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 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 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 venture into the field has actually been "years in the making", said Chen Qiheng, an associated scientist at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed promises of real-world organization applications, Chen informed CNA.

But it was DeepSeek's rise that actually "urged" the concept that smaller gamers like start-up firms might have functions to play in AI research and advancements, 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 just changed the guidelines of tech-geopolitics

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

2025 could also see the emergence of more Chinese AI designs taking on advanced reasoning jobs.

"We could see some AI companies focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete ways to commercialise their models and incorporate them with scientific research study," Chen added.

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

Chinese AI business are moving rapidly, analysts state, building on DeepSeek's momentum to come up with their own innovative and cost-effective methods to use 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, genbecle.com 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 ability of Chinese tech companies ... forcing many to rely on older or lower-performance options which can slow training and lower design capabilities," she said.

"While some business like DeepSeek, have discovered creative ways to enhance or utilize more basic hardware effectively, obtaining cutting-edge chips still makes a big distinction for training large AI models."

DeepSeek-Nvidia chips: systemcheck-wiki.de Singapore says it anticipates companies to abide by its laws

US looking into whether DeepSeek used limited AI chips obtained through other nations, 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 considered delicate by the state are censored on the web so it should come as no surprise that Chinese-made chatbots will not acknowledge territorial disputes or inform you what occurred in Tiananmen Square in 1989.

Tests suggest 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 math, coding, and reasoning issues instead!"

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

The car attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social media - with authorities only disclosing the death toll a day later on.

DeepSeek failed to discuss that an attack had taken place, highlighting rather a military air program and other occasions that had actually happened in the city like singles' day shopping sales as well as sports and cultural activities.

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

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

"Its strong focus on Chinese-language information may likewise limit its versatility (to perform) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been evaluated as broadly or on the very same scale as more established AI designs which presents extra obstacles throughout real-world implementation."

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

That wanted multiple duplicated efforts - four triggers to be exact - in a period of around 20 minutes.

It eventually communicated details about the attack which eliminated 35 individuals and trademarketclassifieds.com left dozens of others injured, also going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it wrote that "the police are conducting a thorough investigation into the intentions and scenarios surrounding the occurrence", details which is now outdated.

The chauffeur, Fan, was performed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a major and terrible event happened in Zhuhai, China. According to multiple news sources, a male named Fan Weiqiu (樊某, male, 62 years old) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a substantial number of casualties. Here are the crucial details:

Date and Time: pediascape.science The incident happened on November 11, 2024, at around 19:48 PM.

Location: Zhuhai Sports Center, in the Xiangzhou District of Zhuhai.

Casualties: The attack resulted in 35 deaths and 43 injuries.

Perpetrator: The driver, recognized as Fan Weiqiu (male, 62 years old), was collared by the authorities.

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

Investigation: The police are conducting a thorough investigation into the motives and setiathome.berkeley.edu circumstances surrounding the event.

This event was widely reported in the media and public issue. The federal 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 event.

If you need more detailed details or have specific concerns about the occurrence, feel totally free to ask.

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

The transformed action likewise raised concerns about its consistency and reliability.

Predictably, ChatGPT mentioned public details that had been widely published in international news reports at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 provided a story with a more introspective tone and smoother emotional shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that builds gradually from curiosity to urgency, keeping the reader engaged. It provides an unanticipated and impactful twist at the end and immersive descriptions and vibrant imagery for the setting," she said, adding that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more considerable twist".

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

Opinions, however, vary.

Chen believes that Qwen2.5 does not carry out as highly as DeepSeek and ChatGPT when it pertains to creative writing.

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

As reporters and authors, 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, featuring main characters from the timeless Chinese folklore impressive, Journey to the West.

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

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

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

ChatGPT set up an excellent battle, developing an equally remarkable cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary figures of Journey to the West".

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

Disappointingly, Qwen2.5 fell short in this obstacle - delivering a storyline that seemed more matched for an animation movie.

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

Realising his brand-new reality and "seeking to comprehend his function in this strange new world", he then gets away and fulfills Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

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

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI designs are not just reproducing Western paradigms, but rather developing in cost-efficient innovation approaches - and delivering localised and enhanced results.

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

DeepSeek's sci-fi motion picture plot showed its imaginative flair that produced 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, pipewiki.org offers precise and accurate responses to concerns about Chinese existing occasions, which provides it an added benefit.

Experts also 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 company Strategy Risks.

"When offered a choice, Chinese users want the non-censored version - just like anyone else, so I feel 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 attempting to get a much deeper understanding about Xi Jinping or politically delicate topics. They're using it for other efficient methods," Chen said.