How do Chinese aI Bots Stack up Against ChatGPT?

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’S BEHIND CHINA’S AI BOOM?

Transforming the country 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 important” and its foray into the field has been “years in the making”, surgiteams.com 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 accelerated after ChatGPT removed in 2022 and revealed promises of real-world organization applications, Chen informed CNA.

But it was DeepSeek’s increase that actually “encouraged” the concept that smaller sized gamers like start-up firms could have functions to play in AI research study and advancements, he adds.

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

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

The “focus on cost advantage” is an unique function of Chinese AI, Chen states, with lower training and inference costs – the expenses of utilizing a trained design to reason from new data.

2025 might also see the development of more Chinese AI models tackling sophisticated thinking jobs.

“We could see some AI firms focusing on getting closer to synthetic general intelligence (AGI) while others focus on concrete methods to commercialise their designs and integrate them with scientific research study,” Chen included.

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

Chinese AI companies are moving quickly, analysts say, constructing on DeepSeek’s momentum to come up with their own innovative and cost-efficient ways to apply generative AI to tasks and develop more innovative items beyond .

But on the flip side, access to high-end hardware, particularly Nvidia’s sophisticated chips, remains a key hurdle 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 ability of Chinese tech business … forcing many to rely on older or lower-performance alternatives which can slow training and decrease model capabilities,” she said.

“While some business like DeepSeek, have found innovative ways to enhance or use more fundamental hardware effectively, obtaining advanced chips still makes a big distinction for training huge AI models.”

DeepSeek-Nvidia chips: wiki.vst.hs-furtwangen.de Singapore says it anticipates companies to comply with its laws

US looking into 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 considered delicate by the state are censored on the web so it need 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 steer 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 mathematics, coding, and reasoning issues rather!”

To even more test 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 heavily censored on Chinese social media – with authorities just revealing the death toll a day later.

DeepSeek failed to point out that an attack had actually occurred, highlighting instead a military air show and other occasions that had actually occurred in the city like singles’ day shopping sales along with sports and cultural activities.

Dr Zhang thinks that it may be a mix of elements at play, such as censorship along with “a few practical constraints”.

“DeepSeek relies on a mix of older graphics processing systems and has actually limited access to innovative hardware which can impact 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 information may likewise limit its flexibility (to perform) multilingual jobs … As a fairly new product, DeepSeek likewise hasn’t yet been checked as broadly or on the very same scale as more recognized AI designs which presents additional difficulties throughout real-world deployment.”

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

That wanted numerous duplicated efforts – 4 prompts to be precise – in a span of around 20 minutes.

It eventually relayed details about the attack which eliminated 35 individuals and left dozens of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it wrote that “the cops are conducting a thorough investigation into the intentions and scenarios surrounding the incident”, details which is now dated.

The motorist, Fan, was carried out last month.

This is Qwen2.5’s reaction completely:

Answer: On Nov 11, 2024, a major and awful occurrence happened in Zhuhai, China. According to several news sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a significant number of casualties. Here are the essential details:

Date and Time: The incident happened 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 captured by the police.

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

Investigation: The authorities are conducting a thorough investigation into the intentions and circumstances surrounding the occurrence.

This event was widely reported in the media and caused considerable public concern. The federal government and regional authorities have been working to supply assistance to the victims and their households, and to guarantee a detailed examination into the occurrence.

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

Despite preliminary success, subsequent efforts to pose the same question to Qwen2.5 led to the censors back at work with the reply “I do not have particular details on occasions that occurred in Zhuhai on November 11, 2024”.

The transformed action also raised questions about its consistency and dependability.

Predictably, ChatGPT mentioned public details that had been extensively published in global news reports 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 psychological shifts for a well-paced story,” composed tech author Amanda Caswell, who specialises in AI.

“Qwen2.5 delivered a story that constructs slowly from interest to seriousness, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and vivid images for the setting,” she said, adding that Qwen2.5 eventually “crafted a more cinematic, mentally abundant story with a more significant twist”.

“DeepSeek wrote a great story but lacked stress and an impactful climax, making Qwen2.5 the apparent option.”

Opinions, however, 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 likewise see that it is refraining from doing as strongly as others in creative writing,” he told CNA.

Related:

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

‘Made in China’: Pride, pleasant surprise from Chinese netizens as DeepSeek jolts international 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 embeded in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore legendary, Journey to the West.

True to form, DeepSeek created an engaging story embeded in the year 2145 titled, “Neon Pilgrimage: The Silicon Sutra” – which sees “a future where Buddhism combines with quantum computing”.

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

It likewise remarkably reimagined standard heroes Sun Wukong as “a sarcastic, self-aware AI housed in a stolen combat body”, Zhu Bajie as a cyborg club owner “drowning in financial obligation 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 battle, creating a similarly dramatic cyberpunk storyline which likewise reimagined “a ragteam of cyber-enhanced misfits, each matching 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 misconceptions.”

Disappointingly, Qwen2.5 fell short in this obstacle – providing a storyline that seemed more suited for an animation movie.

“The film begins with the awakening of Sun Wukong within a state-of-the-art research study facility situated 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 weird brand-new world”, he then escapes and fulfills Zhu Bajie and Sha Wujing – “each dealing with their own existential crises”.

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

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was “hard to make a conclusive declaration” about which bot was best, including that each displayed its own strengths in different locations, “such as language focus, training data and hardware optimization”.

Her insight underscores how Chinese AI models are not simply replicating Western paradigms, wiki.dulovic.tech however rather evolving in economical innovation methods – and providing localised and enhanced outcomes.

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

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

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

Experts likewise weighed in on their thoughts 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 study company Strategy Risks.

“When offered a choice, Chinese users want the non-censored version – just like anyone 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, specifically for Chinese users.

“Ninety per cent of individuals utilizing the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate subjects. They’re using it for other productive means,” Chen said.