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 start-up 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 China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "tactically important" and its foray into the field has actually 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 investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed pledges of real-world service applications, Chen informed CNA.

But it was DeepSeek's increase that really "urged" the concept that smaller sized players like start-up firms might 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 company 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 reasoning expenses - the expenses of using a trained design to draw conclusions from brand-new data.

2025 could likewise see the development of more Chinese AI designs tackling sophisticated reasoning jobs.

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

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

Chinese AI companies are moving quickly, analysts state, building on DeepSeek's momentum to come up with their own innovative and affordable ways to use generative AI to jobs and develop more innovative items beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's advanced AI chips, remains an essential obstacle 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) restrict the capability of Chinese tech business ... forcing numerous to depend on older or lower-performance options which can slow training and decrease design abilities," she said.

"While some companies like DeepSeek, have actually discovered creative methods to optimize or utilize more basic hardware effectively, obtaining innovative chips still makes a huge difference for training large AI designs."

DeepSeek-Nvidia chips: Singapore says it anticipates business to comply with its laws

US checking out whether DeepSeek utilized 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 delicate by the state are censored on the internet so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what occurred in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are configured 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 logic issues rather!"

To further evaluate for accuracy and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What happened in Zhuhai on November 11, 2024?"

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

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

Dr Zhang believes that it may be a mix of elements at play, such as censorship as well as "a few practical constraints".

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

"Its strong focus on Chinese-language data might also restrict its versatility (to carry out) multilingual tasks ... As a fairly new product, DeepSeek also hasn't yet been checked as broadly or on the same scale as more established AI designs which postures additional obstacles during real-world release."

When it pertained to Qwen2.5, Alibaba's chatbot surprisingly addressed our concern about the Zhuhai automobile attack.

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

It eventually relayed details about the attack which killed 35 individuals and left lots of others injured, likewise going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it composed that "the cops are conducting a comprehensive examination into the motives and situations surrounding the incident", details which is now outdated.

The motorist, Fan, was carried out last month.

This is Qwen2.5's response in complete:

Answer: On Nov 11, 2024, a significant and awful incident happened in Zhuhai, China. According to several 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, leading to a considerable number of casualties. Here are the crucial 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 chauffeur, determined as Fan Weiqiu (male, 62 years of ages), was collared by the police.

Response: The authorities reacted rapidly to the scene, and emergency situation services worked to transfer the hurt to hospitals for treatment.

Investigation: The police are carrying out an extensive examination into the motives and circumstances surrounding the occurrence.

This event was extensively reported in the media and triggered considerable public issue. The government and regional authorities have actually been working to provide support to the victims and their households, and to ensure a detailed examination into the incident.

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

Despite preliminary success, subsequent efforts to present the exact same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on events that occurred in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had been widely released in global news reports at the time of the mishap - so no 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 provided a story with a more reflective tone and smoother emotional shifts for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that builds gradually from curiosity to seriousness, keeping the reader engaged. It provides an unforeseen 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, mentally rich story with a more substantial twist".

"DeepSeek wrote a good story however lacked tension and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, however, differ.

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

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

Related:

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

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek jolts worldwide 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, including main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek came up with an interesting storyline embeded 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 skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also remarkably reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken 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 an excellent battle, creating an equally significant 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 replace emperors and cybernetic implants are as common as ancient myths."

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

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

Realising his brand-new truth and "looking for to understand his purpose in this weird new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each having a hard time with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a conclusive declaration" about which bot was best, including that each displayed its own strengths in various areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI designs are not simply duplicating Western paradigms, however rather developing in cost-efficient development techniques - and delivering localised and enhanced outcomes.

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

DeepSeek's sci-fi movie plot showed its innovative flair that produced a more interesting and creative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, gratisafhalen.be provides precise and accurate actions to questions about Chinese existing occasions, which offers it an included advantage.

Experts also weighed in on their ideas after utilizing 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 company Strategy Risks.

"When offered an option, Chinese users desire the non-censored version - much like anyone else, so I seem like that's a piece missing 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 people using the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other efficient ways," Chen said.