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

China views AI as being "strategically essential" 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 pledges of real-world service applications, Chen informed CNA.

But it was DeepSeek's rise that actually "encouraged" the concept that smaller sized players like start-up companies could have roles to play in AI research and advancements, he includes.

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

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

The "emphasis on cost advantage" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning costs - the expenses of using a trained model to draw conclusions from brand-new information.

2025 might also see the development of more Chinese AI designs dealing with innovative thinking jobs.

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

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

Chinese AI companies are moving rapidly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to use generative AI to tasks and develop advanced items beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a crucial difficulty for Chinese developers, kept in mind 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 numerous to depend on older or lower-performance alternatives which can slow training and minimize model capabilities," she said.

"While some companies like DeepSeek, have actually found innovative ways to enhance or use more basic hardware effectively, obtaining innovative chips still makes a huge distinction for training large AI designs."

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

US checking out whether DeepSeek used limited AI chips obtained through other countries, source states

So how do Chinese AI bots compare against ChatGPT? We put them to the test.

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, subjects deemed delicate by the state are censored on the web so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what took place 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 concern yet. Let's chat about math, coding, and reasoning problems rather!"

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

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

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

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

"DeepSeek counts on a mix of older graphics processing units and has actually restricted access to cutting-edge hardware which can impact how rapidly and thoroughly the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data may also limit its flexibility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the same scale as more recognized AI designs which postures extra challenges during real-world deployment."

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

That sought numerous repeated efforts - four prompts to be precise - in a span of around 20 minutes.

It ultimately communicated details about the attack which killed 35 individuals and left dozens of others injured, setiathome.berkeley.edu also going on to list details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it wrote that "the authorities are conducting an extensive investigation into the motives and circumstances surrounding the incident", 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 awful occurrence occurred in Zhuhai, China. According to multiple news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a considerable number of casualties. Here are the key details:

Date and Time: The incident occurred 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 chauffeur, determined as Fan Weiqiu (male, 62 years of ages), was collared by the police.

Response: The cops reacted rapidly to the scene, and emergency services worked to transfer the injured to health centers for treatment.

Investigation: The police are conducting a comprehensive investigation into the intentions and circumstances surrounding the incident.

This occasion was extensively reported in the media and caused substantial public issue. The government and regional authorities have actually been working to supply support to the victims and their households, and to guarantee a detailed examination into the occurrence.

If you require more detailed details or have particular concerns about the event, feel complimentary to ask.

Despite preliminary success, subsequent attempts to present the very same concern to Qwen2.5 led to 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 response also raised questions about its consistency and .

Predictably, ChatGPT pointed out public details that had been commonly published in worldwide 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 transitions for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that builds slowly from curiosity to seriousness, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more considerable twist".

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

Opinions, though, vary.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can also see that it is refraining from doing as strongly 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': higgledy-piggledy.xyz Pride, gratisafhalen.be enjoyable surprise from Chinese netizens as DeepSeek jolts global AI scene

As journalists 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 classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek created an interesting storyline embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges 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 remarkably reimagined standard 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 set up an excellent battle, developing a similarly dramatic cyberpunk story 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 guideline, corporations replace emperors and cybernetic implants are as common as ancient myths."

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

"The motion picture begins with the awakening of Sun Wukong within a modern research study 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 understand his function in this weird new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to protect the sacred "Eternal Scroll" from falling under the incorrect 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 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 merely reproducing Western paradigms, raovatonline.org however rather evolving in affordable innovation techniques - and delivering 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 showed its imaginative flair that produced a more appealing and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual actions to concerns about Chinese present events, which offers 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," kept in mind Isaac Stone Fish, creator and CEO of the research study firm Strategy Risks.

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

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

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