GitLab

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 lags CHINA'S AI BOOM?

Transforming the country into a tech superpower has actually 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 essential" and its venture 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 removed in 2022 and revealed pledges of real-world service applications, Chen told CNA.

But it was DeepSeek's rise that truly "encouraged" the idea that smaller sized gamers like start-up companies could have functions to play in AI research study and advancements, he adds.

'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 just changed the guidelines of tech-geopolitics

The "focus on cost advantage" is a distinguishing characteristic of AI, Chen states, with lower training and reasoning expenses - the costs of utilizing a trained model to draw conclusions from new information.

2025 might also see the emergence of more Chinese AI designs tackling advanced thinking jobs.

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

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

Chinese AI business are moving quickly, experts state, constructing on DeepSeek's momentum to come up with their own innovative and affordable 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 advanced AI chips, remains a key 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 companies ... forcing many to rely on older or lower-performance alternatives which can slow training and reduce model capabilities," she said.

"While some companies like DeepSeek, have actually discovered imaginative ways to optimize or utilize more standard hardware efficiently, obtaining innovative chips still makes a big difference for training huge AI designs."

DeepSeek-Nvidia chips: Singapore states it expects companies to comply with its laws

US checking out whether DeepSeek utilized restricted AI chips obtained through other nations, 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 deemed delicate 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 disputes or tell you what happened in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are set to stay away from domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about mathematics, coding, and logic problems rather!"

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

The cars and truck attack outside a sports arena in the southern Chinese city was initially heavily censored on Chinese social networks - with authorities just disclosing the death toll a day later on.

DeepSeek failed to point out that an attack had actually taken place, highlighting instead a military air show and other events that had actually occurred in the city like songs' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it might be a mix of factors at play, such as censorship in addition to "a couple of useful constraints".

"DeepSeek counts on a mix of older graphics processing units and has actually restricted access to innovative hardware which can impact how rapidly and thoroughly the model can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data might also restrict its versatility (to perform) multilingual jobs ... As a fairly new product, DeepSeek also hasn't yet been tested as broadly or on the exact same scale as more recognized AI designs which poses additional challenges during real-world release."

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

That sought numerous repeated efforts - four prompts to be exact - in a span of around 20 minutes.

It eventually passed on details about the attack which eliminated 35 individuals and left dozens of others injured, also going on to list 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 carrying out a comprehensive examination into the intentions and situations surrounding the occurrence", details which is now dated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's response in complete:

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

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

Response: The authorities responded quickly to the scene, and emergency services worked to carry the injured to health centers for treatment.

Investigation: The police are performing a thorough investigation into the motives and circumstances surrounding the incident.

This occasion was commonly reported in the media and caused considerable public concern. The federal government and local authorities have actually been working to offer support to the victims and their families, and to make sure a detailed examination into the occurrence.

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

Despite initial success, subsequent attempts to pose the exact same concern to Qwen2.5 led to the censors back at work with the reply "I do not have specific details on occasions that happened in Zhuhai on November 11, 2024".

The transformed response likewise raised questions about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had actually been commonly published in global report at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 provided a story that develops gradually from curiosity to seriousness, keeping the reader engaged. It offers an unanticipated and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more substantial twist".

"DeepSeek wrote a good story however lacked stress and an impactful climax, making Qwen2.5 the obvious option."

Opinions, though, vary.

Chen believes that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to innovative 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 innovative writing," he informed CNA.

Related:

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

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts 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 basic sci-fi film plot embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore epic, Journey to the West.

True to form, DeepSeek came up with an interesting storyline embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It included elaborate settings - smoggy skies "pierced by high-rise buildings", "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 "a sarcastic, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg bar 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 set up an excellent battle, developing an equally significant cyberpunk story which similarly 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 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 movie.

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

Realising his new truth and "looking for to understand his function in this unusual new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".

The trio then embarks on a mission, 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 "hard to make a definitive declaration" about which bot was best, including that each showed its own strengths in various areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI designs are not just reproducing Western paradigms, however rather progressing in economical development techniques - and providing localised and enhanced outcomes.

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

DeepSeek's sci-fi motion picture plot showed its innovative flair that made for a more engaging and creative story as compared to Qwen2.5 and ChatGPT's efforts.

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

Experts also weighed in on their ideas after utilizing DeepSeek and wiki.lafabriquedelalogistique.fr 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 study firm Strategy Risks.

"When provided an option, Chinese users want the non-censored version - simply like anybody else, so I feel 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 much deeper understanding about Xi Jinping or politically sensitive topics. They're utilizing it for other efficient means," Chen said.