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 video 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 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 crucial" and its foray into the field has actually 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 investments in Chinese AI sped up after ChatGPT took off in 2022 and showed promises of real-world organization applications, Chen told CNA.

But it was DeepSeek's rise that truly "encouraged" the concept that smaller gamers like start-up companies could have functions to play in AI research and advancements, he includes.

'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 just altered the guidelines of tech-geopolitics

The "focus on cost benefit" is a distinguishing characteristic of Chinese AI, Chen states, with lower training and reasoning expenses - the costs of utilizing a trained design to draw conclusions from new data.

2025 might also see the development of more Chinese AI models taking on sophisticated reasoning jobs.

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

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

Chinese AI business are moving rapidly, experts say, developing on DeepSeek's momentum to come up with their own innovative and economical ways to apply generative AI to jobs and develop more advanced items beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's advanced AI chips, remains an essential hurdle for Chinese designers, kept in mind Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the capability of Chinese tech companies ... forcing lots of to count on older or lower-performance alternatives which can slow training and reduce model capabilities," she said.

"While some companies like DeepSeek, have found creative ways to optimize or utilize more basic hardware efficiently, obtaining cutting-edge chips still makes a huge difference for training large AI models."

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

US checking out whether DeepSeek utilized limited AI chips obtained through other countries, 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 web so it must come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to stay away from 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 reasoning problems rather!"

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

The automobile attack outside a sports stadium in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities just revealing the death toll a day later on.

DeepSeek failed to point out that an attack had actually occurred, highlighting rather a military air program and other events that had happened in the city like singles' day shopping sales in addition to sports and cultural activities.

Dr Zhang thinks that it might 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 limited access to innovative hardware which can impact how rapidly and thoroughly the model can be trained or upgraded," she said, pointing to existing US export curbs on China.

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

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

That was after multiple duplicated efforts - four prompts to be accurate - in a span of around 20 minutes.

It eventually relayed details about the attack which killed 35 individuals and left lots of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, along with casualties.

However, it composed that "the cops are performing an extensive investigation into the motives and circumstances surrounding the incident", details which is now dated.

The motorist, Fan, was performed last month.

This is Qwen2.5's reaction in complete:

Answer: wiki.snooze-hotelsoftware.de On Nov 11, 2024, a significant and terrible incident happened in Zhuhai, China. According to several news sources, a male named Fan Weiqiu (樊某, setiathome.berkeley.edu male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a significant variety of casualties. Here are the crucial details:

Date and Time: The occurrence occurred on November 11, 2024, at approximately 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 collared by the police.

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

Investigation: The cops are performing a comprehensive examination into the motives and scenarios surrounding the occurrence.

This occasion was extensively reported in the media and caused substantial public concern. The federal government and local authorities have actually been working to supply support to the victims and their families, and to guarantee a detailed examination into the incident.

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

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

The modified response likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had been commonly published in international news reports at the time of the accident - so not a 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 offered a story with a more reflective tone and smoother emotional shifts for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that builds slowly from interest to urgency, keeping the reader engaged. It provides an unforeseen and impactful twist at the end and immersive descriptions and vivid images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, mentally abundant story with a more considerable twist".

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

Opinions, though, 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 tasks, however we can likewise see that it is refraining from doing as strongly as others in imaginative writing," he informed CNA.

Related:

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

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks global AI scene

As journalists and authors, we had to see this for ourselves so we put each bot to the test - to come up with a basic sci-fi movie plot embeded in the futuristic megacity of Chongqing, including main characters from the classic Chinese folklore epic, Journey to the West.

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

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

It also brilliantly reimagined conventional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a stolen battle 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 installed a great fight, developing an equally remarkable cyberpunk storyline which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the famous 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 story that seemed more matched for an animation film.

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

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

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

SO WHICH IS BETTER?

Dr Zhang noted that it was "hard to make a definitive statement" about which bot was best, bytes-the-dust.com including that each displayed its own strengths in different locations, "such as language focus, training information and hardware optimization".

Her insight highlights how Chinese AI designs are not merely reproducing Western paradigms, however rather developing in affordable development methods - and providing localised and improved results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies precise and accurate reactions to questions about Chinese current occasions, 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 drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research firm Strategy Risks.

"When offered an option, Chinese users desire the non-censored variation - similar to anyone else, so I seem like that's a piece missing out on from it."

Independent Beijing-based consultant Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, particularly for Chinese users.

"Ninety per cent of people using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically delicate topics. They're using it for other efficient ways," Chen said.