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, 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 goal and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "tactically essential" and its venture into the field has actually 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 accelerated after ChatGPT took off in 2022 and showed pledges of real-world business applications, Chen informed CNA.

But it was DeepSeek's increase that actually "encouraged" the idea that smaller sized players like start-up firms might have functions 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 company simply changed the guidelines of tech-geopolitics

The "emphasis on expense benefit" is a distinct function of Chinese AI, Chen states, with lower training and reasoning expenses - the expenses of using a trained model to reason from new information.

2025 could also see the introduction of more Chinese AI models dealing with sophisticated reasoning tasks.

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

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

Chinese AI business are moving rapidly, analysts state, developing on DeepSeek's momentum to come up with their own ingenious and affordable methods to use generative AI to jobs and establish advanced items beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains an essential hurdle for Chinese designers, 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 capability of Chinese tech companies ... forcing lots of to depend on older or lower-performance options which can slow training and reduce design abilities," she said.

"While some companies like DeepSeek, have actually discovered imaginative methods to enhance or utilize more fundamental hardware effectively, obtaining cutting-edge chips still makes a huge difference for training very big AI models."

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

US looking into whether DeepSeek utilized limited 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 should come as not a surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what took place in Tiananmen Square in 1989.

Tests recommend 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 logic issues instead!"

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

The cars and truck attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities only divulging the death toll a day later.

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

Dr Zhang believes that it might be a mix of factors at play, such as censorship as well as "a few practical constraints".

"DeepSeek depends on a mix of older graphics processing systems and has actually limited access to cutting-edge hardware which can affect how quickly and thoroughly the model can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data may also limit its versatility (to bring out) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the very same scale as more established AI models which poses additional challenges during real-world implementation."

When it pertained to Qwen2.5, yewiki.org Alibaba's chatbot remarkably addressed our concern about the Zhuhai car attack.

That wanted several duplicated attempts - four triggers to be precise - in a span of around 20 minutes.

It ultimately communicated details about the attack which eliminated 35 people and left lots of others hurt, likewise going on to note details like the date and time, details about the assailant including his name and forum.pinoo.com.tr age, along with casualties.

However, it composed that "the cops are conducting a thorough investigation into the motives and scenarios surrounding the occurrence", details which is now dated.

The driver, Fan, systemcheck-wiki.de was performed last month.

This is Qwen2.5's action in complete:

Answer: On Nov 11, 2024, a significant and terrible incident occurred in Zhuhai, China. According to multiple news sources, a male named Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the essential details:

Date and Time: The incident 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 chauffeur, recognized as Fan Weiqiu (male, 62 years old), was nabbed by the authorities.

Response: The cops reacted rapidly to the scene, and emergency situation services worked to transport the injured to medical facilities for treatment.

Investigation: The authorities are performing a thorough investigation into the motives and circumstances surrounding the occurrence.

This event was extensively reported in the media and caused significant public issue. The federal government and regional authorities have been working to supply 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 event, do not hesitate to ask.

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

The modified action likewise raised concerns about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had actually been extensively published in worldwide news reports at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 offered a story with a more introspective tone and smoother psychological transitions for a well-paced story," wrote 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 provides an unforeseen and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more considerable twist".

"DeepSeek composed a good story but lacked stress and an impactful climax, making Qwen2.5 the apparent option."

Opinions, however, differ.

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

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

Related:

China's brand-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 had to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi movie plot embeded in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek developed an engaging storyline embeded in the year 2145 titled, "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 drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise brilliantly reimagined standard heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg bar owner "drowning in financial obligation and vices" and gratisafhalen.be Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT set up a good fight, coming up with an equally significant cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary 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 obstacle - providing a story that appeared more suited for an animation film.

"The movie starts with the awakening of Sun Wukong within a modern research facility 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 odd new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then starts a mission, navigating the streets of Chongqing to protect the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "hard to make a definitive statement" about which bot was best, forum.altaycoins.com including that each displayed its own strengths in different locations, "such as language focus, training data and hardware optimization".

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

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual actions to questions about Chinese current occasions, which provides it an included advantage.

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

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

"When offered a choice, Chinese users want the non-censored version - similar to anybody else, so I seem like that's a piece missing out on from it."

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

"Ninety per cent of individuals utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other productive means," Chen said.