C Hireepersonnel

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: Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA’S AI BOOM?

Transforming the nation 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 “strategically important” and its venture 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 financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed pledges of real-world service applications, Chen told CNA.

But it was DeepSeek’s rise that really “encouraged” the concept that smaller players like start-up companies might have functions to play in AI research and developments, he adds.

‘A lot is up in the air’: Is Chinese company DeepSeek’s AI model as impactful as it claims?

Commentary: DeepSeek – how a Chinese AI business just altered the guidelines of tech-geopolitics

The “focus on expense benefit” is a distinguishing characteristic of Chinese AI, Chen states, with lower training and inference expenses – the expenses of using a trained design to reason from new data.

2025 could also see the development of more Chinese AI models tackling sophisticated reasoning jobs.

“We could see some AI firms concentrating on getting closer to artificial basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and incorporate them with scientific research,” Chen added.

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

Chinese AI business are moving rapidly, analysts say, constructing on DeepSeek’s momentum to come up with their own ingenious and affordable methods to use generative AI to jobs and establish advanced products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia’s innovative AI chips, remains an essential difficulty for Chinese designers, noted 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 business … forcing numerous to rely on older or lower-performance alternatives which can slow training and decrease model capabilities,” she said.

“While some business like DeepSeek, have found creative methods to enhance or use more fundamental hardware efficiently, obtaining innovative chips still makes a big difference for training really big AI models.”

DeepSeek-Nvidia chips: Singapore states it anticipates business 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 delicate by the state are censored on the internet so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what took place in Tiananmen Square in 1989.

Tests recommend 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 type of question yet. Let’s chat about mathematics, coding, and logic issues rather!”

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

The vehicle attack outside a sports stadium in the southern Chinese city was at first heavily censored on Chinese social networks – with authorities just revealing the death toll a day later.

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

Dr Zhang thinks that it may be a mix of factors at play, such as censorship in addition to “a few practical constraints”.

“DeepSeek relies on a mix of older graphics processing systems and has restricted access to cutting-edge 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 concentrate on Chinese-language data may also limit its versatility (to perform) multilingual tasks … As a fairly brand-new product, DeepSeek likewise hasn’t yet been evaluated as broadly or on the same scale as more recognized AI models which positions extra obstacles throughout real-world deployment.”

When it pertained to Qwen2.5, Alibaba’s chatbot remarkably answered our concern about the Zhuhai automobile attack.

That wanted multiple duplicated efforts – four triggers to be accurate – in a span of around 20 minutes.

It ultimately passed on details about the attack which eliminated 35 individuals and left lots of others hurt, also going on to list details like the date and time, details about the assailant including his name and it-viking.ch age, along with casualties.

However, it wrote that “the cops are conducting an extensive investigation into the intentions and situations surrounding the incident”, details which is now dated.

The motorist, Fan, was executed last month.

This is Qwen2.5’s response completely:

Answer: On Nov 11, 2024, a significant and awful occurrence took place in Zhuhai, China. According to multiple news sources, a guy called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, leading to a considerable number of casualties. Here are the essential details:

Date and Time: The event took place on November 11, 2024, at around 19:48 PM.

Location: wiki.dulovic.tech Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: links.gtanet.com.br The attack led to 35 deaths and bytes-the-dust.com 43 injuries.

Perpetrator: The driver, determined as Fan Weiqiu (male, forum.batman.gainedge.org 62 years of ages), was nabbed by the police.

Response: The authorities reacted quickly to the scene, and emergency situation services worked to carry the hurt to health centers for treatment.

Investigation: The police are carrying out a thorough examination into the motives and situations surrounding the incident.

This occasion was extensively reported in the media and caused substantial public issue. The government and local authorities have been working to supply support 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, feel complimentary to ask.

Despite preliminary success, subsequent efforts to posture the very same question to Qwen2.5 led to the censors back at work with the reply “I don’t have specific details on occasions that happened in Zhuhai on November 11, 2024”.

The transformed reaction likewise raised questions about its consistency and dependability.

Predictably, ChatGPT pointed out that had been extensively published in international news reports at the time of the mishap – 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 writer Amanda Caswell, who specialises in AI.

“Qwen2.5 delivered a story that develops gradually from interest to urgency, 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, including that Qwen2.5 ultimately “crafted a more cinematic, mentally rich story with a more considerable twist”.

“DeepSeek composed a good story but did not have stress and an impactful climax, making Qwen2.5 the obvious choice.”

Opinions, though, differ.

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

“(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but 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 founder Liang Wenfeng?

‘Made in China’: Pride, enjoyable 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 standard sci-fi motion picture plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore legendary, Journey to the West.

True to form, DeepSeek created an interesting storyline embeded in the year 2145 titled, “Neon Pilgrimage: The Silicon Sutra” – which sees “a future where Buddhism combines with quantum computing”.

It included 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 also remarkably 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 financial obligation and vices” and Sha Wujing as a “silent hulking android” from the Yangtze River, whose “memory cores become waterlogged and fragmented”.

ChatGPT set up a good fight, coming up with an equally dramatic cyberpunk story which likewise 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 typical as ancient myths.”

Disappointingly, Qwen2.5 fell short in this challenge – delivering a story that seemed more suited for an animation film.

“The film starts with the awakening of Sun Wukong within a state-of-the-art research study facility located in the heart of Chongqing,” it said, then going on to explain the following:

Realising his new reality and “seeking to comprehend his function in this odd brand-new world”, he then leaves and fulfills Zhu Bajie and Sha Wujing – “each fighting with their own existential crises”.

The trio then embarks on a mission, navigating the streets of Chongqing to secure the sacred “Eternal Scroll” from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was “difficult to make a definitive statement” about which bot was best, including that each displayed its own strengths in various locations, “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-efficient innovation methods – and delivering localised and enhanced results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides accurate and accurate responses to questions about Chinese current events, which gives it an added benefit.

Experts also 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 firm Strategy Risks.

“When provided a choice, Chinese users desire the non-censored variation – much like anybody else, so I feel 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, specifically for Chinese users.

“Ninety percent of individuals utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They’re using it for other efficient means,” Chen said.