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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the nation 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 important" and its venture 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 financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed promises of real-world service applications, Chen told CNA.

But it was DeepSeek's rise that actually "encouraged" the idea that smaller sized players like start-up firms could have roles to play in AI research and developments, 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 altered the guidelines of tech-geopolitics

The "emphasis on expense advantage" is a distinguishing characteristic of Chinese AI, Chen says, with lower training and reasoning costs - the expenses of utilizing a trained design to reason from brand-new data.

2025 might also see the development of more Chinese AI models taking on innovative reasoning tasks.

"We could see some AI firms focusing on getting closer to artificial general intelligence (AGI) while others focus on concrete methods to commercialise their designs and integrate them with clinical research study," Chen added.

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

Chinese AI companies are moving rapidly, analysts say, developing on DeepSeek's momentum to come up with their own ingenious and cost-efficient ways to use generative AI to jobs and trademarketclassifieds.com establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's innovative AI chips, remains a crucial obstacle 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) limit the capability of Chinese tech companies ... requiring numerous to depend on older or lower-performance options which can slow training and lower design abilities," she said.

"While some business like DeepSeek, have discovered imaginative methods to enhance or use more basic hardware efficiently, obtaining advanced chips still makes a huge distinction for training huge AI models."

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

US checking out whether DeepSeek utilized limited AI chips obtained through other countries, source states

So how do Chinese AI bots compare against ChatGPT? We put them to the test.

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, subjects deemed sensitive by the state are censored on the internet so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what happened in Tiananmen Square in 1989.

Tests recommend 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 concern yet. Let's chat about math, coding, and reasoning issues rather!"

To further check 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 automobile attack outside a sports stadium in the southern Chinese city was at first 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 taken place, 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 may be a mix of aspects at play, such as censorship as well as "a few practical constraints".

"DeepSeek counts on a mix of older graphics processing units and has restricted access to advanced 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 might also restrict its adaptability (to perform) multilingual tasks ... As a fairly brand-new item, DeepSeek also hasn't yet been evaluated as broadly or on the very same scale as more established AI designs which presents extra obstacles during real-world implementation."

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

That was after several duplicated efforts - 4 prompts to be exact - in a span of around 20 minutes.

It ultimately 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, wiki.dulovic.tech it composed that "the police are carrying out a thorough examination into the intentions and circumstances surrounding the incident", details which is now dated.

The driver, Fan, was executed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, yewiki.org 2024, a significant and terrible occurrence happened in Zhuhai, China. According to several news sources, a man called Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a significant variety of casualties. Here are the key details:

Date and Time: The incident happened on November 11, 2024, at roughly 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 driver, identified as Fan Weiqiu (male, 62 years of ages), was captured by the authorities.

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

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

This occasion was commonly reported in the media and triggered significant public concern. The government and local authorities have been working to provide support to the victims and their families, and to guarantee 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 preliminary success, subsequent attempts to pose the same question 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 modified action likewise raised questions about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had actually been extensively published in international report at the time of the accident - so no 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 provided a story with a more introspective tone and smoother emotional transitions for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that constructs slowly from interest to urgency, keeping the reader engaged. It provides an unexpected and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, adding that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more significant twist".

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

Opinions, however, differ.

Chen thinks that Qwen2.5 does not perform as highly as DeepSeek and ChatGPT when it pertains to imaginative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, however we can also see that it is refraining from doing as highly as others in creative writing," he told 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 worldwide AI scene

As reporters and writers, 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 embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek created an engaging storyline set in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It consisted of elaborate settings - smoggy skies "pierced by high-rise buildings", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also remarkably reimagined conventional 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 "quiet hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT put up a great battle, coming up with a similarly remarkable cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities guideline, corporations replace emperors and cybernetic implants are as typical as ancient misconceptions."

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

"The movie starts with the awakening of Sun Wukong within a high-tech research center located in the heart of Chongqing," it said, setiathome.berkeley.edu then going on to explain the following:

Realising his new reality and "seeking to comprehend his purpose in this odd new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to protect the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "difficult 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 data and hardware optimization".

Her insight underscores how Chinese AI models are not just reproducing Western paradigms, however rather developing in cost-effective innovation methods - and delivering localised and improved results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual actions to questions about Chinese current occasions, which provides it an included advantage.

Experts likewise weighed in on their thoughts after using DeepSeek and 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 offered a choice, Chinese users desire the non-censored variation - much like anybody else, so I seem like that's a piece missing from it."

Independent Beijing-based specialist 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 using the tool are not trying to get a much deeper understanding about Xi Jinping or politically delicate topics. They're utilizing it for other productive ways," Chen said.