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: wiki.dulovic.tech Reuters/Dado Ruvic, AFP/Sebastien Bozon)

This audio is produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags 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 ending up being the world leader in AI by 2030.

China views AI as being "tactically crucial" and its venture into the field has been "years in the making", said Chen Qiheng, an associated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public financial investments in Chinese AI sped up after ChatGPT removed in 2022 and showed pledges of real-world business applications, Chen informed CNA.

But it was DeepSeek's increase that actually "urged" the concept 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': Is Chinese company DeepSeek's AI model as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business simply changed the rules 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 design to draw conclusions from brand-new information.

2025 could likewise see the emergence of more Chinese AI models dealing with innovative thinking jobs.

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

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

Chinese AI business are moving quickly, experts state, developing on DeepSeek's momentum to come up with their own ingenious and cost-effective methods to apply generative AI to tasks and develop more sophisticated products beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a key hurdle 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) limit the capability of Chinese tech companies ... forcing numerous to rely on older or lower-performance options which can slow training and reduce design abilities," she said.

"While some business like DeepSeek, have found innovative methods to enhance or use more standard hardware effectively, obtaining cutting-edge chips still makes a huge difference for training really large AI models."

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

US checking out whether DeepSeek used 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 delicate by the state are censored on the internet so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to guide clear of domestic politics.

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

To even more check for accuracy 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 stadium in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities only disclosing the death toll a day later on.

DeepSeek failed to mention that an attack had actually taken location, highlighting rather a military air show and other occasions that had actually taken place in the city like singles' day shopping sales along with sports and cultural activities.

Dr Zhang thinks that it may be a mix of factors at play, such as censorship in addition to "a few practical constraints".

"DeepSeek counts on a mix of older graphics processing units and has actually limited access to advanced hardware which can impact how quickly and thoroughly 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 adaptability (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek likewise hasn't yet been evaluated as broadly or on the same scale as more established AI designs which positions extra challenges throughout real-world implementation."

When it pertained to Qwen2.5, remarkably addressed our question about the Zhuhai vehicle attack.

That sought multiple duplicated efforts - four triggers to be accurate - in a span of around 20 minutes.

It ultimately relayed details about the attack which killed 35 people and left lots of others hurt, also 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 composed that "the cops are performing a comprehensive examination into the intentions and situations surrounding the event", details which is now outdated.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's action in full:

Answer: On Nov 11, 2024, a significant and terrible occurrence happened in Zhuhai, China. According to multiple news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the key details:

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

Response: The police responded quickly to the scene, and emergency situation services worked to transport the hurt to health centers for treatment.

Investigation: The cops are carrying out a thorough investigation into the intentions and situations surrounding the event.

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

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

Despite initial success, subsequent efforts to pose the same concern to Qwen2.5 resulted in 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 action also raised questions about its consistency and dependability.

Predictably, ChatGPT cited public details that had actually been extensively released in worldwide report at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that constructs gradually from interest to seriousness, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more significant twist".

"DeepSeek composed an excellent story however lacked stress and an impactful climax, making Qwen2.5 the obvious choice."

Opinions, however, differ.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to innovative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can likewise see that it is refraining from doing as strongly as others in innovative writing," he told CNA.

Related:

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

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

As journalists and authors, we needed 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 impressive, Journey to the West.

True to form, DeepSeek created an engaging storyline set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It included 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 likewise remarkably reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen combat 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 a good battle, developing a similarly dramatic 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 replace emperors and cybernetic implants are as typical as ancient misconceptions."

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

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

Realising his brand-new reality and "seeking to comprehend his purpose in this odd brand-new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to safeguard the sacred "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "tough to make a conclusive statement" 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 underscores how Chinese AI designs are not simply reproducing Western paradigms, however rather evolving in cost-efficient development techniques - and delivering localised and enhanced results.

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

DeepSeek's sci-fi movie plot showed 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, offers accurate and factual actions to questions about Chinese current occasions, which gives it an added advantage.

Experts also weighed in on their thoughts 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 firm Strategy Risks.

"When given a choice, Chinese users desire the non-censored variation - just like anyone else, so I seem like that's a piece missing 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 individuals utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other efficient ways," Chen said.