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 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 goal and China has its sights on becoming 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 scientist at the Asia Society Policy Institute's Center for China Analysis.

Private and public investments in Chinese AI accelerated after ChatGPT took off in 2022 and showed guarantees of real-world company applications, Chen informed CNA.

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

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

Commentary: bio.rogstecnologia.com.br DeepSeek - how a Chinese AI business just altered the rules of tech-geopolitics

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

2025 might also see the development of more Chinese AI designs tackling innovative reasoning tasks.

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

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

Chinese AI companies are moving quickly, engel-und-waisen.de analysts say, constructing on DeepSeek's momentum to come up with their own ingenious and cost-efficient methods to use generative AI to tasks and establish more innovative products beyond chatbots.

But on the other side, access to high-end hardware, particularly Nvidia's advanced AI chips, surgiteams.com remains an essential difficulty 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 capability of Chinese tech companies ... requiring numerous to count on older or lower-performance options which can slow training and lower design abilities," she said.

"While some companies like DeepSeek, have found innovative ways to optimize or use more standard hardware efficiently, obtaining cutting-edge chips still makes a big distinction for training large AI designs."

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

US checking out whether DeepSeek used limited AI chips obtained through other countries, source says

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, topics 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 disputes or inform you what occurred in Tiananmen Square in 1989.

Tests recommend Chinese chatbots are programmed to avoid 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 mathematics, coding, and reasoning issues rather!"

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

The vehicle attack outside a sports arena in the southern Chinese city was initially greatly censored on Chinese social networks - with authorities only divulging the death toll a day later on.

DeepSeek failed to discuss that an attack had actually happened, highlighting instead a military air show and other occasions that had actually taken place 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 factors at play, such as censorship along with "a few practical constraints".

"DeepSeek depends on a mix of older graphics processing units and has actually restricted access to cutting-edge 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 focus on Chinese-language data may likewise restrict its flexibility (to carry out) multilingual jobs ... As a fairly brand-new product, DeepSeek also hasn't yet been tested as broadly or on the same scale as more recognized AI models which postures extra challenges during real-world implementation."

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

That wanted numerous duplicated attempts - 4 prompts to be precise - in a period of around 20 minutes.

It ultimately communicated details about the attack which killed 35 people 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, as well as casualties.

However, it wrote that "the authorities are carrying out a comprehensive investigation into the intentions and scenarios surrounding the occurrence", wavedream.wiki details which is now obsoleted.

The chauffeur, Fan, was carried out last month.

This is Qwen2.5's response completely:

Answer: On Nov 11, 2024, a major and terrible incident took place in Zhuhai, China. According to several news sources, a man called Fan Weiqiu (樊某, male, 62 years of ages) drove an automobile 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 took place 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 of ages), was nabbed by the authorities.

Response: The cops responded rapidly to the scene, and emergency services worked to carry the hurt to health centers for treatment.

Investigation: The police are conducting a thorough examination into the motives and scenarios surrounding the occurrence.

This event was commonly reported in the media and triggered considerable public issue. The government and local authorities have been working to provide assistance to the victims and their households, and to make sure a detailed examination into the incident.

If you need more detailed details or have particular concerns about the occurrence, feel totally free to ask.

Despite initial success, subsequent attempts to present the very same question to Qwen2.5 resulted in the censors back at work with the reply "I don't have particular details on occasions that took place in Zhuhai on November 11, 2024".

The transformed response likewise raised questions about its consistency and dependability.

Predictably, ChatGPT pointed out public details that had been commonly released in global report at the time of the mishap - so no surprises there.

WHICH IS MORE CREATIVE?

Users have actually praised the ability of Chinese AI apps to deliver 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 author pipewiki.org Amanda Caswell, who specialises in AI.

"Qwen2.5 provided a story that builds gradually from curiosity to seriousness, keeping the reader engaged. It offers an unanticipated 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 abundant story with a more substantial twist".

"DeepSeek composed a good story however 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 highly as DeepSeek and ChatGPT when it pertains to innovative writing.

"(Qwen2.5) is on par with DeepSeek V3 on certain jobs, however we can likewise see that it is refraining from doing as strongly as others in creative writing," he told CNA.

Related:

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

'Made in China': Pride, pleasant surprise from Chinese netizens as DeepSeek jolts 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 basic sci-fi motion picture plot set 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 appealing storyline set in the year 2145 titled, "Neon Pilgrimage: The Silicon Sutra" - which sees "a future where Buddhism merges with quantum computing".

It consisted of elaborate settings - smoggy skies "pierced by skyscrapers", "holographic lanterns that float above neon-lit streets" and "ancient temples nestled between quantum server farms".

It also remarkably reimagined traditional heroes Sun Wukong as "an ironical, self-aware AI housed in a taken combat body", Zhu Bajie as a cyborg nightclub owner "drowning in debt and vices" and Sha Wujing as a "silent hulking android" from the Yangtze River, whose "memory cores become waterlogged and fragmented".

ChatGPT installed an excellent battle, developing an equally significant cyberpunk story which likewise reimagined "a ragteam of cyber-enhanced misfits, each mirroring 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 difficulty - delivering a storyline that appeared more matched for an animation film.

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

Realising his brand-new truth and "seeking to comprehend his function in this strange new world", he then gets away and fulfills 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 secure the sacred "Eternal Scroll" from falling under the wrong hands.

SO WHICH IS BETTER?

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

Her insight underscores how Chinese AI models are not just replicating Western paradigms, but rather evolving in economical innovation approaches - and forum.batman.gainedge.org delivering localised and improved results.

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

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

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

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

"DeepSeek is at a drawback when it pertains to censorship constraints," kept in mind Isaac Stone Fish, founder and CEO of the research study firm Strategy Risks.

"When offered a choice, Chinese users want the non-censored variation - similar to anyone else, so I feel 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, specifically for Chinese users.

"Ninety per cent of people using the tool are not attempting to get a deeper understanding about Xi Jinping or politically sensitive subjects. They're using it for other productive ways," Chen said.