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, wavedream.wiki AFP/Sebastien Bozon)

This audio is created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually long been President Xi and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "strategically crucial" and its foray into the field has 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 promises of real-world service applications, Chen told CNA.

But it was DeepSeek's rise that actually "encouraged" the idea that smaller sized gamers like start-up companies might have functions to play in AI research and advancements, 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 guidelines of tech-geopolitics

The "emphasis on cost advantage" is a distinct function of Chinese AI, Chen states, with lower training and reasoning costs - the costs of utilizing a trained model to draw conclusions from new information.

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

"We could see some AI firms concentrating on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their models and incorporate them with clinical research," Chen included.

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

Chinese AI companies are moving rapidly, experts state, developing on DeepSeek's momentum to come up with their own ingenious and affordable ways to apply generative AI to jobs and develop more advanced items beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's innovative AI chips, remains a crucial 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 ability of Chinese tech companies ... requiring numerous to depend on older or lower-performance alternatives which can slow training and minimize model abilities," she said.

"While some business like DeepSeek, have discovered imaginative ways to enhance or utilize more standard hardware efficiently, obtaining cutting-edge chips still makes a huge difference for training large AI models."

DeepSeek-Nvidia chips: Singapore states it expects business to abide by its laws

US checking out 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 web so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to avoid 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 mathematics, coding, and logic problems instead!"

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

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

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

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

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

"Its strong focus on Chinese-language data may likewise limit its versatility (to carry out) multilingual tasks ... As a fairly new product, DeepSeek likewise hasn't yet been tested as broadly or on the exact same scale as more recognized AI designs which positions extra challenges throughout real-world release."

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

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

It eventually communicated details about the attack which eliminated 35 people and left dozens of others injured, likewise going on to note details like the date and time, details about the assailant including his name and age, along with casualties.

However, it wrote that "the authorities are carrying out a comprehensive examination into the motives and scenarios surrounding the event", details which is now outdated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's reaction in full:

Answer: On Nov 11, 2024, a significant and tragic occurrence happened in Zhuhai, pipewiki.org China. According to multiple news sources, a guy called Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a considerable number of casualties. Here are the essential details:

Date and Time: The occurrence took place on November 11, 2024, at approximately 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 motorist, identified as Fan Weiqiu (male, 62 years of ages), was nabbed by the police.

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

Investigation: The authorities are performing a thorough investigation into the intentions and wiki.myamens.com circumstances surrounding the occurrence.

This event was commonly reported in the media and caused substantial public concern. The government and local authorities have been working to supply assistance to the victims and their households, and to make sure a detailed investigation into the occurrence.

If you need more detailed details or have specific questions about the incident, pediascape.science feel complimentary to ask.

Despite preliminary success, subsequent attempts to posture the exact same concern to Qwen2.5 resulted in 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 action likewise raised questions about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had actually been widely released in international 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 used a story with a more introspective tone and smoother emotional transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that constructs gradually from interest to urgency, keeping the reader engaged. It uses an unexpected and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally abundant story with a more significant twist".

"DeepSeek wrote a great story however did not have stress and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, however, 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 jobs, however we can likewise see that it is refraining from doing as highly as others in creative writing," he told 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 jolts 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 basic sci-fi movie plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek developed 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 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 conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen battle 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 put up an excellent battle, creating an equally significant cyberpunk storyline 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 change emperors and cybernetic implants are as common as ancient myths."

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

"The film starts with the awakening of Sun Wukong within a modern research facility located in the heart of Chongqing," it said, then going on to explain the following:

Realising his new reality and "looking for to understand his function in this odd brand-new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on a mission, navigating the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "difficult to make a definitive statement" about which bot was best, including that each showed its own strengths in various locations, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI models are not simply replicating Western paradigms, however rather developing in cost-efficient innovation techniques - and providing localised and improved results.

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

DeepSeek's sci-fi movie plot demonstrated its innovative flair that produced a more appealing and creative story as compared to Qwen2.5 and ChatGPT's efforts.

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

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

"DeepSeek is at a downside when it pertains to censorship constraints," kept in mind Isaac Stone Fish, creator and CEO of the research study firm Strategy Risks.

"When provided an option, Chinese users desire the non-censored variation - just 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, larsaluarna.se particularly for Chinese users.

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