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: 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 country into a tech superpower has long been President Xi Jinping's objective and wavedream.wiki China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically crucial" 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 sped up after ChatGPT took off in 2022 and revealed pledges of real-world service applications, Chen told CNA.

But it was DeepSeek's increase that really "urged" the idea that smaller sized 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 design as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI business simply altered the rules of tech-geopolitics

The "focus on expense benefit" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and inference costs - the costs of utilizing a trained design to reason from new information.

2025 might also see the introduction of more Chinese AI designs dealing with sophisticated thinking jobs.

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

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

Chinese AI business are moving rapidly, experts say, constructing on DeepSeek's momentum to come up with their own innovative and affordable ways to use generative AI to jobs and establish more innovative products beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains an essential hurdle 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) restrict the ability of Chinese tech business ... requiring numerous to rely on older or lower-performance options which can slow training and reduce design abilities," she said.

"While some companies like DeepSeek, have found innovative ways to optimize or use more fundamental hardware efficiently, obtaining advanced chips still makes a huge difference for training extremely big AI models."

DeepSeek-Nvidia chips: Singapore says it anticipates companies to abide by its laws

US checking out 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, subjects considered delicate by the state are censored on the web so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed to guide clear of 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 math, coding, and logic issues rather!"

To further evaluate for accuracy 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 media - with authorities only disclosing the death toll a day later.

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

"DeepSeek depends on a mix of older graphics processing units and has actually restricted access to advanced hardware which can affect how rapidly and thoroughly 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 also restrict its versatility (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been tested as broadly or on the very same scale as more established AI models which positions additional challenges throughout real-world deployment."

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

That wanted multiple duplicated attempts - four prompts to be exact - in a period of around 20 minutes.

It ultimately relayed details about the attack which eliminated 35 individuals and left lots of others injured, likewise going on to note details like the date and time, about the assailant including his name and age, in addition to casualties.

However, it wrote that "the police are performing a thorough investigation into the intentions and situations surrounding the incident", details which is now dated.

The driver, Fan, was carried out last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and terrible occurrence happened in Zhuhai, China. According to multiple news sources, a male called 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 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 driver, identified as Fan Weiqiu (male, 62 years old), was collared by the police.

Response: The cops reacted quickly to the scene, and emergency services worked to carry the hurt to hospitals for systemcheck-wiki.de treatment.

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

This occasion was extensively reported in the media and triggered significant public concern. The federal government and regional authorities have actually been working to supply support to the victims and their families, and to ensure a detailed examination into the event.

If you require more detailed details or have particular concerns about the event, do not hesitate to ask.

Despite initial success, subsequent efforts to posture the very same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on events that occurred in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had been commonly published in worldwide report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that constructs gradually from interest to seriousness, keeping the reader engaged. It offers an unexpected and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, emotionally rich story with a more considerable twist".

"DeepSeek composed a good story but did not have tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, though, vary.

Chen believes that Qwen2.5 does not carry out as strongly as DeepSeek and ChatGPT when it pertains to creative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can also see that it is refraining from doing as highly as others in creative writing," he informed 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 worldwide 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 movie plot set in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore legendary, Journey to the West.

True to form, DeepSeek came up with 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 consisted of fancy settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It also brilliantly reimagined standard heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen battle body", Zhu Bajie as a cyborg club 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 great fight, creating a similarly significant cyberpunk story 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 rule, corporations change emperors and cybernetic implants are as common as ancient myths."

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

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

Realising his new reality and "seeking to comprehend his function in this weird brand-new world", he then leaves and satisfies Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then embarks on a mission, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not merely duplicating Western paradigms, but rather evolving in cost-effective development approaches - and delivering localised and enhanced results.

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

DeepSeek's sci-fi film plot showed its imaginative flair that produced a more appealing and imaginative story as compared to Qwen2.5 and systemcheck-wiki.de ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, offers accurate and factual reactions to concerns about Chinese present occasions, which provides it an included benefit.

Experts also weighed in on their ideas after utilizing 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 provided a choice, Chinese users desire the non-censored version - similar to anyone else, so I feel like that's a piece missing out on from it."

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

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