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, wiki.vst.hs-furtwangen.de AFP/Sebastien Bozon)

This audio is produced by an AI tool.

Bong Xin Ying

Lakeisha Leo

WHAT lags CHINA'S AI BOOM?

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

Private and public financial investments in Chinese AI accelerated after ChatGPT removed in 2022 and revealed promises of real-world service applications, Chen told CNA.

But it was DeepSeek's increase that really "encouraged" the concept that smaller players like start-up companies 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 model as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI company simply altered the guidelines of tech-geopolitics

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

2025 might likewise see the development of more Chinese AI designs dealing with innovative reasoning tasks.

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

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

Chinese AI companies are moving quickly, analysts state, developing on DeepSeek's momentum to come up with their own ingenious and affordable ways to use generative AI to jobs and develop advanced products beyond chatbots.

But on the other hand, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a key difficulty for Chinese developers, 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 lots of to depend on older or lower-performance options which can slow training and decrease model capabilities," she said.

"While some companies like DeepSeek, have discovered creative ways to enhance or use more fundamental hardware efficiently, obtaining cutting-edge chips still makes a big difference for training large AI models."

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

US checking out whether DeepSeek used limited AI chips obtained through other nations, source states

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

WHICH BEST ADDRESSES CURRENT EVENTS IN CHINA?

In China, subjects deemed sensitive by the state are censored on the internet so it should 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 configured to steer clear of domestic politics.

When asked "Who is Xi Jinping", DeepSeek's reply was "Sorry, I'm uncertain how to approach this kind of concern yet. Let's chat about mathematics, coding, and logic problems rather!"

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

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

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

Dr Zhang believes that it may be a mix of factors at play, such as censorship as well as "a couple of useful constraints".

"DeepSeek relies on a mix of older graphics processing units and has actually restricted access to cutting-edge 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 concentrate on Chinese-language data may also restrict its flexibility (to perform) multilingual jobs ... As a fairly brand-new item, DeepSeek also hasn't yet been evaluated as broadly or on the same scale as more recognized AI designs which postures extra challenges during real-world deployment."

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

That sought multiple duplicated efforts - four prompts to be exact - in a span of around 20 minutes.

It ultimately relayed details about the attack which eliminated 35 individuals and 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 incident", details which is now obsoleted.

The chauffeur, Fan, was executed last month.

This is Qwen2.5's response in full:

Answer: On Nov 11, 2024, a significant and disgaeawiki.info terrible event took place in Zhuhai, China. According to multiple news sources, a male 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 incident 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 chauffeur, identified as Fan Weiqiu (male, 62 years old), was nabbed by the authorities.

Response: wiki.asexuality.org The cops responded quickly to the scene, and emergency situation services worked to transfer the injured to healthcare facilities for treatment.

Investigation: The police are carrying out a thorough investigation into the intentions and scenarios surrounding the incident.

This event was widely reported in the media and caused considerable public issue. The government and local authorities have actually been working to offer assistance to the victims and their households, and to ensure a detailed investigation into the occurrence.

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

Despite preliminary success, subsequent attempts to present the same concern to Qwen2.5 led to 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 action also raised concerns about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had been extensively 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 psychological transitions for a well-paced story," wrote tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that constructs slowly from curiosity to seriousness, keeping the reader engaged. It uses an unanticipated and impactful twist at the end and immersive descriptions and brilliant imagery for the setting," she said, forum.pinoo.com.tr adding that Qwen2.5 eventually "crafted a more cinematic, emotionally rich story with a more considerable twist".

"DeepSeek composed an excellent story however did not have tension and an impactful climax, making Qwen2.5 the evident option."

Opinions, it-viking.ch though, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, but 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 founder Liang Wenfeng?

'Made in China': Pride, enjoyable surprise from Chinese netizens as DeepSeek shocks global 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 basic sci-fi film plot embeded in the futuristic megacity of Chongqing, including main characters from the traditional Chinese folklore epic, Journey to the West.

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

It included fancy 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 likewise brilliantly reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken fight body", Zhu Bajie as a cyborg bar 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 set up a good battle, creating a similarly dramatic cyberpunk storyline which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring the legendary 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 challenge - delivering a story that appeared more matched for an animation movie.

"The movie begins with the awakening of Sun Wukong within a modern research 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 purpose in this odd brand-new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each fighting with their own existential crises".

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

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not merely reproducing Western paradigms, however rather developing in cost-efficient innovation methods - and providing localised and improved results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides precise and accurate actions to questions about Chinese existing events, which gives it an added benefit.

Experts likewise weighed in on their ideas after using 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 offered an option, Chinese users want the non-censored variation - just like 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, particularly for Chinese users.

"Ninety per cent of people utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive topics. They're using it for other productive methods," Chen said.