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 generated by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

Transforming the nation into a tech superpower has long been President Xi Jinping's objective and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "tactically crucial" 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 investments in Chinese AI sped up after ChatGPT removed in 2022 and revealed pledges of real-world company applications, Chen informed CNA.

But it was DeepSeek's increase that actually "encouraged" the idea that smaller sized gamers like start-up firms might have functions to play in AI research 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 company simply changed the guidelines of tech-geopolitics

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

2025 could likewise see the development of more Chinese AI models tackling innovative reasoning jobs.

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

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

Chinese AI companies are moving quickly, experts say, wiki.snooze-hotelsoftware.de developing on DeepSeek's momentum to come up with their own innovative and cost-effective methods to apply generative AI to jobs and establish advanced products beyond chatbots.

But on the other hand, access to high-end hardware, particularly Nvidia's sophisticated AI chips, remains a crucial hurdle for Chinese designers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) restrict the capability of Chinese tech business ... requiring numerous to count on older or lower-performance options which can slow training and minimize design capabilities," she said.

"While some business like DeepSeek, have discovered innovative methods to enhance or utilize more basic hardware effectively, obtaining innovative chips still makes a big difference for training extremely big AI designs."

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

US looking into 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 considered delicate by the state are censored on the internet so it ought to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what took place in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed 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 logic problems rather!"

To further test for precision and self-censorship, we asked DeepSeek-R1, archmageriseswiki.com Qwen2.5 and ChatGPT the very same question: "What took place in Zhuhai on November 11, 2024?"

The cars and truck attack outside a sports stadium 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 mention that an attack had actually happened, highlighting rather a military air program and other events that had actually occurred in the city like songs' day shopping sales along with sports and cultural activities.

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

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

"Its strong concentrate on Chinese-language information may also restrict its versatility (to carry out) multilingual tasks ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the exact same scale as more established AI models which poses extra challenges throughout real-world release."

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

That was after several repeated attempts - 4 prompts to be accurate - in a period of around 20 minutes.

It ultimately passed on details about the attack which killed 35 people and hb9lc.org 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 composed that "the cops are performing an extensive examination into the intentions and situations surrounding the event", details which is now obsoleted.

The motorist, Fan, was executed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a major and terrible incident occurred in Zhuhai, China. According to multiple news sources, a guy named Fan Weiqiu (樊某, male, 62 years old) drove a car into a crowd at the Zhuhai Sports Center, leading to a substantial variety 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 resulted in 35 deaths and pediascape.science 43 injuries.

Perpetrator: The chauffeur, identified as Fan Weiqiu (male, 62 years of ages), was collared by the cops.

Response: The police responded quickly to the scene, and emergency services worked to transfer the hurt to medical facilities for treatment.

Investigation: The cops are conducting a comprehensive investigation into the intentions and circumstances surrounding the event.

This event was commonly reported in the media and triggered considerable public concern. The government and regional authorities have actually been working to offer support to the victims and their households, and to make sure a detailed examination into the occurrence.

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

Despite preliminary success, subsequent attempts to posture the same question to Qwen2.5 led to the censors back at work with the reply "I don't have particular details on events that took place in Zhuhai on November 11, 2024".

The modified action also raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had been extensively published in international report at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the ability of Chinese AI apps to provide structured and even "mentally abundant" writing.

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

"Qwen2.5 provided a story that develops slowly from interest to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and brilliant images for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more significant twist".

"DeepSeek composed a great story but did not have stress and an impactful climax, making Qwen2.5 the evident choice."

Opinions, however, differ.

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

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

Related:

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

'Made in China': Pride, bytes-the-dust.com enjoyable surprise from Chinese netizens as DeepSeek shocks global 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 film plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore epic, Journey to the West.

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

It consisted of elaborate settings - smoggy skies "pierced by skyscrapers", "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 stolen combat body", Zhu Bajie as a cyborg nightclub 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 a great battle, coming up with a similarly dramatic 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 guideline, corporations replace emperors and cybernetic implants are as common as ancient myths."

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

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

Realising his new truth and "seeking to understand his purpose in this odd brand-new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then starts a mission, browsing the streets of to safeguard the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "challenging to make a conclusive statement" about which bot was best, including that each displayed its own strengths in different locations, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI designs are not simply reproducing Western paradigms, however rather evolving in cost-effective development approaches - and delivering localised and improved outcomes.

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

DeepSeek's sci-fi film plot demonstrated its imaginative 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, supplies precise and factual responses to questions about Chinese present events, which offers it an added benefit.

Experts likewise weighed in on their thoughts 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 provided a choice, Chinese users desire the non-censored variation - similar to 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, particularly for Chinese users.

"Ninety percent of people utilizing the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate subjects. They're utilizing it for other productive means," Chen said.