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 startup 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 long been President Xi Jinping's goal and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "tactically crucial" 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 wiki.lafabriquedelalogistique.fr China Analysis.

Private and public investments in Chinese AI sped up after ChatGPT removed in 2022 and revealed guarantees of real-world service applications, Chen informed CNA.

But it was DeepSeek's rise that truly "urged" the idea that smaller sized gamers like start-up companies might have roles to play in AI research and developments, he includes.

'A lot is up in the air': Is Chinese firm DeepSeek's AI model as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI company just altered the rules of tech-geopolitics

The "emphasis on cost advantage" is a distinctive function of Chinese AI, Chen says, with lower training and surgiteams.com inference expenses - the expenses of utilizing a trained design to draw conclusions from brand-new information.

2025 could likewise see the development of more Chinese AI designs taking on sophisticated reasoning tasks.

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

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

Chinese AI companies are moving rapidly, experts state, building on DeepSeek's momentum to come up with their own ingenious and pediascape.science affordable ways to apply generative AI to jobs and establish advanced products beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's innovative AI chips, remains an essential hurdle 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) limit the capability of Chinese tech business ... requiring lots of to depend on older or lower-performance alternatives which can slow training and lower model capabilities," she said.

"While some companies like DeepSeek, have actually found imaginative methods to enhance or utilize more standard hardware effectively, obtaining cutting-edge chips still makes a big difference for training large AI models."

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

US checking out whether DeepSeek utilized limited AI chips obtained through other nations, 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 should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are set 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 mathematics, coding, and logic problems rather!"

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

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

DeepSeek failed to discuss that an attack had actually taken place, highlighting instead a military air show and other events that had taken place in the city like singles' day shopping sales in addition to sports and cultural activities.

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

"DeepSeek relies on a mix of older graphics processing systems and has actually limited access to advanced hardware which can impact how rapidly and extensively the model can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong focus on Chinese-language data might also limit its versatility (to perform) multilingual jobs ... As a fairly new item, DeepSeek likewise hasn't yet been checked as broadly or on the same scale as more established AI models which presents extra challenges throughout real-world release."

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

That wanted multiple repeated attempts - 4 triggers to be exact - in a period of around 20 minutes.

It eventually communicated details about the attack which eliminated 35 people 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 authorities are conducting a thorough investigation into the motives and scenarios surrounding the occurrence", details which is now outdated.

The motorist, Fan, was performed last month.

This is Qwen2.5's response in full:

Answer: On Nov 11, 2024, bio.rogstecnologia.com.br a major and awful event happened in Zhuhai, China. According to numerous news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove a car into a crowd at the Zhuhai Sports Center, leading to a significant number of casualties. Here are the key details:

Date and Time: The occurrence occurred 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, as Fan Weiqiu (male, 62 years of ages), was captured by the cops.

Response: The authorities reacted rapidly to the scene, and emergency services worked to transport the hurt to health centers for treatment.

Investigation: The authorities are conducting an extensive investigation into the motives and scenarios surrounding the incident.

This occasion was widely reported in the media and caused significant public concern. The federal government and local authorities have actually been working to offer support to the victims and their households, and to ensure a detailed investigation into the incident.

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

Despite initial success, subsequent attempts to pose the same concern to Qwen2.5 led to 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 response likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had actually been widely released in international news reports 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 "mentally abundant" writing.

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

"Qwen2.5 provided a story that constructs slowly from curiosity to seriousness, keeping the reader engaged. It offers an unanticipated and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, emotionally abundant story with a more considerable twist".

"DeepSeek composed a good story however did not have tension and an impactful climax, making Qwen2.5 the obvious choice."

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 also see that it is refraining from doing as strongly as others in innovative 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 shocks global 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 movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore legendary, Journey to the West.

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

It included sophisticated settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It likewise remarkably reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg nightclub owner "drowning in financial obligation and vices" and Sha Wujing as a "quiet hulking android" from the Yangtze River, whose "memory cores end up being waterlogged and fragmented".

ChatGPT installed a great fight, creating an equally significant cyberpunk story 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 change emperors and cybernetic implants are as common as ancient myths."

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

"The motion picture begins with the awakening of Sun Wukong within a high-tech research study center situated in the heart of Chongqing," it said, then going on to explain the following:

Realising his new truth and "looking for to comprehend his purpose in this strange brand-new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each having problem with their own existential crises".

The trio then starts a mission, navigating the streets of Chongqing to secure the sacred "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "difficult to make a definitive declaration" about which bot was best, adding that each showed its own strengths in different locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not merely duplicating Western paradigms, however rather progressing in economical innovation methods - and providing localised and enhanced outcomes.

In our tests, each bot showcased their own distinct 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 narrative as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, provides accurate and factual actions to questions about Chinese existing occasions, which gives it an included benefit.

Experts likewise weighed in on their ideas after using 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 provided a choice, Chinese users want the non-censored variation - simply like anybody else, so I seem like that's a piece missing out on from it."

Independent Beijing-based specialist 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 trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other efficient methods," Chen said.