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 created 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 becoming 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 financial investments in Chinese AI sped up after ChatGPT took off in 2022 and revealed guarantees of real-world business applications, Chen informed CNA.

But it was DeepSeek's rise that truly "urged" the idea that smaller players like start-up firms 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 reason from new information.

2025 could also see the introduction of more Chinese AI models tackling advanced reasoning jobs.

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

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

Chinese AI companies are moving rapidly, analysts state, building on DeepSeek's momentum to come up with their own innovative and affordable methods to apply generative AI to jobs and establish advanced products beyond chatbots.

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

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

"While some business like DeepSeek, have actually found creative ways to enhance or use more fundamental hardware effectively, obtaining cutting-edge chips still makes a big difference for training extremely large AI designs."

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

US looking into whether DeepSeek utilized limited 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, subjects deemed sensitive by the state are censored on the internet so it need to come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or forum.altaycoins.com inform you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed to avoid domestic politics.

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

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

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

DeepSeek failed to point out that an attack had actually occurred, highlighting instead a military air program and pediascape.science 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 may be a mix of elements at play, such as censorship in addition to "a couple of practical constraints".

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

"Its strong focus on Chinese-language information might likewise restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more established AI models which presents extra difficulties during real-world release."

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

That wanted multiple repeated efforts - four triggers to be accurate - in a period of around 20 minutes.

It eventually passed on details about the attack which eliminated 35 individuals and left lots of others hurt, likewise going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it wrote that "the authorities are performing a thorough investigation into the motives and situations surrounding the occurrence", details which is now obsoleted.

The motorist, Fan, was performed last month.

This is Qwen2.5's action in complete:

Answer: On Nov 11, 2024, a significant and awful incident took place in Zhuhai, China. According to multiple news sources, a male called Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, resulting in a significant variety of casualties. Here are the essential 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 driver, identified as Fan Weiqiu (male, 62 years of ages), was nabbed by the authorities.

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

Investigation: The cops are conducting an extensive examination into the intentions and scenarios surrounding the incident.

This occasion was widely reported in the media and wavedream.wiki caused significant public issue. The government and regional authorities have been working to provide support to the victims and their families, and to make sure a detailed investigation into the occurrence.

If you require more detailed details or have particular questions about the event, feel totally free to ask.

Despite preliminary success, subsequent attempts to posture the same question to Qwen2.5 resulted in 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 modified response likewise raised concerns about its consistency and dependability.

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

WHICH IS MORE CREATIVE?

Users have praised the capability of Chinese AI apps to deliver structured and even "mentally abundant" 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 constructs slowly from interest to seriousness, 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, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more significant twist".

"DeepSeek composed an excellent story however lacked tension 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 innovative 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 innovative writing," he told CNA.

Related:

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

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

As journalists and writers, we had to see this for ourselves so we put each bot to the test - to come up with a sci-fi film plot embeded in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore impressive, Journey to the West.

True to form, DeepSeek came up with an appealing story set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It consisted of intricate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also remarkably reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg bar 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 set up an excellent battle, developing an equally remarkable cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the famous 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 misconceptions."

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

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

Realising his brand-new reality and "seeking to understand his purpose in this weird brand-new world", he then leaves and fulfills Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to secure the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a definitive declaration" about which bot was best, adding 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 just reproducing Western paradigms, but rather evolving in cost-efficient development approaches - and delivering localised and improved results.

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

DeepSeek's sci-fi film plot demonstrated its creative flair that produced a more appealing and imaginative narrative as compared to Qwen2.5 and engel-und-waisen.de ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and factual responses to questions about Chinese present events, hb9lc.org which offers it an included benefit.

Experts also weighed in on their ideas after using 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 company Strategy Risks.

"When offered an option, Chinese users want the non-censored variation - much like anybody else, so I seem 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 utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other efficient means," Chen said.