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 nation 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 "tactically essential" and its foray into the field has actually 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 sped up after ChatGPT took off in 2022 and revealed promises of real-world business applications, Chen informed CNA.

But it was DeepSeek's increase that really "encouraged" the idea that smaller sized players like start-up firms could 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 business just altered the rules of tech-geopolitics

The "emphasis on cost advantage" is an unique feature of Chinese AI, Chen says, with lower training and reasoning costs - the expenses of using a trained model to draw conclusions from new data.

2025 could likewise see the introduction of more Chinese AI models tackling innovative reasoning jobs.

"We might see some AI companies focusing on getting closer to artificial basic intelligence (AGI) while others concentrate on concrete methods to commercialise their models and integrate them with clinical research," Chen included.

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

Chinese AI companies are moving quickly, experts state, building on DeepSeek's momentum to come up with their own innovative and cost-effective ways to apply generative AI to jobs and establish advanced products beyond chatbots.

But on the other side, access to high-end hardware, especially Nvidia's sophisticated AI chips, remains a crucial hurdle for Chinese developers, noted Dr Marina Zhang, an associate teacher 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 alternatives which can slow training and minimize design abilities," she said.

"While some business like DeepSeek, have found creative methods to enhance or utilize more standard hardware efficiently, obtaining cutting-edge chips still makes a big distinction for training very big AI designs."

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

US checking out whether DeepSeek utilized limited 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 delicate 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 took place in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are set to avoid domestic politics.

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

To further check for precision and self-censorship, we asked DeepSeek-R1, Qwen2.5 and ChatGPT the very 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 divulging the death toll a day later.

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

Dr Zhang thinks that it might be a mix of aspects at play, such as censorship as well as "a few practical constraints".

"DeepSeek depends on a mix of older graphics processing systems and has limited access to advanced hardware which can affect how quickly and thoroughly the design can be trained or upgraded," she said, indicating existing US export curbs on China.

"Its strong concentrate on Chinese-language information might also restrict its flexibility (to perform) multilingual jobs ... As a fairly brand-new item, DeepSeek likewise hasn't yet been checked as broadly or on the same scale as more recognized AI models which positions additional challenges throughout real-world release."

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

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

It eventually relayed details about the attack which killed 35 people 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, in addition to casualties.

However, it composed that "the police are conducting a comprehensive investigation into the intentions and scenarios surrounding the incident", details which is now dated.

The motorist, Fan, was performed last month.

This is Qwen2.5's reaction completely:

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

Date and Time: The incident happened on November 11, 2024, at approximately 19:48 PM.

Location: Zhuhai Sports Center, wiki.vst.hs-furtwangen.de 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 old), was captured by the cops.

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

Investigation: The cops are conducting a thorough examination into the motives and circumstances surrounding the occurrence.

This event was commonly reported in the media and triggered substantial public concern. The federal government and regional authorities have actually been working to provide assistance to the victims and their families, and to guarantee a detailed investigation into the occurrence.

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

Despite preliminary success, subsequent efforts to pose the exact same question to Qwen2.5 led to the censors back at work with the reply "I do not have specific details on events that occurred in Zhuhai on November 11, 2024".

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

Predictably, ChatGPT pointed out public details that had actually been commonly released in international news reports at the time of the accident - so not a surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the ability of Chinese AI apps to deliver structured and even "emotionally rich" writing.

"DeepSeek-R1 provided a story with a more introspective tone and smoother emotional transitions for a well-paced story," composed tech author Amanda Caswell, who specialises in AI.

"Qwen2.5 delivered a story that builds gradually from interest to seriousness, keeping the reader engaged. It uses an unforeseen and impactful twist at the end and immersive descriptions and vivid imagery for the setting," she said, including that Qwen2.5 ultimately "crafted a more cinematic, mentally rich story with a more considerable twist".

"DeepSeek wrote a great story however lacked tension and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, though, differ.

Chen believes that Qwen2.5 does not perform as strongly 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 told 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 shocks global AI scene

As reporters and writers, we had 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, including main characters from the timeless Chinese folklore epic, Journey to the West.

True to form, DeepSeek created an appealing story set 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 skyscrapers", "holographic lanterns that drift above neon-lit streets" and "ancient temples nestled in between quantum server farms".

It likewise remarkably reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen combat body", Zhu Bajie as a cyborg nightclub 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 great battle, creating a similarly significant cyberpunk story which similarly reimagined "a ragteam of cyber-enhanced misfits, each matching the legendary figures of Journey to the West".

"This is a world where AI deities guideline, corporations replace emperors and cybernetic implants are as typical as ancient myths."

Disappointingly, Qwen2.5 fell short in this difficulty - providing a story that appeared more suited for an animation movie.

"The motion picture begins with the awakening of Sun Wukong within a high-tech 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 strange brand-new world", he then gets away and satisfies Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on a mission, browsing the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling into the wrong hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "tough to make a definitive declaration" about which bot was best, including that each showed its own strengths in different areas, "such as language focus, training information and hardware optimization".

Her insight underscores how Chinese AI models are not simply duplicating Western paradigms, but rather developing in cost-efficient innovation approaches - and delivering localised and enhanced results.

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

DeepSeek's sci-fi film plot demonstrated its innovative flair that produced a more engaging and imaginative story as compared to Qwen2.5 and ChatGPT's efforts.

Unsurprisingly, the more established ChatGPT, unburdened by Chinese censorship constraints, supplies accurate and accurate reactions to concerns about Chinese current events, which offers it an included benefit.

Experts also weighed in on their ideas after utilizing DeepSeek and other Chinese AI apps.

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

"When offered an option, Chinese users want the non-censored version - just like anyone 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 utilizing the tool are not trying to get a much deeper understanding about Xi Jinping or politically sensitive subjects. They're utilizing it for other productive means," Chen said.