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 lags 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 "tactically 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 sped up after ChatGPT removed in 2022 and showed promises of real-world organization applications, Chen informed CNA.

But it was DeepSeek's rise that actually "encouraged" the idea that smaller gamers like start-up companies might have functions to play in AI research and developments, he includes.

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

Commentary: forum.batman.gainedge.org DeepSeek - how a Chinese AI company just changed the rules of tech-geopolitics

The "emphasis on cost benefit" is a distinctive function of Chinese AI, Chen says, with lower training and inference expenses - the expenses of utilizing a trained model to draw conclusions from brand-new data.

2025 could also see the emergence of more Chinese AI models taking on advanced reasoning tasks.

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

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

Chinese AI companies are moving rapidly, experts state, constructing on DeepSeek's momentum to come up with their own ingenious and economical ways to use generative AI to jobs and develop advanced products beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a key obstacle 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) restrict the capability of Chinese tech business ... requiring numerous to rely on older or lower-performance options which can slow training and minimize model capabilities," she said.

"While some business like DeepSeek, have discovered imaginative ways to optimize or utilize more standard hardware efficiently, obtaining advanced chips still makes a big difference for training large AI models."

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

US checking out whether DeepSeek used restricted AI chips obtained through other nations, source states

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 delicate by the state are censored on the web so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured 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 question yet. Let's chat about mathematics, coding, and logic problems rather!"

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

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

DeepSeek failed to point out that an attack had happened, highlighting instead a military air show and other events that had actually taken place in the city like songs' day shopping sales as well as 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 useful constraints".

"DeepSeek relies on a mix of older graphics processing units and has actually restricted access to innovative 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 concentrate on Chinese-language information might likewise restrict its versatility (to carry out) multilingual tasks ... As a fairly new product, DeepSeek also hasn't yet been checked as broadly or on the same scale as more recognized AI models which postures additional difficulties during real-world release."

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

That was after several duplicated efforts - 4 triggers to be precise - in a period of around 20 minutes.

It eventually relayed details about the attack which killed 35 individuals and left lots of others injured, likewise going on to note 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 performing a thorough examination into the motives and situations surrounding the incident", details which is now obsoleted.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a major engel-und-waisen.de and terrible event occurred in Zhuhai, archmageriseswiki.com China. According to numerous news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the crucial details:

Date and Time: The occurrence took place on November 11, 2024, at roughly 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, recognized as Fan Weiqiu (male, 62 years of ages), was collared by the authorities.

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

Investigation: The police are performing an extensive examination into the intentions and circumstances surrounding the incident.

This event was widely reported in the media and caused significant public concern. The government and local authorities have actually been working to supply support to the victims and their families, and to guarantee a detailed investigation into the occurrence.

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

Despite initial success, subsequent efforts to position the same concern to Qwen2.5 led to the censors back at work with the reply "I do not have specific details on occasions that took place in Zhuhai on November 11, 2024".

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

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

WHICH IS MORE CREATIVE?

Users have praised the ability of Chinese AI apps to provide structured and even "emotionally rich" writing.

"DeepSeek-R1 used a story with a more reflective tone and smoother emotional transitions for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that develops slowly from curiosity to seriousness, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more significant twist".

"DeepSeek composed a great story however did not have tension and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, though, 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 tasks, however we can also see that it is refraining from doing as strongly as others in creative writing," he informed CNA.

Related:

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

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks international 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 set in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore epic, Journey to the West.

True to form, DeepSeek developed an engaging storyline set 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 between quantum server farms".

It also brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight 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 become waterlogged and fragmented".

ChatGPT set up a great battle, coming up with a similarly dramatic 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 change emperors and cybernetic implants are as common as ancient myths."

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

"The motion picture 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 brand-new reality and "seeking to understand his purpose in this odd brand-new world", he then escapes and meets Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then starts a mission, browsing the streets of Chongqing to safeguard 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 conclusive statement" 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 highlights how Chinese AI designs are not simply duplicating Western paradigms, however rather developing in economical innovation approaches - and providing localised and improved results.

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

DeepSeek's sci-fi motion picture plot showed its imaginative flair that made for a more engaging and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual reactions to questions about Chinese current occasions, which gives it an included benefit.

Experts also weighed in on their ideas after using 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 given a choice, Chinese users want the non-censored version - similar to 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, specifically for Chinese users.

"Ninety percent of people using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other efficient methods," Chen said.