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 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'S BEHIND CHINA'S AI BOOM?

Transforming the country into a tech superpower has actually 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 "strategically essential" and its venture into the field has 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 sped up after ChatGPT took off in 2022 and revealed guarantees of real-world company applications, Chen informed CNA.

But it was DeepSeek's rise that truly "urged" the idea that smaller gamers like start-up companies could have roles to play in AI research study and developments, 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 benefit" is a distinctive function of Chinese AI, Chen says, with lower training and inference expenses - the costs of using a trained design to draw conclusions from brand-new information.

2025 could also see the emergence of more Chinese AI models taking on advanced thinking tasks.

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

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

Chinese AI business are moving quickly, analysts say, developing on DeepSeek's momentum to come up with their own innovative and affordable ways to apply generative AI to jobs and establish more beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a key difficulty 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 capability of Chinese tech companies ... forcing many to depend on older or lower-performance options which can slow training and lower model abilities," she said.

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

DeepSeek-Nvidia chips: Singapore states it expects business to abide by its laws

US looking into whether DeepSeek used limited 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, subjects considered sensitive by the state are censored on the internet so it should 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 suggest Chinese chatbots are configured 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 reasoning issues instead!"

To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the exact same concern: "What occurred 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 just disclosing the death toll a day later.

DeepSeek failed to mention that an attack had actually happened, highlighting instead a military air program and other occasions that had actually happened in the city like songs' day shopping sales as well as sports and cultural activities.

Dr Zhang thinks that it may be a mix of aspects at play, such as censorship along with "a few useful constraints".

"DeepSeek counts on a mix of older graphics processing units and has limited access to cutting-edge hardware which can affect how quickly and extensively the design can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data may also restrict its flexibility (to carry out) multilingual tasks ... As a fairly brand-new product, DeepSeek likewise hasn't yet been checked as broadly or on the exact same scale as more recognized AI models which poses extra difficulties throughout real-world implementation."

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

That sought several duplicated efforts - four triggers to be accurate - in a span of around 20 minutes.

It ultimately passed on details about the attack which eliminated 35 people and left lots of others hurt, likewise 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 wrote that "the police are conducting a thorough examination into the motives and scenarios surrounding the incident", details which is now dated.

The motorist, Fan, was performed last month.

This is Qwen2.5's action in full:

Answer: surgiteams.com On Nov 11, 2024, a major and awful incident happened in Zhuhai, China. According to multiple news sources, pipewiki.org a man named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a considerable variety of casualties. Here are the crucial details:

Date and Time: The incident happened 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, recognized as Fan Weiqiu (male, 62 years old), was collared by the authorities.

Response: The authorities reacted quickly to the scene, and emergency situation services worked to transfer the hurt to health centers for treatment.

Investigation: The cops are conducting an extensive examination into the motives and scenarios surrounding the occurrence.

This event was widely reported in the media and triggered significant public concern. The government and local authorities have been working to provide assistance to the victims and their households, and to guarantee a detailed investigation into the occurrence.

If you need more detailed details or have particular concerns about the occurrence, feel free to ask.

Despite preliminary success, subsequent efforts to pose the same concern to Qwen2.5 led to 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 dependability.

Predictably, ChatGPT pointed out public details that had actually been widely released in global report at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

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

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

"Qwen2.5 delivered a story that constructs gradually from interest to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally rich story with a more substantial twist".

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

Opinions, though, 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 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 shocks international AI scene

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

True to form, trademarketclassifieds.com DeepSeek developed an engaging storyline set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism combines with quantum computing".

It included sophisticated 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 also brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg bar 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 significant cyberpunk storyline which similarly 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 change emperors and cybernetic implants are as common as ancient myths."

Disappointingly, Qwen2.5 fell short in this challenge - providing a story that appeared more suited for an animation film.

"The motion picture starts with the awakening of Sun Wukong within a modern research study facility located in the heart of Chongqing," it said, then going on to explain the following:

Realising his brand-new truth and "looking for to comprehend his function in this strange new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a quest, browsing the streets of Chongqing to protect the sacred "Eternal Scroll" from falling into the wrong 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 displayed its own strengths in various areas, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI models are not merely duplicating Western paradigms, however rather developing in cost-effective innovation approaches - and providing localised and improved 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 imaginative flair that produced a more interesting and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides accurate and mediawiki.hcah.in factual actions to concerns about Chinese existing events, which offers it an added benefit.

Experts also weighed in on their thoughts after utilizing DeepSeek and other Chinese AI apps.

"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When provided an option, Chinese users desire 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 per cent of individuals utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're using it for other productive ways," Chen said.