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 created by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the nation into a tech superpower has actually long been President Xi Jinping's objective and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically essential" and its venture into the field has actually 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 removed in 2022 and showed pledges of real-world organization applications, Chen told CNA.

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

'A lot is up in the air': Is Chinese company DeepSeek's AI design 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 utilizing a trained design to draw conclusions from new data.

2025 might also see the emergence of more Chinese AI designs dealing with advanced reasoning tasks.

"We might see some AI firms focusing on getting closer to synthetic basic intelligence (AGI) while others focus on concrete methods to commercialise their designs and integrate them with clinical research study," Chen included.

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

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

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

"US export controls (still) limit the capability of Chinese tech companies ... requiring lots of to count on older or lower-performance alternatives which can slow training and decrease design abilities," she said.

"While some companies like DeepSeek, have found imaginative ways to enhance or use more standard hardware effectively, obtaining advanced chips still makes a huge difference for training very big AI models."

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

US looking into whether DeepSeek utilized restricted AI chips obtained through other countries, 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 sensitive by the state are censored on the internet so it need 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 suggest Chinese chatbots are configured to stay away from .

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 logic problems rather!"

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

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

DeepSeek failed to discuss that an attack had actually taken place, highlighting rather a military air program and other occasions that had actually happened in the city like singles' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it may be a mix of factors at play, such as censorship as well as "a couple of useful constraints".

"DeepSeek relies on a mix of older graphics processing units and has limited access to innovative hardware which can affect how quickly and extensively the model can be trained or upgraded," she said, indicating existing US export curbs on China.

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

When it pertained to Qwen2.5, Alibaba's chatbot remarkably answered our concern about the Zhuhai cars and truck attack.

That wanted several duplicated efforts - four prompts to be exact - in a span of around 20 minutes.

It eventually communicated details about the attack which killed 35 individuals and left dozens of others hurt, likewise 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 an extensive investigation into the motives and situations surrounding the event", details which is now outdated.

The driver, Fan, was carried out last month.

This is Qwen2.5's reaction in complete:

Answer: On Nov 11, 2024, a significant and awful event occurred in Zhuhai, China. According to numerous news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a substantial variety of casualties. Here are the essential details:

Date and Time: The event took place 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 motorist, identified as Fan Weiqiu (male, 62 years of ages), was nabbed by the cops.

Response: The cops reacted rapidly to the scene, and emergency services worked to carry the injured to medical facilities for treatment.

Investigation: The cops are performing an extensive examination into the motives and situations surrounding the incident.

This event was widely reported in the media and caused substantial public concern. The government and regional authorities have actually been working to offer assistance to the victims and their families, and to make sure a detailed investigation into the event.

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

Despite initial success, subsequent attempts to posture the same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that occurred in Zhuhai on November 11, 2024".

The transformed reaction also raised questions about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had actually been widely released in global 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 "emotionally abundant" writing.

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

"Qwen2.5 delivered a story that develops slowly from curiosity to urgency, keeping the reader engaged. It offers an unforeseen and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more substantial twist".

"DeepSeek wrote an excellent story but lacked tension and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, however, vary.

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 jobs, however we can also see that it is refraining from doing as strongly as others in innovative writing," he told CNA.

Related:

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

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

As journalists and authors, we had to see this for ourselves so we put each bot to the test - to come up with a fundamental sci-fi motion picture plot embeded 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 story embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It included elaborate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also remarkably reimagined traditional 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 "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up an excellent fight, creating a similarly remarkable cyberpunk storyline which similarly 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 common as ancient misconceptions."

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

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

Realising his brand-new truth and "looking for to comprehend his function in this odd brand-new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

The trio then starts a quest, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a definitive declaration" about which bot was best, including that each displayed its own strengths in various locations, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI designs are not merely replicating Western paradigms, however rather evolving in cost-effective development methods - and delivering localised and improved results.

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

DeepSeek's sci-fi film plot showed its innovative flair that produced a more interesting and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, ratemywifey.com the more established ChatGPT, unburdened by Chinese censorship constraints, provides accurate and factual actions to concerns about Chinese current events, which offers it an added benefit.

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

"DeepSeek is at a disadvantage when it pertains to censorship constraints," noted Isaac Stone Fish, founder and CEO of the research firm Strategy Risks.

"When provided 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 consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, especially for Chinese users.

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