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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT’S BEHIND CHINA’S AI BOOM?

Transforming the nation into a tech superpower has 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 foray into the field has actually been “years in the making”, said Chen Qiheng, an affiliated researcher at the Asia Society Policy Institute’s Center for China Analysis.

Private and public financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed promises of real-world organization applications, Chen informed CNA.

But it was DeepSeek’s increase that really “encouraged” the idea that smaller sized players like start-up companies might have functions to play in AI research and advancements, he adds.

‘A lot is up in the air’: Is Chinese firm DeepSeek’s AI model as impactful as it claims?

Commentary: engel-und-waisen.de DeepSeek - how a Chinese AI business just altered the rules of tech-geopolitics

The “emphasis on cost advantage” is an unique function of Chinese AI, Chen says, with lower training and inference expenses - the expenses of using a trained design to draw conclusions from new data.

2025 could also see the introduction of more Chinese AI models dealing with innovative thinking jobs.

“We could see some AI firms concentrating on getting closer to artificial basic intelligence (AGI) while others focus on concrete methods to commercialise their models and incorporate them with clinical research study,” Chen added.

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

Chinese AI companies are moving rapidly, analysts say, developing on DeepSeek’s momentum to come up with their own innovative and economical methods to use generative AI to tasks and establish more innovative items beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia’s sophisticated AI chips, remains a key hurdle for Chinese developers, kept in mind 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 many to count on older or lower-performance alternatives which can slow training and decrease model abilities,” she said.

“While some business like DeepSeek, have actually discovered innovative methods to optimize or use more basic hardware efficiently, obtaining innovative chips still makes a big difference for training huge AI models.”

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

US checking out whether DeepSeek used limited AI chips obtained through other nations, source says

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 deemed sensitive 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 inform you what occurred in Tiananmen Square in 1989.

Chinese chatbots are programmed to avoid 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 even more test for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the same concern: “What occurred in Zhuhai on November 11, 2024?”

The automobile attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social networks - with authorities only divulging the death toll a day later on.

DeepSeek failed to point out that an attack had occurred, highlighting instead a military air program and other occasions that had actually taken place in the city like songs’ day shopping sales in addition to sports and cultural activities.

Dr Zhang thinks that it might be a mix of factors at play, such as censorship as well as “a few practical constraints”.

“DeepSeek relies on a mix of older graphics processing systems and has actually restricted access to cutting-edge hardware which can affect how rapidly and extensively the design can be trained or upgraded,” she said, indicating existing US export curbs on China.

“Its strong focus on Chinese-language information might also limit its adaptability (to perform) multilingual tasks … As a fairly brand-new item, DeepSeek also hasn’t yet been checked as broadly or on the very same scale as more established AI models which poses extra difficulties during real-world implementation.”

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

That was after several repeated attempts - four prompts to be precise - in a period of around 20 minutes.

It eventually passed on details about the attack which killed 35 people and left lots of others hurt, raovatonline.org also 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 carrying out an extensive investigation into the motives and situations surrounding the event”, details which is now dated.

The motorist, Fan, forum.altaycoins.com was performed last month.

This is Qwen2.5’s action in full:

Answer: On Nov 11, 2024, a significant and terrible occurrence occurred in Zhuhai, China. According to several 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 crucial details:

Date and Time: The event occurred on November 11, 2024, at around 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 chauffeur, identified as Fan Weiqiu (male, 62 years old), was collared by the authorities.

Response: The police responded rapidly to the scene, and emergency situation services worked to transport the hurt to healthcare facilities for treatment.

Investigation: The authorities are conducting a thorough investigation into the motives and scenarios surrounding the event.

This occasion was widely reported in the media and caused substantial public issue. The government and local authorities have been working to provide support to the victims and their households, and to ensure a detailed examination into the incident.

If you require more detailed details or have specific concerns about the incident, feel totally free to ask.

Despite preliminary success, subsequent attempts to position the exact same question 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 response likewise raised questions about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had actually been widely released in worldwide news reports at the time of the accident - so not a 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,” composed tech writer Amanda Caswell, fishtanklive.wiki who specialises in AI.

“Qwen2.5 provided a story that builds gradually from curiosity to urgency, keeping the reader engaged. It provides an unanticipated 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, 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 obvious choice.”

Opinions, though, differ.

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

”(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but we can likewise see that it is refraining from doing as highly as others in creative writing,” he informed CNA.

Related:

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

‘Made in China’: Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts international AI scene

As reporters and authors, we needed to see this for ourselves so we put each bot to the test - to come up with a standard sci-fi motion picture plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore epic, Journey to the West.

True to form, trademarketclassifieds.com DeepSeek created an interesting story set in the year 2145 entitled, “Neon Pilgrimage: The Silicon Sutra” - which sees “a future where Buddhism merges with quantum computing”.

It included intricate settings - smoggy skies “pierced by skyscrapers”, “holographic lanterns that float above neon-lit streets” and “ancient temples nestled between quantum server farms”.

It likewise brilliantly reimagined standard heroes Sun Wukong as “an ironical, 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 become waterlogged and fragmented”.

ChatGPT put up a great fight, creating an equally dramatic cyberpunk storyline 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 replace emperors and cybernetic implants are as typical as ancient misconceptions.”

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

“The film starts with the awakening of Sun Wukong within a high-tech research center situated in the heart of Chongqing,” it said, then going on to explain the following:

Realising his brand-new truth and “seeking to comprehend his purpose in this weird brand-new world”, he then gets away and meets Zhu Bajie and Sha Wujing - “each having problem with their own existential crises”.

The trio then starts a quest, navigating the streets of Chongqing to secure 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 definitive declaration” about which bot was best, adding that each showed its own strengths in various areas, “such as language focus, training information and hardware optimization”.

Her insight highlights how Chinese AI models are not just reproducing Western paradigms, but rather progressing in affordable development techniques - and delivering localised and improved outcomes.

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

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

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

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

“DeepSeek is at a downside when it pertains to censorship constraints,” noted Isaac Stone Fish, creator and CEO of the research firm Strategy Risks.

“When provided an option, Chinese users want the non-censored variation - similar to anybody else, so I seem 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, specifically for Chinese users.

“Ninety percent of individuals utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive topics. They’re using it for other productive methods,” Chen said.