twist".

"DeepSeek composed an excellent story but lacked tension and an impactful climax, making Qwen2.5 the obvious option."

Opinions, though, differ.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to creative 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 told CNA.

Related:

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

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks global 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 motion picture plot set 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 engaging story embeded in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It consisted of sophisticated settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise brilliantly reimagined traditional heroes Sun Wukong as "an ironical, 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 "silent hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT installed a great battle, creating a similarly significant cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".

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

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

"The movie begins with the awakening of Sun Wukong within a state-of-the-art 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 understand his purpose in this unusual new world", he then escapes and meets 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 safeguard the spiritual "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a conclusive statement" 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 highlights how Chinese AI designs are not just reproducing Western paradigms, however rather evolving in cost-effective development approaches - and delivering localised and enhanced results.

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

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

Unsurprisingly, the more recognized ChatGPT, bytes-the-dust.com unburdened by Chinese censorship constraints, offers accurate and factual actions to concerns about Chinese existing occasions, which provides it an included advantage.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research company Strategy Risks.

"When provided an option, Chinese users desire the non-censored version - much like anyone else, so I seem like that's a piece missing from it."

Independent Beijing-based expert 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 utilizing the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other efficient methods," Chen said.