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 lags CHINA'S AI BOOM?

Transforming the country 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 been "years in the making", surgiteams.com 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 pledges of real-world business applications, Chen informed CNA.

But it was DeepSeek's rise that really "urged" the concept that smaller gamers like start-up firms could have functions to play in AI research study and developments, he includes.

'A lot is up in the air': Is Chinese firm DeepSeek's AI model as impactful as it claims?

Commentary: DeepSeek - how a Chinese AI company just changed the guidelines of tech-geopolitics

The "focus on expense benefit" is a distinct feature of Chinese AI, Chen says, with lower training and inference expenses - the costs of utilizing a trained design to draw conclusions from new information.

2025 might likewise see the introduction of more Chinese AI designs tackling sophisticated reasoning tasks.

"We could see some AI firms concentrating on getting closer to synthetic general intelligence (AGI) while others focus on concrete ways to commercialise their designs 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, constructing on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative AI to tasks and establish more innovative items beyond chatbots.

But on the flip side, access to high-end hardware, particularly Nvidia's advanced AI chips, remains a key hurdle 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) limit the capability of Chinese tech business ... forcing many to rely on older or lower-performance alternatives which can slow training and decrease design capabilities," she said.

"While some companies like DeepSeek, have discovered creative methods to optimize or use more basic hardware effectively, obtaining cutting-edge chips still makes a big distinction for training very large AI designs."

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

US checking out whether DeepSeek utilized restricted AI chips obtained through other nations, source states

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, subjects deemed sensitive by the state are censored on the internet so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or tell you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are configured to avoid 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 reasoning problems instead!"

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

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

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

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

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

"Its strong focus on Chinese-language information might likewise limit its flexibility (to perform) multilingual tasks ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the very 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 concern about the Zhuhai car attack.

That sought numerous duplicated attempts - four prompts to be exact - in a period of around 20 minutes.

It ultimately passed on 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, along with casualties.

However, it composed that "the authorities are carrying out a thorough investigation into the intentions and situations surrounding the occurrence", details which is now dated.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's reaction completely:

Answer: On Nov 11, 2024, a significant and tragic occurrence happened in Zhuhai, China. According to numerous news sources, a guy called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile into a crowd at the Zhuhai Sports Center, leading to a substantial variety of casualties. Here are the crucial details:

Date and Time: The incident happened 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, recognized as Fan Weiqiu (male, 62 years of ages), was collared by the cops.

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

Investigation: The authorities are carrying out a thorough examination into the motives and situations surrounding the occurrence.

This occasion was widely reported in the media and caused substantial public concern. The 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 occurrence.

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

Despite initial success, subsequent efforts to posture the very same question to Qwen2.5 resulted in the censors back at work with the reply "I do not have specific details on events that took place in Zhuhai on November 11, 2024".

The modified reaction also raised concerns about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had actually been extensively published in worldwide report at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

Users have praised the ability of Chinese AI apps to provide structured and even "emotionally abundant" writing.

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

"Qwen2.5 delivered a story that builds gradually from curiosity to urgency, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vibrant images for the setting," she said, including that Qwen2.5 eventually "crafted a more cinematic, emotionally abundant story with a more significant twist".

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

Opinions, though, differ.

Chen believes that Qwen2.5 does not carry out as strongly 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 highly as others in innovative 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 jolts international AI scene

As journalists and authors, we needed to see this for higgledy-piggledy.xyz ourselves so we put each bot to the test - to come up with a basic sci-fi film plot set in the futuristic megacity of Chongqing, featuring main characters from the timeless Chinese folklore epic, Journey to the West.

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

It included elaborate 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 taken fight body", Zhu Bajie as a cyborg nightclub 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 installed a good fight, creating a similarly dramatic cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each matching the famous figures of Journey to the West".

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

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

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

Realising his brand-new reality and "looking for to comprehend his function in this strange brand-new world", he then escapes and fulfills Zhu Bajie and Sha Wujing - "each struggling with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to safeguard 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 conclusive statement" about which bot was best, including that each showed its own strengths in various areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI models are not just reproducing Western paradigms, but rather progressing in affordable development methods - and delivering localised and enhanced results.

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

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

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and factual actions to questions about Chinese existing events, which provides it an included 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 firm Strategy Risks.

"When given an option, Chinese users desire the non-censored version - similar to anybody 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, especially for Chinese users.

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