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 produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT'S BEHIND 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 ending up being the world leader in AI by 2030.

China views AI as being "strategically important" 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 China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT removed in 2022 and showed guarantees of real-world company applications, Chen informed CNA.

But it was DeepSeek's increase that actually "urged" the idea that smaller gamers like start-up companies might have roles to play in AI research study and developments, 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 rules of tech-geopolitics

The "emphasis on cost advantage" is a distinctive function of Chinese AI, Chen says, with lower training and reasoning costs - the costs of using a trained model to draw conclusions from new data.

2025 might likewise see the development of more Chinese AI models dealing with innovative thinking tasks.

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

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

Chinese AI business are moving rapidly, experts state, developing on DeepSeek's momentum to come up with their own innovative and cost-efficient ways to use generative AI to jobs and establish advanced products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's sophisticated AI chips, demo.qkseo.in remains an essential difficulty 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) restrict the capability of Chinese tech companies ... forcing many to count on older or lower-performance alternatives which can slow training and minimize design capabilities," she said.

"While some business like DeepSeek, have found innovative ways to optimize or use more standard hardware effectively, obtaining innovative chips still makes a big difference for training huge AI models."

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

US looking into whether DeepSeek utilized limited AI chips obtained through other countries, source says

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

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, topics deemed sensitive 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 happened in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to guide clear of 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 instead!"

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

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

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

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

"DeepSeek counts on a mix of older graphics processing systems and has restricted access to innovative hardware which can impact how rapidly and extensively 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 item, DeepSeek likewise hasn't yet been evaluated as broadly or on the exact same scale as more recognized AI models which presents extra obstacles during real-world deployment."

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

That sought numerous repeated efforts - four triggers to be exact - in a span of around 20 minutes.

It ultimately communicated details about the attack which killed 35 individuals and left lots of others injured, also going on to list details like the date and time, details about the assailant including his name and age, as well as casualties.

However, it wrote that "the cops are conducting an extensive investigation into the intentions and scenarios surrounding the occurrence", 89u89.com details which is now outdated.

The driver, Fan, was performed last month.

This is Qwen2.5's reaction in full:

Answer: On Nov 11, 2024, a major and awful occurrence happened in Zhuhai, China. According to several news sources, a male called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a considerable number of casualties. Here are the essential details:

Date and Time: The occurrence took place 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 43 injuries.

Perpetrator: engel-und-waisen.de The driver, identified as Fan Weiqiu (male, 62 years old), was nabbed by the police.

Response: The police reacted quickly to the scene, and emergency situation services worked to carry the injured to medical facilities for treatment.

Investigation: The authorities are performing an extensive examination into the intentions and circumstances surrounding the occurrence.

This event was extensively reported in the media and caused considerable public issue. The government and local authorities have been working to supply support to the victims and their families, and to make sure a detailed investigation into the incident.

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

Despite initial success, subsequent attempts to pose the exact same concern to Qwen2.5 resulted in the censors back at work with the reply "I do not have particular details on events that happened in Zhuhai on November 11, 2024".

The altered reaction also raised questions about its consistency and dependability.

Predictably, ChatGPT cited public details that had actually been commonly released in worldwide news reports at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the capability of Chinese AI apps to deliver structured and even "mentally rich" writing.

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

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

"DeepSeek wrote an excellent story but did not have tension and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, though, vary.

Chen believes 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 jobs, but we can also see that it is refraining from doing as highly as others in innovative writing," he informed 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 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 standard sci-fi movie plot set in the futuristic megacity of Chongqing, featuring main characters from the traditional Chinese folklore impressive, Journey to the West.

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

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

It also brilliantly reimagined traditional heroes Sun Wukong as "a sarcastic, self-aware AI housed in a taken battle 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 a great fight, creating an equally significant 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 change emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this difficulty - delivering a that appeared more suited for an animation film.

"The movie starts 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 reality and "looking for to understand his function in this odd new world", he then gets away and meets Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on 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 "challenging to make a definitive declaration" about which bot was best, adding 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 affordable development techniques - and delivering localised and enhanced results.

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

DeepSeek's sci-fi motion picture plot showed its creative flair that made for a more engaging and creative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more recognized ChatGPT, unburdened by Chinese censorship constraints, offers precise and accurate actions 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 disadvantage when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When given a choice, Chinese users desire the non-censored version - 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 people using the tool are not trying to get a deeper understanding about Xi Jinping or politically delicate topics. They're using it for other productive methods," Chen said.