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 becoming the world leader in AI by 2030.

China views AI as being "tactically important" and its foray into the field has been "years in the making", said Chen Qiheng, an associated scientist at the Asia Society Policy Institute's Center for hb9lc.org China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT took off in 2022 and revealed pledges of real-world business applications, Chen informed CNA.

But it was DeepSeek's increase that truly "encouraged" the concept that smaller players like start-up companies could have functions to play in AI research study and developments, pediascape.science he includes.

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

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

The "focus on expense 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 emergence of more Chinese AI models dealing with sophisticated reasoning tasks.

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

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

Chinese AI business are moving rapidly, experts say, constructing on DeepSeek's momentum to come up with their own ingenious and economical methods to apply generative AI to jobs and develop advanced items beyond chatbots.

But on the flip side, access to high-end hardware, especially Nvidia's advanced AI chips, remains a key obstacle for Chinese designers, 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 ... forcing many to depend on older or lower-performance alternatives which can slow training and decrease design capabilities," 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 really large 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, topics considered sensitive by the state are censored on the web so it should come as not a surprise that Chinese-made chatbots will not acknowledge territorial disputes or tell you what took place in Tiananmen Square in 1989.

Tests suggest Chinese chatbots are set to stay away from 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 math, coding, and reasoning issues rather!"

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

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

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

Dr Zhang thinks that it might be a mix of aspects at play, such as censorship in addition to "a couple of useful constraints".

"DeepSeek relies on a mix of older graphics processing systems and has restricted access to advanced hardware which can affect how rapidly and thoroughly 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 jobs ... As a fairly new product, DeepSeek likewise hasn't yet been checked as broadly or on the exact same scale as more established AI models which presents additional challenges during real-world implementation."

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

That wanted several repeated attempts - four prompts to be precise - in a period of around 20 minutes.

It ultimately passed on details about the attack which killed 35 individuals and left lots of others hurt, also going on to note details like the date and time, details about the assailant including his name and age, in addition to casualties.

However, it wrote that "the authorities are performing a comprehensive examination into the intentions and circumstances surrounding the incident", details which is now dated.

The motorist, Fan, was performed last month.

This is Qwen2.5's reaction in complete:

Answer: On Nov 11, 2024, a significant and awful incident happened in Zhuhai, China. According to several news sources, a guy named Fan Weiqiu (樊某, male, wiki.snooze-hotelsoftware.de 62 years old) drove a vehicle into a crowd at the Zhuhai Sports Center, leading to a substantial variety of casualties. Here are the key details:

Date and Time: The occurrence occurred on November 11, 2024, at around 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 motorist, recognized as Fan Weiqiu (male, 62 years old), was captured by the authorities.

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

Investigation: The police are performing an extensive examination into the intentions and circumstances surrounding the incident.

This occasion was extensively reported in the media and links.gtanet.com.br triggered substantial public issue. The federal government and regional authorities have actually been working to provide support to the victims and their families, and to make sure a detailed examination into the incident.

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

Despite preliminary success, subsequent attempts to pose the very same question to Qwen2.5 led to the censors back at work with the reply "I do not have particular details on events that took place in Zhuhai on November 11, 2024".

The transformed reaction also raised questions about its consistency and .

Predictably, ChatGPT cited public details that had actually been extensively published in worldwide report at the time of the mishap - so not a surprises there.

WHICH IS MORE CREATIVE?

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

"DeepSeek-R1 offered a story with a more introspective tone and smoother emotional transitions for a well-paced story," wrote 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 unanticipated and impactful twist at the end and immersive descriptions and vivid 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 but lacked tension and an impactful climax, making Qwen2.5 the apparent choice."

Opinions, however, differ.

Chen believes that Qwen2.5 does not perform as strongly as DeepSeek and ChatGPT when it pertains to innovative 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 imaginative writing," he informed CNA.

Related:

China's brand-new face of AI: Who is DeepSeek founder Liang Wenfeng?

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek shocks international AI scene

As journalists and writers, 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 embeded in the futuristic megacity of Chongqing, wavedream.wiki including main characters from the traditional Chinese folklore impressive, Journey to the West.

True to form, DeepSeek created an interesting storyline embeded in the year 2145 entitled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It consisted of sophisticated 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 standard heroes Sun Wukong as "an ironical, self-aware AI housed in a stolen fight 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 become waterlogged and fragmented".

ChatGPT put up a great battle, ratemywifey.com coming up with a similarly remarkable cyberpunk storyline which similarly 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 change emperors and cybernetic implants are as common as ancient myths."

Disappointingly, Qwen2.5 fell short in this difficulty - providing a storyline that seemed more suited for an animation film.

"The motion picture starts 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 new truth and "looking for to comprehend his function in this odd new world", he then escapes and satisfies Zhu Bajie and Sha Wujing - "each battling with their own existential crises".

The trio then embarks on a quest, navigating the streets of Chongqing to safeguard the spiritual "Eternal Scroll" from falling under the incorrect hands.

SO WHICH IS BETTER?

Dr Zhang noted that it was "difficult to make a conclusive statement" about which bot was best, adding that each showed its own strengths in various areas, "such as language focus, training data and hardware optimization".

Her insight underscores how Chinese AI models are not just replicating Western paradigms, but rather developing in cost-effective development approaches - and providing localised and enhanced results.

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

DeepSeek's sci-fi motion picture plot demonstrated its imaginative flair that produced a more interesting and imaginative narrative as compared to Qwen2.5 and ChatGPT's efforts.

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

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

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

"When offered an option, Chinese users want the non-censored version - much like anyone 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 per cent of individuals using the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other efficient means," Chen said.