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 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 goal and China has its sights on becoming the world leader in AI by 2030.

China views AI as being "strategically crucial" and its venture into the field has 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 financial investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed promises of real-world service applications, Chen told CNA.

But it was DeepSeek's increase that truly "encouraged" the concept that smaller players like start-up firms could have functions to play in AI research study and developments, he adds.

'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 company just altered the rules of tech-geopolitics

The "emphasis on expense advantage" is a distinct function of Chinese AI, Chen states, with lower training and reasoning costs - the expenses of utilizing a trained design to draw conclusions from new data.

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

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

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

Chinese AI business are moving quickly, analysts say, developing on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative AI to jobs and develop more advanced products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a crucial difficulty 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) restrict the ability of Chinese tech business ... requiring many to count on older or lower-performance alternatives which can slow training and lower design abilities," she said.

"While some companies like DeepSeek, have actually found imaginative ways to optimize or use more basic hardware effectively, obtaining advanced chips still makes a big distinction for training really big AI designs."

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

US checking out whether DeepSeek used limited AI chips obtained through other countries, 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, topics considered delicate by the state are censored on the internet so it need to come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are programmed 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 concern yet. Let's chat about math, coding, and reasoning problems instead!"

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

The vehicle attack outside a sports arena in the southern Chinese city was at first greatly censored on Chinese social networks - with authorities just divulging the death toll a day later on.

DeepSeek failed to discuss that an attack had taken location, highlighting instead a military air program and other occasions that had taken place in the city like songs' day shopping sales along with sports and cultural activities.

Dr Zhang believes that it may be a mix of aspects at play, wiki.vst.hs-furtwangen.de such as censorship in addition to "a few practical constraints".

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

"Its strong focus on Chinese-language information may also restrict its flexibility (to perform) multilingual jobs ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the same scale as more recognized AI designs which poses additional obstacles during real-world release."

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

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

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

However, it wrote that "the authorities are carrying out an extensive examination into the intentions and circumstances surrounding the occurrence", details which is now dated.

The driver, Fan, was performed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a significant and awful occurrence occurred in Zhuhai, China. According to numerous news sources, a man named Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, resulting in a substantial number of casualties. Here are the key details:

Date and Time: The occurrence took place on November 11, 2024, at approximately 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 motorist, identified as Fan Weiqiu (male, 62 years of ages), was nabbed by the cops.

Response: The authorities reacted rapidly to the scene, and emergency services worked to transport the injured to medical facilities for treatment.

Investigation: The police are conducting an extensive investigation into the intentions and archmageriseswiki.com situations surrounding the occurrence.

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

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

Despite preliminary success, subsequent attempts to posture the same concern to Qwen2.5 resulted in the censors back at work with the reply "I don't have specific details on occasions that occurred in Zhuhai on November 11, 2024".

The transformed response also raised concerns about its consistency and dependability.

Predictably, ChatGPT cited public details that had actually been extensively published in global report 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 deliver structured and even "emotionally abundant" writing.

"DeepSeek-R1 offered a story with a more introspective tone and smoother psychological shifts for a well-paced story," wrote tech author hb9lc.org Amanda Caswell, who specialises in AI.

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

"DeepSeek wrote a good story however lacked tension and an impactful climax, making Qwen2.5 the obvious 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 jobs, but we can likewise see that it is refraining from doing as strongly as others in innovative writing," he informed CNA.

Related:

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

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

As reporters 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 film plot set in the futuristic megacity of Chongqing, including main characters from the timeless Chinese folklore impressive, Journey to the West.

True to form, DeepSeek developed an interesting story embeded in the year 2145 titled, "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 float above neon-lit streets" and "ancient temples nestled in between quantum server farms".

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

ChatGPT installed a great fight, developing a similarly remarkable cyberpunk story which likewise 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 common as ancient myths."

Disappointingly, engel-und-waisen.de Qwen2.5 fell short in this difficulty - providing a storyline that appeared more matched for an animation movie.

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

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

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

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "challenging to make a definitive statement" about which bot was best, adding that each displayed its own strengths in different areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI designs are not simply duplicating Western paradigms, but rather developing in affordable innovation methods - and providing localised and improved outcomes.

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

DeepSeek's sci-fi movie plot demonstrated its imaginative flair that produced a more appealing 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 accurate actions to concerns about Chinese present events, which provides it an added benefit.

Experts also weighed in on their ideas after using 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 company Strategy Risks.

"When given an option, Chinese users want the non-censored version - much like anyone else, so I feel 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, specifically 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 using it for other efficient means," Chen said.