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'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 important" and its foray 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 revealed promises of real-world company applications, Chen told CNA.

But it was DeepSeek's rise that truly "urged" the concept that smaller players like start-up companies could have functions to play in AI research study and advancements, he includes.

'A lot is up in the air': Is Chinese firm 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 advantage" is a distinctive function of Chinese AI, Chen says, with lower training and inference costs - the costs of using a trained design to draw conclusions from new information.

2025 might also see the development of more Chinese AI models dealing with advanced reasoning tasks.

"We could see some AI firms concentrating on getting closer to artificial basic intelligence (AGI) while others focus on concrete methods to commercialise their models and integrate them with clinical research study," Chen added.

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

Chinese AI business are moving quickly, analysts say, building on DeepSeek's momentum to come up with their own innovative and affordable methods to use generative AI to jobs and establish more innovative items beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's innovative AI chips, remains an essential obstacle for Chinese developers, noted Dr Marina Zhang, an associate professor at of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the ability of Chinese tech companies ... forcing many to count on older or lower-performance options which can slow training and minimize model capabilities," she said.

"While some business like DeepSeek, have actually discovered innovative ways to optimize or use more fundamental hardware effectively, obtaining advanced chips still makes a big distinction for training large AI designs."

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

US checking out whether DeepSeek utilized restricted 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, topics deemed 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 suggest Chinese chatbots are set to stay away from 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 reasoning problems instead!"

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

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

DeepSeek failed to mention that an attack had actually taken place, highlighting instead a military air program and other events that had taken place in the city like singles' day shopping sales in addition to 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 useful constraints".

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

"Its strong concentrate on Chinese-language information might also limit its adaptability (to carry out) multilingual jobs ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the same scale as more established AI designs which presents extra challenges during real-world release."

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

That was after several duplicated efforts - four triggers to be precise - in a span of around 20 minutes.

It ultimately communicated details about the attack which killed 35 people 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 performing a thorough examination into the intentions and situations surrounding the event", details which is now dated.

The driver, Fan, was executed last month.

This is Qwen2.5's action in full:

Answer: On Nov 11, 2024, a significant and terrible event occurred in Zhuhai, China. According to multiple news sources, a male named 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 variety of casualties. Here are the crucial details:

Date and Time: The event took place on November 11, 2024, classificados.diariodovale.com.br at around 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, recognized as Fan Weiqiu (male, 62 years of ages), was captured by the authorities.

Response: The police reacted quickly to the scene, and emergency services worked to transport the hurt to healthcare facilities for treatment.

Investigation: garagesale.es The cops are carrying out an extensive examination into the intentions and scenarios surrounding the event.

This occasion was widely reported in the media and caused substantial public concern. The federal government and regional authorities have actually been working to provide support to the victims and their households, and to ensure a detailed examination into the event.

If you need more detailed details or have specific questions about the occurrence, feel free to ask.

Despite initial 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 response also raised questions about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had been widely 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 provide structured and even "mentally rich" writing.

"DeepSeek-R1 provided a story with a more introspective tone and smoother emotional shifts for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that constructs slowly from interest to urgency, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, trademarketclassifieds.com including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more significant twist".

"DeepSeek wrote a good story however did not have tension and an impactful climax, making Qwen2.5 the obvious option."

Opinions, however, 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, however we can also see that it is refraining from doing as highly as others in imaginative writing," he informed CNA.

Related:

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

'Made in China': setiathome.berkeley.edu Pride, pleasant surprise from Chinese netizens as DeepSeek jolts global AI scene

As reporters 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 movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, Journey to the West.

True to form, DeepSeek developed an engaging story 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 high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise remarkably reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen fight body", Zhu Bajie as a cyborg nightclub owner "drowning in debt 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 a good battle, creating an equally remarkable cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".

"This is a world where AI deities rule, corporations replace emperors and cybernetic implants are as common as ancient myths."

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

"The motion picture begins with the awakening of Sun Wukong within a high-tech research 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 unusual brand-new world", he then escapes and meets 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 spiritual "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a conclusive 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 models are not merely duplicating Western paradigms, but rather progressing in economical development methods - and delivering localised and improved outcomes.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers precise and accurate responses to concerns about Chinese present events, which gives it an included benefit.

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

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

"When provided a choice, Chinese users want the non-censored variation - simply like anyone else, so I seem like that's a piece missing out on from it."

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

"Ninety per cent of people 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.