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 created 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 objective and China has its sights on ending up being the world leader in AI by 2030.

China views AI as being "strategically important" and its venture into the field has been "years in the making", said Chen Qiheng, an affiliated researcher at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI sped up after ChatGPT removed in 2022 and showed guarantees of real-world business applications, Chen informed CNA.

But it was DeepSeek's rise that actually "urged" the concept that smaller sized players like start-up companies might have roles to play in AI research study and developments, he adds.

'A lot is up in the air': Is Chinese company DeepSeek's AI design as as it claims?

Commentary: DeepSeek - how a Chinese AI company simply changed the rules of tech-geopolitics

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

2025 could also see the introduction of more Chinese AI models tackling advanced thinking jobs.

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

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

Chinese AI business are moving rapidly, experts state, developing on DeepSeek's momentum to come up with their own ingenious and cost-effective methods to use generative AI to tasks and develop more sophisticated products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a key obstacle 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 ... forcing lots of to count on older or lower-performance alternatives which can slow training and minimize model abilities," she said.

"While some companies like DeepSeek, have actually discovered creative ways to optimize or utilize more fundamental hardware effectively, obtaining innovative chips still makes a huge difference for training extremely big AI designs."

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

US looking into whether DeepSeek utilized restricted AI chips obtained through other nations, 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, subjects deemed delicate by the state are censored on the web so it must come as not a surprise that Chinese-made chatbots will not acknowledge territorial disagreements or inform you what occurred in Tiananmen Square in 1989.

Tests suggest 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 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 automobile attack outside a sports arena in the southern Chinese city was at first heavily censored on Chinese social networks - with authorities only divulging the death toll a day later on.

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

Dr Zhang believes that it might be a mix of factors at play, such as censorship in addition to "a couple of practical constraints".

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

"Its strong focus on Chinese-language data may likewise limit its versatility (to perform) multilingual tasks ... As a fairly new item, DeepSeek also hasn't yet been tested as broadly or on the exact same scale as more recognized AI models which poses additional challenges during real-world release."

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

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

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

However, it wrote that "the police are carrying out a thorough examination into the intentions and situations surrounding the incident", details which is now obsoleted.

The chauffeur, systemcheck-wiki.de Fan, was executed last month.

This is Qwen2.5's action completely:

Answer: On Nov 11, 2024, a significant and terrible occurrence took place in Zhuhai, China. According to multiple news sources, a guy named Fan Weiqiu (樊某, male, 62 years of ages) drove a cars and truck into a crowd at the Zhuhai Sports Center, resulting in a substantial number of casualties. Here are the crucial 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 resulted in 35 deaths and 43 injuries.

Perpetrator: The driver, determined as Fan Weiqiu (male, hb9lc.org 62 years old), was collared by the cops.

Response: The authorities reacted rapidly to the scene, and emergency services worked to transfer the injured to health centers for treatment.

Investigation: The authorities are conducting a comprehensive investigation into the motives and situations surrounding the event.

This event was commonly reported in the media and triggered significant public issue. The federal government and local authorities have been working to offer support to the victims and their households, and to make sure a detailed investigation into the incident.

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

Despite initial success, subsequent attempts to position the same concern to Qwen2.5 led to the censors back at work with the reply "I don't have particular details on events that took place in Zhuhai on November 11, 2024".

The modified response likewise raised questions about its consistency and reliability.

Predictably, ChatGPT pointed out public details that had actually been widely released in worldwide news reports at the time of the accident - 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 introspective tone and smoother psychological transitions for a well-paced story," composed tech writer Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that constructs gradually from interest to urgency, keeping the reader engaged. It provides an unforeseen 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, emotionally rich story with a more significant twist".

"DeepSeek composed a great story but did not have stress and an impactful climax, making Qwen2.5 the evident choice."

Opinions, though, differ.

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

"(Qwen2.5) is on par with DeepSeek V3 on certain tasks, but we can likewise 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 shocks global 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 standard sci-fi movie 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 created an engaging story set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It consisted of intricate 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 remarkably reimagined conventional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken battle 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 put up a good fight, creating a similarly 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 change emperors and cybernetic implants are as typical as ancient misconceptions."

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

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

Realising his new truth and "looking for to comprehend his purpose in this odd new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each dealing with their own existential crises".

The trio then embarks on a quest, browsing the streets of Chongqing to secure the spiritual "Eternal Scroll" from falling into the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang kept in mind that it was "hard to make a conclusive declaration" about which bot was best, including that each displayed its own strengths in different areas, "such as language focus, training data and hardware optimization".

Her insight highlights how Chinese AI models are not merely replicating Western paradigms, however rather developing in economical development methods - and providing localised and enhanced outcomes.

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

DeepSeek's sci-fi movie plot showed its creative flair that produced a more appealing and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, provides accurate and accurate responses to questions about Chinese existing occasions, which provides it an included benefit.

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

"DeepSeek is at a drawback when it pertains to censorship constraints," noted Isaac Stone Fish, founder and trademarketclassifieds.com CEO of the research study company Strategy Risks.

"When offered a choice, Chinese users desire the non-censored variation - simply like anyone else, so I seem like that's a piece missing from it."

Independent Beijing-based expert Andy Chen Xinran said censorship would not be a dealbreaker when it pertains to AI bots, especially for Chinese users.

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