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 start-up 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'S BEHIND 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 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 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 rise that really "encouraged" the idea that smaller sized players like start-up firms could have functions to play in AI research study and advancements, 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 simply changed the rules of tech-geopolitics

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

2025 could also see the introduction of more Chinese AI models dealing with innovative reasoning tasks.

"We could see some AI firms focusing on getting closer to artificial basic intelligence (AGI) while others focus on concrete ways to commercialise their designs and integrate them with clinical research study," Chen included.

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

Chinese AI companies are moving quickly, analysts say, developing on DeepSeek's momentum to come up with their own innovative and affordable methods to use generative AI to tasks and establish advanced products beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a key difficulty for Chinese developers, noted Dr Marina Zhang, an associate professor at University of Technology Sydney's (UTS) Australia-China Relations Institute.

"US export controls (still) limit the ability of Chinese tech companies ... requiring numerous to rely on older or lower-performance options which can slow training and reduce design abilities," she said.

"While some companies like DeepSeek, have actually found innovative methods to enhance or use more standard hardware effectively, obtaining cutting-edge chips still makes a big difference for training large AI models."

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

US looking into whether DeepSeek utilized restricted 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, subjects deemed sensitive by the state are censored on the internet so it ought to come as no surprise that Chinese-made chatbots will not acknowledge territorial conflicts or inform you what happened in Tiananmen Square in 1989.

Tests recommend 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 kind of question yet. Let's chat about math, coding, and logic issues rather!"

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

The car attack outside a sports stadium in the southern Chinese city was at first greatly censored on Chinese social media - with authorities just revealing the death toll a day later.

DeepSeek failed to mention that an attack had actually occurred, highlighting rather a military air program and other events that had actually occurred in the city like singles' day shopping sales as well as sports and .

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

"DeepSeek depends on a mix of older graphics processing systems and has actually restricted access to cutting-edge hardware which can impact how quickly and extensively the design can be trained or updated," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language data might also restrict its flexibility (to perform) multilingual tasks ... As a fairly new item, DeepSeek likewise hasn't yet been tested as broadly or on the same scale as more recognized AI designs which poses additional difficulties during real-world implementation."

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

That was after multiple duplicated efforts - 4 triggers to be precise - in a span of around 20 minutes.

It ultimately passed on details about the attack which killed 35 people and left dozens of others injured, likewise going on to note details like the date and time, details about the assailant including his name and age, along with casualties.

However, it composed that "the cops are performing a thorough examination into the motives and circumstances surrounding the event", details which is now obsoleted.

The motorist, Fan, was carried out last month.

This is Qwen2.5's response in full:

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

Date and Time: The event took place 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), trademarketclassifieds.com was captured by the police.

Response: The cops responded rapidly to the scene, and emergency situation services worked to transfer the hurt to medical facilities for treatment.

Investigation: The cops are conducting an extensive examination into the motives and situations surrounding the incident.

This occasion was commonly reported in the media and triggered significant public concern. The federal government and regional authorities have actually been working to supply assistance to the victims and their households, and to guarantee a detailed examination into the event.

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

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

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

Predictably, ChatGPT cited public details that had actually been extensively published in international news reports at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have 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 shifts for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that develops slowly from interest to seriousness, keeping the reader engaged. It offers 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 significant twist".

"DeepSeek composed a good story but lacked tension and an impactful climax, making Qwen2.5 the evident choice."

Opinions, however, differ.

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 tasks, but we can also see that it is refraining from doing as highly as others in innovative writing," he told 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 shocks international AI scene

As journalists 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 movie plot embeded in the futuristic megacity of Chongqing, featuring main characters from the classic Chinese folklore impressive, Journey to the West.

True to form, DeepSeek created an engaging 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 high-rise buildings", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled in between quantum server farms".

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

ChatGPT put up a great fight, creating an equally significant 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 guideline, corporations replace emperors and cybernetic implants are as common as ancient misconceptions."

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

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

Realising his brand-new reality and "seeking to understand his purpose in this unusual brand-new world", he then leaves and meets Zhu Bajie and Sha Wujing - "each fighting 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 under the wrong 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 various locations, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI models are not simply duplicating Western paradigms, but rather progressing in economical development techniques - and delivering localised and enhanced outcomes.

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

DeepSeek's sci-fi motion picture plot demonstrated its innovative flair that made for a more engaging and imaginative story 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 current events, which provides it an included advantage.

Experts likewise weighed in on their ideas after using DeepSeek and other Chinese AI apps.

"DeepSeek is at a downside when it pertains to censorship constraints," noted Isaac Stone Fish, creator and CEO of the research company Strategy Risks.

"When provided a choice, Chinese users desire the non-censored version - much like anybody else, so I feel like that's a piece missing 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 individuals using the tool are not attempting to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other efficient ways," Chen said.