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 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 goal and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically important" 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 sped up after ChatGPT took off in 2022 and showed promises of real-world organization applications, Chen told CNA.

But it was DeepSeek's rise that actually "urged" the idea that smaller players like start-up companies might have functions to play in AI research and developments, higgledy-piggledy.xyz he adds.

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

Commentary: wiki.snooze-hotelsoftware.de DeepSeek - how a Chinese AI company just changed the guidelines of tech-geopolitics

The "emphasis on expense advantage" is a distinctive feature of Chinese AI, Chen says, with lower training and inference expenses - the expenses of using a trained model to reason from new information.

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

"We might see some AI companies concentrating on getting closer to artificial basic intelligence (AGI) while others focus on concrete methods to commercialise their designs and incorporate them with clinical research," Chen .

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

Chinese AI business are moving rapidly, experts state, building on DeepSeek's momentum to come up with their own ingenious and affordable ways to use generative AI to tasks and establish advanced products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a crucial difficulty for Chinese developers, noted Dr Marina Zhang, an associate teacher at University of Technology Sydney's (UTS) Australia-China Relations Institute.

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

"While some business like DeepSeek, have found innovative ways to enhance or utilize more basic hardware efficiently, obtaining cutting-edge chips still makes a big distinction for training huge AI models."

DeepSeek-Nvidia chips: Singapore states it expects business to comply with its laws

US checking out whether DeepSeek utilized restricted AI chips obtained through other countries, source says

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

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, topics deemed sensitive by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to avoid domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about mathematics, coding, and reasoning problems rather!"

To even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very same concern: "What occurred 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 only divulging the death toll a day later.

DeepSeek failed to point out that an attack had occurred, highlighting instead a military air program and other events that had actually happened in the city like songs' day shopping sales in addition to sports and cultural activities.

Dr Zhang thinks that it may be a mix of aspects at play, such as censorship as well as "a few practical constraints".

"DeepSeek depends on a mix of older graphics processing systems and has limited access to advanced hardware which can affect how rapidly and extensively the model can be trained or updated," she said, pointing to existing US export curbs on China.

"Its strong focus on Chinese-language data may likewise restrict its flexibility (to bring out) multilingual tasks ... As a fairly brand-new item, DeepSeek likewise hasn't yet been evaluated as broadly or on the same scale as more recognized AI designs which poses extra challenges during real-world release."

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

That sought numerous duplicated attempts - four triggers to be exact - in a period of around 20 minutes.

It eventually relayed details about the attack which killed 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 age, along with casualties.

However, it wrote that "the cops are conducting a comprehensive investigation into the intentions and scenarios surrounding the occurrence", details which is now outdated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's response in complete:

Answer: On Nov 11, 2024, a significant and tragic event happened in Zhuhai, China. According to several news sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a considerable variety of casualties. Here are the essential details:

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

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

Casualties: The attack resulted in 35 deaths and 43 injuries.

Perpetrator: The motorist, determined as Fan Weiqiu (male, 62 years old), was nabbed by the authorities.

Response: The police responded rapidly to the scene, and emergency services worked to transfer the injured to hospitals for treatment.

Investigation: The police are performing an extensive investigation into the motives and situations surrounding the occurrence.

This event was widely reported in the media and triggered considerable public issue. The federal government and local authorities have actually been working to offer assistance to the victims and their families, and to make sure a detailed examination into the event.

If you require more detailed details or have specific questions about the incident, do not hesitate to ask.

Despite initial success, subsequent attempts 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 occasions that happened in Zhuhai on November 11, 2024".

The modified response also raised questions about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had been widely published in global news reports at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have actually 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 psychological shifts for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that develops slowly 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, including that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more significant twist".

"DeepSeek wrote a good story however lacked stress 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 also see that it is refraining from doing as highly as others in creative writing," he informed CNA.

Related:

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

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts international AI scene

As reporters and authors, 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 set in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek came up with 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 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 also brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg club owner "drowning in debt and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT put up an excellent fight, coming up with an equally remarkable 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 guideline, corporations change emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this obstacle - providing a story that seemed more suited for an animation movie.

"The movie starts with the awakening of Sun Wukong within a state-of-the-art research center situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new reality and "looking for to understand his function in this unusual brand-new world", he then leaves and satisfies Zhu Bajie and forum.altaycoins.com Sha Wujing - "each battling 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 under the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not merely duplicating Western paradigms, but rather developing in affordable development approaches - and providing localised and enhanced outcomes.

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

DeepSeek's sci-fi movie plot demonstrated its imaginative flair that made for a more appealing and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate reactions to concerns about Chinese existing occasions, which gives it an added benefit.

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

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

"When offered an option, Chinese users want the non-censored variation - much like 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, especially 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 topics. They're utilizing it for other efficient ways," Chen said.